Publications

Quantitative studies of historical syntax require large amounts of syntactically annotated data, which are rarely available. The application of NLP methods could reduce manual annotation effort, provided that they achieve sufficient levels of accuracy. The present study investigates the automatic identification of chunks in historical German texts. Because no training data exists for this task, chunks are extracted from modern and historical constituency treebanks and used to train a CRF-based neural sequence labeling tool. The evaluation shows that the neural chunker outperforms an unlexicalized baseline and achieves overall F-scores between 90% and 94% for different historical data sets when POS tags are used as feature. The conducted experiments demonstrate the usefulness of including historical training data while also highlighting the importance of reducing boundary errors to improve annotation precision.

• https://aclanthology.org/2021.nodalida-main.19

@inproceedings{Ortmann2021,
title = {Chunking Historical German},
author = {Katrin Ortmann},
url = {https://aclanthology.org/2021.nodalida-main.19},
year = {2021},
date = {2021},
booktitle = {Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)},
pages = {190-199},
publisher = {Link{\"o}ping University Electronic Press, Sweden},
address = {Reykjavik, Iceland (Online)},
abstract = {Quantitative studies of historical syntax require large amounts of syntactically annotated data, which are rarely available. The application of NLP methods could reduce manual annotation effort, provided that they achieve sufficient levels of accuracy. The present study investigates the automatic identification of chunks in historical German texts. Because no training data exists for this task, chunks are extracted from modern and historical constituency treebanks and used to train a CRF-based neural sequence labeling tool. The evaluation shows that the neural chunker outperforms an unlexicalized baseline and achieves overall F-scores between 90% and 94% for different historical data sets when POS tags are used as feature. The conducted experiments demonstrate the usefulness of including historical training data while also highlighting the importance of reducing boundary errors to improve annotation precision.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

This paper reports on two experiments that partially replicate an experiment by Fraundorf and Watson (2011, J Mem. Lang.) on the recall effect of filler particles. Their subjects listened to three passages of a story, either with or without filler particles, which they had to retell afterwards. They analysed the subject‘ retelling in terms of whether important plot points were remem- bered or not. For their English data, they found that filler parti- cles facilitate the recall of the plot points significantly compared to stories that did not include filler particles. As this seems to be a convincing experimental design, we aimed at evaluating this method as a web-based experiment which may, if found to be suitable, easily be applied to other languages. Furthermore, we investigated whether their results are found in German as well (Experiment 1), and evaluated whether filler duration has an ef- fect on recall performance (Experiment 2). Our results could not replicate the findings of the original study: in fact, the op- posite effect was found for German. In Experiment 1, participants performed better on recall in the fluent condition, while no significant results were found for English in Experiment 2.

• Muhlack_et_al_2021     (0.19MB)
• https://www.isca-speech.org/archive/interspeech_2021/muhlack21_interspeech.html
• https://doi.org/10.21437/Interspeech.2021-1056

@inproceedings{Muhlack2021,
title = {Revisiting recall effects of filler particles in German and English},
author = {Beeke Muhlack and Mikey Elmers and Heiner Drenhaus and Marjolein van Os and Raphael Werner and Margarita Ryzhova and Bernd M{\"o}bius},
url = {https://www.isca-speech.org/archive/interspeech_2021/muhlack21_interspeech.html},
doi = {https://doi.org/10.21437/Interspeech.2021-1056},
year = {2021},
date = {2021},
booktitle = {Proceedings of Interspeech 2021},
pages = {3979-3983},
publisher = {Interspeech},
address = {Brno, Czechia},
abstract = {This paper reports on two experiments that partially replicate an experiment by Fraundorf and Watson (2011, J Mem. Lang.) on the recall effect of filler particles. Their subjects listened to three passages of a story, either with or without filler particles, which they had to retell afterwards. They analysed the subject' retelling in terms of whether important plot points were remem- bered or not. For their English data, they found that filler parti- cles facilitate the recall of the plot points significantly compared to stories that did not include filler particles. As this seems to be a convincing experimental design, we aimed at evaluating this method as a web-based experiment which may, if found to be suitable, easily be applied to other languages. Furthermore, we investigated whether their results are found in German as well (Experiment 1), and evaluated whether filler duration has an ef- fect on recall performance (Experiment 2). Our results could not replicate the findings of the original study: in fact, the op- posite effect was found for German. In Experiment 1, participants performed better on recall in the fluent condition, while no significant results were found for English in Experiment 2.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

The International Planning Competition (IPC) in 2020 wasthe first one for a long time to host tracks on Hierarchical Task Network (HTN) planning. HYPERTENSION, the winner of the tack on totally-ordered problems, comes with an interesting technique: it stores parts of the decomposition path in the state to mark expanded tasks and forces its depth first search to leave recursive structures in the hierarchy. This can be seen as a form of loop detection (LD) – a technique that is not very common in HTN planning. This might be due to the spirit of encoding enough advice in the model to find plans (so that loop detection is simply not necessary), or because it becomes a computationally hard task in the general (i.e. partially-ordered) setting. We integrated several approximate and exact techniques for LD into the progression search of the HTN planner PANDA. We test our techniques on the benchmark set of the IPC 2020. Both in the partial ordered and total ordered track, PANDA with LD performs better than the respective winner of the competition.

• https://ojs.aaai.org/index.php/ICAPS/article/view/15959

@inproceedings{hoeller-behnke-21-LD,
title = {Loop Detection in the PANDA Planning System},
author = {Daniel H{\"o}ller and Gregor Behnke},
url = {https://ojs.aaai.org/index.php/ICAPS/article/view/15959},
year = {2021},
date = {2021-07-21},
booktitle = {Proceedings of the 31st International Conference on Automated Planning and Scheduling (ICAPS)},
pages = {168-173},
publisher = {AAAI Press},
abstract = {The International Planning Competition (IPC) in 2020 wasthe first one for a long time to host tracks on Hierarchical Task Network (HTN) planning. HYPERTENSION, the winner of the tack on totally-ordered problems, comes with an interesting technique: it stores parts of the decomposition path in the state to mark expanded tasks and forces its depth first search to leave recursive structures in the hierarchy. This can be seen as a form of loop detection (LD) – a technique that is not very common in HTN planning. This might be due to the spirit of encoding enough advice in the model to find plans (so that loop detection is simply not necessary), or because it becomes a computationally hard task in the general (i.e. partially-ordered) setting. We integrated several approximate and exact techniques for LD into the progression search of the HTN planner PANDA. We test our techniques on the benchmark set of the IPC 2020. Both in the partial ordered and total ordered track, PANDA with LD performs better than the respective winner of the competition.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

There have been several approaches to use techniques from classical planning in HTN planning. While a direct translation is in general not possible due to the different expressiveness, there have been translations of bounded HTN problems and approaches to use classical heuristics in HTN search procedures. In this paper, we introduce a different approach. We exploit methods from the field of Computational Linguistics introduced to approximate Context-Free Languages by Finite Automata. We use them to approximate the decomposition structure of Totally Ordered (TO) HTN planning problems by classical problems. The resulting problem can then be solved using standard classical planning systems. A subset of TOHTN problems can be translated exactly, i.e., without changing the set of solutions. For problems where an approximation is necessary, we use an overapproximation, i.e., the set of solutions to the classical problem is a superset of that of the HTN problem. We then use plan verification to check whether a solution is valid and thus obtain a sound and complete overall approach. The resulting system outperforms the state of the art on the IPC 2020 benchmark set in terms of coverage.

• https://ojs.aaai.org/index.php/ICAPS/article/view/15958

@inproceedings{hoeller-21-toad,
title = {Translating Totally Ordered HTN Planning Problems to Classical Planning Problems Using Regular Approximation of Context-Free Languages},
author = {Daniel H{\"o}ller},
url = {https://ojs.aaai.org/index.php/ICAPS/article/view/15958},
year = {2021},
date = {2021},
booktitle = {Proceedings of the 31st International Conference on Automated Planning and Scheduling (ICAPS)},
pages = {159-167},
publisher = {AAAI Press},
abstract = {There have been several approaches to use techniques from classical planning in HTN planning. While a direct translation is in general not possible due to the different expressiveness, there have been translations of bounded HTN problems and approaches to use classical heuristics in HTN search procedures. In this paper, we introduce a different approach. We exploit methods from the field of Computational Linguistics introduced to approximate Context-Free Languages by Finite Automata. We use them to approximate the decomposition structure of Totally Ordered (TO) HTN planning problems by classical problems. The resulting problem can then be solved using standard classical planning systems. A subset of TOHTN problems can be translated exactly, i.e., without changing the set of solutions. For problems where an approximation is necessary, we use an overapproximation, i.e., the set of solutions to the classical problem is a superset of that of the HTN problem. We then use plan verification to check whether a solution is valid and thus obtain a sound and complete overall approach. The resulting system outperforms the state of the art on the IPC 2020 benchmark set in terms of coverage.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Abstract: Polynomial-time heuristic functions for planning are commonplace since 20 years. But polynomial-time in which input? Almost all existing approaches are based on a grounded task representation, not on the actual PDDL input which is exponentially smaller. This limits practical applicability to cases where the grounded representation is „small enough“. Previous attempts to tackle this problem for the delete relaxation leveraged symmetries to reduce the blow-up. Here we take a more radical approach, applying an additional relaxation to obtain a heuristic function that runs in time polynomial in the size of the PDDL input. Our relaxation splits the predicates into smaller predicates of fixed arity K. We show that computing a relaxed plan is still NP-hard (in PDDL input size) for K>=2, but is polynomial-time for K=1. We implement a heuristic function for K=1 and show that it can improve the state of the art on benchmarks whose grounded representation is large.

• https://www.ijcai.org/proceedings/2021/567

@inproceedings{lauer-21,
title = {Polynomial-Time in PDDL Input Size: Making the Delete Relaxation Feasible for Lifted Planning},
author = {Pascal Lauer and {\'A}lvaro Torralba and Daniel Fišer and Daniel H{\"o}ller and Julia Wichlacz and J{\"o}rg Hoffmann},
url = {https://www.ijcai.org/proceedings/2021/567},
year = {2021},
date = {2021},
booktitle = {Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI)},
pages = {4119-4126},
publisher = {IJCAI organization},
abstract = {Abstract: Polynomial-time heuristic functions for planning are commonplace since 20 years. But polynomial-time in which input? Almost all existing approaches are based on a grounded task representation, not on the actual PDDL input which is exponentially smaller. This limits practical applicability to cases where the grounded representation is "small enough". Previous attempts to tackle this problem for the delete relaxation leveraged symmetries to reduce the blow-up. Here we take a more radical approach, applying an additional relaxation to obtain a heuristic function that runs in time polynomial in the size of the PDDL input. Our relaxation splits the predicates into smaller predicates of fixed arity K. We show that computing a relaxed plan is still NP-hard (in PDDL input size) for K>=2, but is polynomial-time for K=1. We implement a heuristic function for K=1 and show that it can improve the state of the art on benchmarks whose grounded representation is large.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Planning problems are usually modeled using lifted representations, they specify predicates and action schemas using variables over a finite universe of objects. However, current planning systems like Fast Downward need a grounded (propositional) input model. The process of grounding might result in an exponential blowup of the model size. This limits the application of grounded planning systems in practical applications. Recent work introduced an efficient planning system for lifted heuristic search, but the work on lifted heuristics is still limited. In this extended abstract, we introduce a novel lifted heuristic based on landmarks, which we extract from the lifted problem representation. Preliminary results on a benchmark set specialized to lifted planning show that there are domains where our approach finds enough landmarks to guide the search more effective than the heuristics available.

• https://ojs.aaai.org/index.php/SOCS/article/view/18597

@inproceedings{wichlacz-21,
title = {Landmark Heuristics for Lifted Planning – Extended Abstract},
author = {Julia Wichlacz and Daniel H{\"o}ller and J{\"o}rg Hoffmann},
url = {https://ojs.aaai.org/index.php/SOCS/article/view/18597},
year = {2021},
date = {2021},
booktitle = {Proceedings of the 13th International Symposium on Combinatorial Search (SoCS)},
pages = {242-244},
publisher = {AAAI Press},
abstract = {Planning problems are usually modeled using lifted representations, they specify predicates and action schemas using variables over a finite universe of objects. However, current planning systems like Fast Downward need a grounded (propositional) input model. The process of grounding might result in an exponential blowup of the model size. This limits the application of grounded planning systems in practical applications. Recent work introduced an efficient planning system for lifted heuristic search, but the work on lifted heuristics is still limited. In this extended abstract, we introduce a novel lifted heuristic based on landmarks, which we extract from the lifted problem representation. Preliminary results on a benchmark set specialized to lifted planning show that there are domains where our approach finds enough landmarks to guide the search more effective than the heuristics available.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

• https://www.cambridge.org/core/journals/journal-of-the-international-neuropsychological-society/article/abs/patients-with-amnestic-mci-fail-to-adapt-executive-control-when-repeatedly-tested-with-semantic-verbal-fluency-tasks/E09D9B7801DA02360B056E34E0BD96F7

@article{troger2021patients,
title = {Patients with amnestic MCI Fail to Adapt Executive Control When Repeatedly Tested with Semantic Verbal Fluency Tasks},
author = {Johannes Tr{\"o}ger and Hali Lindsay and Mario Mina and Nicklas Linz and Stefan Kl{\"o}ppel and Jutta Kray and Jessica Peter},
url = {https://www.cambridge.org/core/journals/journal-of-the-international-neuropsychological-society/article/abs/patients-with-amnestic-mci-fail-to-adapt-executive-control-when-repeatedly-tested-with-semantic-verbal-fluency-tasks/E09D9B7801DA02360B056E34E0BD96F7},
year = {2021},
date = {2021-06-30},
journal = {Journal of the International Neuropsychological Society},
pages = {1-8},
publisher = {Cambridge University Press},
abstract = {

Copy BibTeX to Clipboard

Phonetic structures expand temporally and spectrally when they are difficult to predict from their context. To some extent, effects of predictability are modulated by prosodic structure. So far, studies on the impact of contextual predictability and prosody on phonetic structures have neglected the dynamic nature of the speech signal. This study investigates the impact of predictability and prominence on the dynamic structure of the first and second formants of German vowels. We expect to find differences in the formant movements between vowels standing in different predictability contexts and a modulation of this effect by prominence. First and second formant values are extracted from a large German corpus. Formant trajectories of peripheral vowels are modeled using generalized additive mixed models, which estimate nonlinear regressions between a dependent variable and predictors. Contextual predictability is measured as biphone and triphone surprisal based on a statistical German language model. We test for the effects of the information-theoretic measures surprisal and word frequency, as well as prominence, on formant movement, while controlling for vowel phonemes and duration. Primary lexical stress and vowel phonemes are significant predictors of first and second formant trajectory shape. We replicate previous findings that vowels are more dispersed in stressed syllables than in unstressed syllables. The interaction of stress and surprisal explains formant movement: unstressed vowels show more variability in their formant trajectory shape at different surprisal levels than stressed vowels. This work shows that effects of contextual predictability on fine phonetic detail can be observed not only in pointwise measures but also in dynamic features of phonetic segments.

• https://www.frontiersin.org/articles/10.3389/fcomm.2021.643528/full
• https://doi.org/10.3389/fcomm.2021.643528

@article{Brandt/etal:2021,
title = {Dynamic Formant Trajectories in German Read Speech: Impact of Predictability and Prominence},
author = {Erika Brandt and Bernd M{\"o}bius and Bistra Andreeva},
url = {https://www.frontiersin.org/articles/10.3389/fcomm.2021.643528/full},
doi = {https://doi.org/10.3389/fcomm.2021.643528},
year = {2021},
date = {2021-06-21},
journal = {Frontiers in Communication, section Language Sciences},
pages = {1-15},
volume = {6},
number = {643528},
abstract = {Phonetic structures expand temporally and spectrally when they are difficult to predict from their context. To some extent, effects of predictability are modulated by prosodic structure. So far, studies on the impact of contextual predictability and prosody on phonetic structures have neglected the dynamic nature of the speech signal. This study investigates the impact of predictability and prominence on the dynamic structure of the first and second formants of German vowels. We expect to find differences in the formant movements between vowels standing in different predictability contexts and a modulation of this effect by prominence. First and second formant values are extracted from a large German corpus. Formant trajectories of peripheral vowels are modeled using generalized additive mixed models, which estimate nonlinear regressions between a dependent variable and predictors. Contextual predictability is measured as biphone and triphone surprisal based on a statistical German language model. We test for the effects of the information-theoretic measures surprisal and word frequency, as well as prominence, on formant movement, while controlling for vowel phonemes and duration. Primary lexical stress and vowel phonemes are significant predictors of first and second formant trajectory shape. We replicate previous findings that vowels are more dispersed in stressed syllables than in unstressed syllables. The interaction of stress and surprisal explains formant movement: unstressed vowels show more variability in their formant trajectory shape at different surprisal levels than stressed vowels. This work shows that effects of contextual predictability on fine phonetic detail can be observed not only in pointwise measures but also in dynamic features of phonetic segments.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

This contribution seeks to provide a rational probabilistic explanation for the intelligibility of words in a genetically related language that is unknown to the reader, a phenomenon referred to as intercomprehension. In this research domain, linguistic distance, among other factors, was proved to correlate well with the mutual intelligibility of individual words. However, the role of context for the intelligibility of target words in sentences was subject to very few studies. To address this, we analyze data from web-based experiments in which Czech (CS) respondents were asked to translate highly predictable target words at the final position of Polish sentences. We compare correlations of target word intelligibility with data from 3-g language models (LMs) to their correlations with data obtained from context-aware LMs. More specifically, we evaluate two context-aware LM architectures: Long Short-Term Memory (LSTMs) that can, theoretically, take infinitely long-distance dependencies into account and Transformer-based LMs which can access the whole input sequence at the same time. We investigate how their use of context affects surprisal and its correlation with intelligibility.

• https://www.frontiersin.org/articles/10.3389/fpsyg.2021.662277/full
• https://doi.org/10.3389/fpsyg.2021.662277

@article{10.3389/fpsyg.2021.662277,
title = {On the Correlation of Context-Aware Language Models With the Intelligibility of Polish Target Words to Czech Readers},
author = {Kl{\'a}ra J{\'a}grov{\'a} and Michael Hedderich and Marius Mosbach and Tania Avgustinova and Dietrich Klakow},
url = {https://www.frontiersin.org/articles/10.3389/fpsyg.2021.662277/full},
doi = {https://doi.org/10.3389/fpsyg.2021.662277},
year = {2021},
date = {2021},
journal = {Frontiers in Psychology},
pages = {2296},
volume = {12},
abstract = {This contribution seeks to provide a rational probabilistic explanation for the intelligibility of words in a genetically related language that is unknown to the reader, a phenomenon referred to as intercomprehension. In this research domain, linguistic distance, among other factors, was proved to correlate well with the mutual intelligibility of individual words. However, the role of context for the intelligibility of target words in sentences was subject to very few studies. To address this, we analyze data from web-based experiments in which Czech (CS) respondents were asked to translate highly predictable target words at the final position of Polish sentences. We compare correlations of target word intelligibility with data from 3-g language models (LMs) to their correlations with data obtained from context-aware LMs. More specifically, we evaluate two context-aware LM architectures: Long Short-Term Memory (LSTMs) that can, theoretically, take infinitely long-distance dependencies into account and Transformer-based LMs which can access the whole input sequence at the same time. We investigate how their use of context affects surprisal and its correlation with intelligibility.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

We report on a study of the specific linguistic properties of cross-linguistically mediated communication, comparing written and spoken translation (simultaneous interpreting) in the domain of European Parliament discourse. Specifically, we compare translations and interpreting with target language original texts/speeches in terms of (a) predefined features commonly used for translationese detection, and (b) features derived in a data-driven fashion from translation and interpreting corpora. For the latter, we use n-gram language models combined with relative entropy (Kullback-Leibler Divergence). We set up a number of classification tasks comparing translations with comparable texts originally written in the target language and interpreted speeches with target language comparable speeches to assess the contributions of predefined and data-driven features to the distinction between translation, interpreting and originals. Our analysis reveals that interpreting is more distinct from comparable originals than translation and that its most distinctive features signal an overemphasis of oral, online production more than showing traces of cross-linguistically mediated communication.

• https://aclanthology.org/2021.motra-1.9/

@inproceedings{LapshinovaEtAl2021interp,
title = {Found in translation/interpreting: combining data-driven and supervised methods to analyse cross-linguistically mediated communication},
author = {Ekaterina Lapshinova-Koltunski and Yuri Bizzoni and Heike Przybyl and Elke Teich},
url = {https://aclanthology.org/2021.motra-1.9/},
year = {2021},
date = {2021-05-31},
booktitle = {Proceedings of the Workshop on Modelling Translation: Translatology in the Digital Age (MoTra21)},
pages = {82-90},
publisher = {Association for Computational Linguistics},
address = {online},
abstract = {We report on a study of the specific linguistic properties of cross-linguistically mediated communication, comparing written and spoken translation (simultaneous interpreting) in the domain of European Parliament discourse. Specifically, we compare translations and interpreting with target language original texts/speeches in terms of (a) predefined features commonly used for translationese detection, and (b) features derived in a data-driven fashion from translation and interpreting corpora. For the latter, we use n-gram language models combined with relative entropy (Kullback-Leibler Divergence). We set up a number of classification tasks comparing translations with comparable texts originally written in the target language and interpreted speeches with target language comparable speeches to assess the contributions of predefined and data-driven features to the distinction between translation, interpreting and originals. Our analysis reveals that interpreting is more distinct from comparable originals than translation and that its most distinctive features signal an overemphasis of oral, online production more than showing traces of cross-linguistically mediated communication.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Recent work has shown that linguistic and visual contexts jointly modulate linguistic expectancy and, thus, the processing effort for a (more or less) expected critical word (Ankener et al., 2018; Tourtouri et al., 2019; Staudte et al., 2020). According to these findings, uncertainty about the upcoming referent in a visually-situated sentence can be reduced by exploiting the selectional restrictions of a preceding word (e.g., a verb or an adjective), which then reduces processing effort on the critical word (e.g., a referential noun). Interestingly, however, no such modulation was observed in these studies on the expectation-generating word itself. The goal of the current study is to investigate whether the reduction of uncertainty (i.e., the generation of expectations) simply does not modulate processing effort — or whether the particular subject-verb-object (SVO) sentence structure used in these studies (which emphasizes the referential nature of the noun as direct pointer to visually co-present objects) accounts for the observed pattern. To test these questions, the current design reverses the functional roles of nouns and verbs by using sentence constructions in which the noun reduces uncertainty about upcoming verbs, and the verb provides the disambiguating and reference-resolving piece of information. Experiment~1 (a Visual World Paradigm study) and Experiment~2 (a Grammaticality Maze study) both replicate the effect found in Ankener et al. (2018) of visually-situated context on the word which uniquely identifies the referent, albeit on the verb in the current study. Results on the noun, where uncertainty is reduced and expectations are generated in the current design, were mixed and were most likely influenced by design decisions specific to each experiment. These results show that processing of the reference-resolving word — whether it be a noun or a verb — reliably benefits from the prior linguistic and visual information that lead to the generation of concrete expectations.

• https://www.frontiersin.org/articles/10.3389/fpsyg.2021.661898/full
• https://doi.org/10.3389/fpsyg.2021.661898

@article{Sikos2021b,
title = {A rose by any other verb: The effect of expectations and word category on processing effort in situated sentence comprehension},
author = {Les Sikos and Maria Staudte},
url = {https://www.frontiersin.org/articles/10.3389/fpsyg.2021.661898/full},
doi = {https://doi.org/10.3389/fpsyg.2021.661898},
year = {2021},
date = {2021},
journal = {Frontiers in Psychology},
abstract = {Recent work has shown that linguistic and visual contexts jointly modulate linguistic expectancy and, thus, the processing effort for a (more or less) expected critical word (Ankener et al., 2018; Tourtouri et al., 2019; Staudte et al., 2020). According to these findings, uncertainty about the upcoming referent in a visually-situated sentence can be reduced by exploiting the selectional restrictions of a preceding word (e.g., a verb or an adjective), which then reduces processing effort on the critical word (e.g., a referential noun). Interestingly, however, no such modulation was observed in these studies on the expectation-generating word itself. The goal of the current study is to investigate whether the reduction of uncertainty (i.e., the generation of expectations) simply does not modulate processing effort --- or whether the particular subject-verb-object (SVO) sentence structure used in these studies (which emphasizes the referential nature of the noun as direct pointer to visually co-present objects) accounts for the observed pattern. To test these questions, the current design reverses the functional roles of nouns and verbs by using sentence constructions in which the noun reduces uncertainty about upcoming verbs, and the verb provides the disambiguating and reference-resolving piece of information. Experiment~1 (a Visual World Paradigm study) and Experiment~2 (a Grammaticality Maze study) both replicate the effect found in Ankener et al. (2018) of visually-situated context on the word which uniquely identifies the referent, albeit on the verb in the current study. Results on the noun, where uncertainty is reduced and expectations are generated in the current design, were mixed and were most likely influenced by design decisions specific to each experiment. These results show that processing of the reference-resolving word --- whether it be a noun or a verb --- reliably benefits from the prior linguistic and visual information that lead to the generation of concrete expectations.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

Rational accounts of language use such as the uniform information density hypothesis, which asserts that speakers distribute information uniformly across their utterances, and the rational speech act (RSA) model, which suggests that speakers optimize the formulation of their message by reasoning about what the comprehender would understand, have been hypothesized to account for a wide range of language use phenomena. We here specifically focus on the production of discourse connectives. While there is some prior work indicating that discourse connective production may be governed by RSA, that work uses a strongly gamified experimental setting. In this study, we aim to explore whether speakers reason about the interpretation of their conversational partner also in more realistic settings. We thereby systematically vary the task setup to tease apart effects of task instructions and effects of the speaker explicitly seeing the interpretation alternatives for the listener. Our results show that the RSA-predicted effect of connective choice based on reasoning about the listener is only found in the original setting where explicit interpretation alternatives of the listener are available for the speaker. The effect disappears when the speaker has to reason about listener interpretations. We furthermore find that rational effects are amplified by the gamified task setting, indicating that meta-reasoning about the specific task may play an important role and potentially limit the generalizability of the found effects to more naturalistic every-day language use.

• https://www.frontiersin.org/article/10.3389/fpsyg.2021.660730
• https://doi.org/10.3389/fpsyg.2021.660730

@article{yungJungbluthDemberg2021,
title = {Limits to the Rational Production of Discourse Connectives},
author = {Frances Pik Yu Yung and Jana Jungbluth and Vera Demberg},
url = {https://www.frontiersin.org/article/10.3389/fpsyg.2021.660730},
doi = {https://doi.org/10.3389/fpsyg.2021.660730},
year = {2021},
date = {2021-05-28},
journal = {Frontiers in Psychology},
pages = {1729},
volume = {12},
abstract = {Rational accounts of language use such as the uniform information density hypothesis, which asserts that speakers distribute information uniformly across their utterances, and the rational speech act (RSA) model, which suggests that speakers optimize the formulation of their message by reasoning about what the comprehender would understand, have been hypothesized to account for a wide range of language use phenomena. We here specifically focus on the production of discourse connectives. While there is some prior work indicating that discourse connective production may be governed by RSA, that work uses a strongly gamified experimental setting. In this study, we aim to explore whether speakers reason about the interpretation of their conversational partner also in more realistic settings. We thereby systematically vary the task setup to tease apart effects of task instructions and effects of the speaker explicitly seeing the interpretation alternatives for the listener. Our results show that the RSA-predicted effect of connective choice based on reasoning about the listener is only found in the original setting where explicit interpretation alternatives of the listener are available for the speaker. The effect disappears when the speaker has to reason about listener interpretations. We furthermore find that rational effects are amplified by the gamified task setting, indicating that meta-reasoning about the specific task may play an important role and potentially limit the generalizability of the found effects to more naturalistic every-day language use.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

This paper provides an overview of metadata generation and management for the Royal Society Corpus (RSC), aiming to encourage discussion about the specific challenges in building substantial diachronic corpora intended to be used for linguistic and humanistic analysis. We discuss the motivations and goals of building the corpus, describe its composition and present the types of metadata it contains. Specifically, we tackle two challenges: first, integration of original metadata from the data providers (JSTOR and the Royal Society); second, derivation of additional linguistically relevant metadata regarding text structure and situational context (register).

• https://ricl.aelinco.es/index.php/ricl/article/view/158
• https://doi.org/10.32714/ricl.09.01.02

@article{Menzel2021,
title = {Generating linguistically relevant metadata for the Royal Society Corpus},
author = {Katrin Menzel and J{\"o}rg Knappen and Elke Teich},
editor = {Tanja S{\"a}ily and Jukka Tyrkk{\"o}},
url = {https://ricl.aelinco.es/index.php/ricl/article/view/158},
doi = {https://doi.org/10.32714/ricl.09.01.02},
year = {2021},
date = {2021},
journal = {Research in Corpus Linguistics, Challenges in combining structured and unstructured data in corpus development (special issue)},
pages = {1-18},
volume = {9},
number = {1},
abstract = {This paper provides an overview of metadata generation and management for the Royal Society Corpus (RSC), aiming to encourage discussion about the specific challenges in building substantial diachronic corpora intended to be used for linguistic and humanistic analysis. We discuss the motivations and goals of building the corpus, describe its composition and present the types of metadata it contains. Specifically, we tackle two challenges: first, integration of original metadata from the data providers (JSTOR and the Royal Society); second, derivation of additional linguistically relevant metadata regarding text structure and situational context (register).},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

We investigate the underexplored question of when speakers make use of the omission phenomenon verb phrase ellipsis (VPE) in English given that the full form is also available to them. We base the interpretation of our results on the well-established information-theoretic Uniform Information Density (UID) hypothesis: Speakers tend to distribute processing effort uniformly across utterances and avoid regions of low information by omitting redundant material through, e.g., VPE. We investigate the length of the omittable VP and its predictability in context as sources of redundancy which lead to larger or deeper regions of low information and an increased pressure to use ellipsis. We use both naturalness rating and self-paced reading studies in order to link naturalness patterns to potential processing difficulties. For the length effects our rating and reading results support a UID account. Surprisingly, we do not find an effect of the context on the naturalness and the processing of VPE. We suggest that our manipulation might have been too weak or not effective to evidence such an effect.

• https://www.frontiersin.org/articles/10.3389/fpsyg.2021.661087/full
• https://doi.org/10.3389/fpsyg.2021.661087

@article{schaeferetal_2021b,
title = {The Role of UID for the Usage of Verb Phrase Ellipsis: Psycholinguistic Evidence From Length and Context Effects},
author = {Lisa Sch{\"a}fer and Tyll Robin Lemke and Heiner Drenhaus and Ingo Reich},
url = {https://www.frontiersin.org/articles/10.3389/fpsyg.2021.661087/full},
doi = {https://doi.org/10.3389/fpsyg.2021.661087},
year = {2021},
date = {2021-05-26},
journal = {Frontiers in Psychology},
pages = {1672},
volume = {12},
abstract = {We investigate the underexplored question of when speakers make use of the omission phenomenon verb phrase ellipsis (VPE) in English given that the full form is also available to them. We base the interpretation of our results on the well-established information-theoretic Uniform Information Density (UID) hypothesis: Speakers tend to distribute processing effort uniformly across utterances and avoid regions of low information by omitting redundant material through, e.g., VPE. We investigate the length of the omittable VP and its predictability in context as sources of redundancy which lead to larger or deeper regions of low information and an increased pressure to use ellipsis. We use both naturalness rating and self-paced reading studies in order to link naturalness patterns to potential processing difficulties. For the length effects our rating and reading results support a UID account. Surprisingly, we do not find an effect of the context on the naturalness and the processing of VPE. We suggest that our manipulation might have been too weak or not effective to evidence such an effect.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

German allows for topic drop (Fries1988), the omission of a preverbal constituent from a V2 sentence. I address the underexplored question of why speakers use topic drop with a corpus study and two acceptability rating studies. I propose an information-theoretic explanation based on the Uniform Information Density hypothesis (Levy and Jaeger2007) that accounts for the full picture of data. The information-theoretic approach predicts that topic drop is more felicitous when the omitted constituent is predictable in context and easy to recover. This leads to a more optimal use of the hearer’s processing capacities. The corpus study on the FraC corpus (Horch and Reich2017) shows that grammatical person, verb probability and verbal inflection impact the frequency of topic drop. The two rating experiments indicate that these differences in frequency are also reflected in acceptability and additionally evidence an impact of topicality on topic drop. Taken together my studies constitute the first systematic empirical investigation of previously only sparsely researched observations from the literature. My information-theoretic account provides a unifying explanation of these isolated observations and is also able to account for the effect of verb probability that I find in my corpus study.

• https://www.degruyter.com/document/doi/10.1515/zfs-2021-2024/html
• https://doi.org/10.1515/zfs-2021-2024

@article{schaefer_2021a,
title = {Topic drop in German: Empirical support for an information-theoretic account to a long-known omission phenomenon},
author = {Lisa Sch{\"a}fer},
url = {https://www.degruyter.com/document/doi/10.1515/zfs-2021-2024/html},
doi = {https://doi.org/10.1515/zfs-2021-2024},
year = {2021},
date = {2021-05-19},
journal = {Zeitschrift f{\"u}r Sprachwissenschaft},
pages = {161-197},
volume = {40},
number = {2},
abstract = {German allows for topic drop (Fries1988), the omission of a preverbal constituent from a V2 sentence. I address the underexplored question of why speakers use topic drop with a corpus study and two acceptability rating studies. I propose an information-theoretic explanation based on the Uniform Information Density hypothesis (Levy and Jaeger2007) that accounts for the full picture of data. The information-theoretic approach predicts that topic drop is more felicitous when the omitted constituent is predictable in context and easy to recover. This leads to a more optimal use of the hearer’s processing capacities. The corpus study on the FraC corpus (Horch and Reich2017) shows that grammatical person, verb probability and verbal inflection impact the frequency of topic drop. The two rating experiments indicate that these differences in frequency are also reflected in acceptability and additionally evidence an impact of topicality on topic drop. Taken together my studies constitute the first systematic empirical investigation of previously only sparsely researched observations from the literature. My information-theoretic account provides a unifying explanation of these isolated observations and is also able to account for the effect of verb probability that I find in my corpus study.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

Prediction facilitates word processing in the moment, but the longer-term consequences of prediction remain unclear. We investigated whether prediction error during language encoding enhances memory for words later on. German-speaking participants read sentences in which the gender marking of the pre-nominal article was consistent or inconsistent with the predictable noun. During subsequent word recognition, we probed participants’ recognition memory for predictable and unpredictable nouns. Our results indicate that individuals who demonstrated early prediction error during sentence reading, showed enhanced recognition memory for nouns overall. Results from an exploratory step-wise regression showed that prenominal prediction error and general reading speed were the best proxies for recognition memory. Hence, prediction error may facilitate recognition by furnishing memory traces built during initial reading of the sentences. Results are discussed in the light of hypotheses positing that predictable words show a memory disadvantage because they are processed less thoroughly.

• https://www.tandfonline.com/doi/full/10.1080/23273798.2021.1924387
• https://doi.org/10.1080/23273798.2021.1924387

@article{haeuser2021effects,
title = {Effects of prediction error on episodic memory retrieval: evidence from sentence reading and word recognition},
author = {Katja H{\"a}user and Jutta Kray},
url = {https://www.tandfonline.com/doi/full/10.1080/23273798.2021.1924387},
doi = {https://doi.org/10.1080/23273798.2021.1924387},
year = {2021},
date = {2021},
journal = {Language, Cognition and Neuroscience},
pages = {1-17},
publisher = {Taylor & Francis},
abstract = {Prediction facilitates word processing in the moment, but the longer-term consequences of prediction remain unclear. We investigated whether prediction error during language encoding enhances memory for words later on. German-speaking participants read sentences in which the gender marking of the pre-nominal article was consistent or inconsistent with the predictable noun. During subsequent word recognition, we probed participants’ recognition memory for predictable and unpredictable nouns. Our results indicate that individuals who demonstrated early prediction error during sentence reading, showed enhanced recognition memory for nouns overall. Results from an exploratory step-wise regression showed that prenominal prediction error and general reading speed were the best proxies for recognition memory. Hence, prediction error may facilitate recognition by furnishing memory traces built during initial reading of the sentences. Results are discussed in the light of hypotheses positing that predictable words show a memory disadvantage because they are processed less thoroughly.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

Top-down predictive processes and bottom-up auditory processes interact in speech comprehension. In background noise, the acoustic signal is degraded. This study investigated the interaction of these processes in a word recognition paradigm using high and low predictability sentences in two types of background noise and using phonetically controlled contrasts. Previous studies have reported false hearing, but have not provided insight into what phonetic features are most prone to false hearing. We here systematically explore this issue and find that plosives lead to increased false hearing compared to vowels. Furthermore, this study on German for the first time replicates the overall false hearing effect in young adults for a language other than English.

• https://escholarship.org/uc/item/70z995v4

@inproceedings{vanOs2021,
title = {Recognition of minimal pairs in (un)predictive sentence contexts in two types of noise},
author = {Marjolein van Os and Jutta Kray and Vera Demberg},
url = {https://escholarship.org/uc/item/70z995v4},
year = {2021},
date = {2021},
booktitle = {Proceedings of the 43rd Annual Meeting of the Cognitive Science Society (CogSci)},
pages = {2943-2949},
abstract = {Top-down predictive processes and bottom-up auditory processes interact in speech comprehension. In background noise, the acoustic signal is degraded. This study investigated the interaction of these processes in a word recognition paradigm using high and low predictability sentences in two types of background noise and using phonetically controlled contrasts. Previous studies have reported false hearing, but have not provided insight into what phonetic features are most prone to false hearing. We here systematically explore this issue and find that plosives lead to increased false hearing compared to vowels. Furthermore, this study on German for the first time replicates the overall false hearing effect in young adults for a language other than English.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

The Uniform Information Density hypothesis (UID) predicts that lexical choice between long and short word forms depends on the predictability of the referent in context, and recent studies have shown such an effect of predictability on lexical choice during online production. We here set out to test whether the UID predictions hold up in a related setting, but different language (German) and different phenomenon, namely the choice between compounds (e.g. Badewanne / bathtub) or their base forms (Wanne / tub). Our study is consistent with the UID: we find that participants choose the shorter base form more often in predictive contexts, showing an active tendency to be information-theoretically efficient.

• https://escholarship.org/uc/item/3w6451rz

@inproceedings{Zarcone2021,
title = {A bathtub by any other name: the reduction of german compounds in predictive contexts},
author = {Alessandra Zarcone and Vera Demberg},
url = {https://escholarship.org/uc/item/3w6451rz},
year = {2021},
date = {2021},
booktitle = {Proceedings of the Annual Meeting of the Cognitive Science Society},
abstract = {The Uniform Information Density hypothesis (UID) predicts that lexical choice between long and short word forms depends on the predictability of the referent in context, and recent studies have shown such an effect of predictability on lexical choice during online production. We here set out to test whether the UID predictions hold up in a related setting, but different language (German) and different phenomenon, namely the choice between compounds (e.g. Badewanne / bathtub) or their base forms (Wanne / tub). Our study is consistent with the UID: we find that participants choose the shorter base form more often in predictive contexts, showing an active tendency to be information-theoretically efficient.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

The present chapter applies text classification to test how well we can distinguish between texts along two dimensions: a text-production dimension that distinguishes between translations and non-translations (where translations also include interpreted texts); and a mode dimension that distinguishes between and spoken and written texts. The chapter also aims to investigate the relationship between these two dimensions. Moreover, it investigates whether the same linguistic features that are derived from variational linguistics contribute to the prediction of mode in both translations and non-translations. The distributional information about these features was used to statistically model variation along the two dimensions. The results show that the same feature set can be used to automatically differentiate translations from non-translations, as well as spoken texts from the written texts. However, language variation along the dimension of mode is stronger
than that along the dimension of text production, as classification into spoken and written texts delivers better results. Besides, linguistic features that contribute to the distinction between spoken and written mode are similar in both translated and non-translated language.

• https://doi.org/10.5281/zenodo.4450014
• https://doi.org/10.5281/zenodo.4450014

@inbook{Lapshinova2021dimension,
title = {Analysing the Dimension of Mode in Translation},
author = {Ekaterina Lapshinova-Koltunski},
editor = {Mario Bisiada},
url = {https://doi.org/10.5281/zenodo.4450014},
doi = {https://doi.org/10.5281/zenodo.4450014},
year = {2021},
date = {2021},
booktitle = {Empirical Studies in Translation and Discourse. Translation and Multilingual Natural Language Processing},
isbn = {978-3-96110-300-3},
issn = {2364-8899},
pages = {223-243},
publisher = {Language Science Press},
address = {Berlin},
abstract = {The present chapter applies text classification to test how well we can distinguish between texts along two dimensions: a text-production dimension that distinguishes between translations and non-translations (where translations also include interpreted texts); and a mode dimension that distinguishes between and spoken and written texts. The chapter also aims to investigate the relationship between these two dimensions. Moreover, it investigates whether the same linguistic features that are derived from variational linguistics contribute to the prediction of mode in both translations and non-translations. The distributional information about these features was used to statistically model variation along the two dimensions. The results show that the same feature set can be used to automatically differentiate translations from non-translations, as well as spoken texts from the written texts. However, language variation along the dimension of mode is stronger than that along the dimension of text production, as classification into spoken and written texts delivers better results. Besides, linguistic features that contribute to the distinction between spoken and written mode are similar in both translated and non-translated language.},
pubstate = {published},
type = {inbook}
}

Copy BibTeX to Clipboard

The results of a highly influential study that tested the predictions of the Rational Speech Act (RSA) model suggest that (a) listeners use pragmatic reasoning in one-shot web-based referential communication games despite the artificial, highly constrained, and minimally interactive nature of the task, and (b) that RSA accurately captures this behavior. In this work, we reevaluate the contribution of the pragmatic reasoning formalized by RSA in explaining listener behavior by comparing RSA to a baseline literal listener model that is only driven by literal word meaning and the prior probability of referring to an object. Across three experiments we observe only modest evidence of pragmatic behavior in one-shot web-based language games, and only under very limited circumstances. We find that although RSA provides a strong fit to listener responses, it does not perform better than the baseline literal listener model. Our results suggest that while participants playing the role of the Speaker are informative in these one-shot web-based reference games, participants playing the role of the Listener only rarely take this Speaker behavior into account to reason about the intended referent. In addition, we show that RSA’s fit is primarily due to a combination of non-pragmatic factors, perhaps the most surprising of which is that in the majority of conditions that are amenable to pragmatic reasoning, RSA (accurately) predicts that listeners will behave non-pragmatically. This leads us to conclude that RSA’s strong overall correlation with human behavior in one-shot web-based language games does not reflect listener’s pragmatic reasoning about informative speakers.

• https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0248388
• https://doi.org/10.1371/journal.pone.0248388

@article{Sikos2021,
title = {Reevaluating pragmatic reasoning in language games},
author = {Les Sikos and Noortje Venhuizen and Heiner Drenhaus and Matthew W. Crocker},
url = {https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0248388},
doi = {https://doi.org/10.1371/journal.pone.0248388},
year = {2021},
date = {2021-03-17},
journal = {PLOS ONE},
abstract = {The results of a highly influential study that tested the predictions of the Rational Speech Act (RSA) model suggest that (a) listeners use pragmatic reasoning in one-shot web-based referential communication games despite the artificial, highly constrained, and minimally interactive nature of the task, and (b) that RSA accurately captures this behavior. In this work, we reevaluate the contribution of the pragmatic reasoning formalized by RSA in explaining listener behavior by comparing RSA to a baseline literal listener model that is only driven by literal word meaning and the prior probability of referring to an object. Across three experiments we observe only modest evidence of pragmatic behavior in one-shot web-based language games, and only under very limited circumstances. We find that although RSA provides a strong fit to listener responses, it does not perform better than the baseline literal listener model. Our results suggest that while participants playing the role of the Speaker are informative in these one-shot web-based reference games, participants playing the role of the Listener only rarely take this Speaker behavior into account to reason about the intended referent. In addition, we show that RSA’s fit is primarily due to a combination of non-pragmatic factors, perhaps the most surprising of which is that in the majority of conditions that are amenable to pragmatic reasoning, RSA (accurately) predicts that listeners will behave non-pragmatically. This leads us to conclude that RSA’s strong overall correlation with human behavior in one-shot web-based language games does not reflect listener’s pragmatic reasoning about informative speakers.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard