Publications

• https://www.cambridgescholars.com/product/978-1-5275-7432-8

@inbook{Menzel2021_eponyms,
title = {Scientific Eponyms throughout the History of English Scholarly Journal Articles},
author = {Katrin Menzel},
editor = {Hans Van de Velde and Fredric T. Dolezal},
url = {https://www.cambridgescholars.com/product/978-1-5275-7432-8},
year = {2021},
date = {2021-11-08},
booktitle = {Broadening Perspectives in the History of Dictionaries and Word Studies},
isbn = {1-5275-7432-6},
pages = {159-193},
publisher = {Cambridge Scholars Publishing},
address = {Newcastle upon Tyne},
pubstate = {published},
type = {inbook}
}

Copy BibTeX to Clipboard

• https://amlap2021.github.io/program/30.pdf

@inproceedings{haeuserkray2021b,
title = {How odd: Diverging effects of predictability and plausibility on online sentence processing and subsequent word recognition},
author = {Katja H{\"a}user and Jutta Kray},
url = {https://amlap2021.github.io/program/30.pdf},
year = {2021},
date = {2021},
booktitle = {Poster presentation at AMLaP 2021: Architectures and Mechanisms for Language Processing, September 2-4},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Recently, Ankener et al. (Frontiers in Psychology, 9, 2387, 2018) presented a visual world study which combined both attention and pupillary measures to demonstrate that anticipating a target results in lower effort to integrate that target (noun). However, they found no indication that the anticipatory processes themselves, i.e., the reduction of uncertainty about upcoming referents, results in processing effort (cf. Linzen and Jaeger, Cognitive Science, 40(6), 1382–1411, 2016). In contrast, Maess et al. (Frontiers in Human Neuroscience, 10, 1–11, 2016) found that more constraining verbs elicited a higher N400 amplitude than unconstraining verbs. The aim of the present study was therefore twofold: Firstly, we examined whether the graded ICA effect, which was previously found on the noun as a result of a likelihood manipulation, replicates in ERP measures. Secondly, we set out to investigate whether the processes leading to the generation of expectations (derived during verb and scene processing) induce an N400 modulation. Our results confirm that visual context is combined with the verb’s meaning to establish expectations about upcoming nouns and that these expectations affect the retrieval of the upcoming noun (modulated N400 on the noun). Importantly, however, we find no evidence for different costs in generating more or less specific expectations for upcoming nouns. Thus, the benefits of generating expectations are not associated with any costs in situated language comprehension.

• https://link.springer.com/article/10.3758/s13423-020-01827-3
• https://doi.org/10.3758/s13423-020-01827-3

@article{staudte2021,
title = {Graded expectations in visually situated comprehension: Costs and benefits as indexed by the N400},
author = {Maria Staudte and Christine Ankener and Heiner Drenhaus and Matthew W. Crocker},
url = {https://link.springer.com/article/10.3758/s13423-020-01827-3},
doi = {https://doi.org/10.3758/s13423-020-01827-3},
year = {2021},
date = {2021},
journal = {Psychonomic Bulletin & Review},
pages = {624-631},
publisher = {Springer},
volume = {28},
number = {2},
abstract = {Recently, Ankener et al. (Frontiers in Psychology, 9, 2387, 2018) presented a visual world study which combined both attention and pupillary measures to demonstrate that anticipating a target results in lower effort to integrate that target (noun). However, they found no indication that the anticipatory processes themselves, i.e., the reduction of uncertainty about upcoming referents, results in processing effort (cf. Linzen and Jaeger, Cognitive Science, 40(6), 1382–1411, 2016). In contrast, Maess et al. (Frontiers in Human Neuroscience, 10, 1–11, 2016) found that more constraining verbs elicited a higher N400 amplitude than unconstraining verbs. The aim of the present study was therefore twofold: Firstly, we examined whether the graded ICA effect, which was previously found on the noun as a result of a likelihood manipulation, replicates in ERP measures. Secondly, we set out to investigate whether the processes leading to the generation of expectations (derived during verb and scene processing) induce an N400 modulation. Our results confirm that visual context is combined with the verb’s meaning to establish expectations about upcoming nouns and that these expectations affect the retrieval of the upcoming noun (modulated N400 on the noun). Importantly, however, we find no evidence for different costs in generating more or less specific expectations for upcoming nouns. Thus, the benefits of generating expectations are not associated with any costs in situated language comprehension.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

• https://www.frontiersin.org/article/10.3389/frai.2021.609970
• https://doi.org/10.3389/frai.2021.609970

@article{Degaetano-Ortlieb2021,
title = {Registerial Adaptation vs. Innovation Across Situational Contexts: 18th Century Women in Transition},
author = {Stefania Degaetano-Ortlieb and Tanja S{\"a}ily and Yuri Bizzoni},
url = {https://www.frontiersin.org/article/10.3389/frai.2021.609970},
doi = {https://doi.org/10.3389/frai.2021.609970},
year = {2021},
date = {2021},
journal = {Frontiers in Artificial Intelligence, section Language and Computation},
pages = {56},
volume = {4},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

• https://aclanthology.org/2021.nodalida-main.6

@inproceedings{Bizzoni2021,
title = {Measuring Translationese across Levels of Expertise: Are Professionals more Surprising than Students?},
author = {Yuri Bizzoni and Ekaterina Lapshinova-Koltunski},
url = {https://aclanthology.org/2021.nodalida-main.6},
year = {2021},
date = {2021},
booktitle = {Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)},
pages = {53--63},
publisher = {Link{\"o}ping University Electronic Press, Sweden},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Previous studies have shown that at moderate levels of spectral degradation, semantic predictability facilitates language comprehension. It is argued that when speech is degraded, listeners have narrowed expectations about the sentence endings; i.e., semantic prediction may be limited to only most highly predictable sentence completions. The main objectives of this study were to (i) examine whether listeners form narrowed expectations or whether they form predictions across a wide range of probable sentence endings, (ii) assess whether the facilitatory effect of semantic predictability is modulated by perceptual adaptation to degraded speech, and (iii) use and establish a sensitive metric for the measurement of language comprehension. For this, we created 360 German Subject-Verb-Object sentences that varied in semantic predictability of a sentence-final target word in a graded manner (high, medium, and low) and levels of spectral degradation (1, 4, 6, and 8 channels noise-vocoding). These sentences were presented auditorily to two groups: One group (n =48) performed a listening task in an unpredictable channel context in which the degraded speech levels were randomized, while the other group (n =50) performed the task in a predictable channel context in which the degraded speech levels were blocked. The results showed that at 4 channels noise-vocoding, response accuracy was higher in high-predictability sentences than in the medium-predictability sentences, which in turn was higher than in the low-predictability sentences. This suggests that, in contrast to the narrowed expectations view, comprehension of moderately degraded speech, ranging from low- to high- including medium-predictability sentences, is facilitated in a graded manner; listeners probabilistically preactivate upcoming words from a wide range of semantic space, not limiting only to highly probable sentence endings. Additionally, in both channel contexts, we did not observe learning effects; i.e., response accuracy did not increase over the course of experiment, and response accuracy was higher in the predictable than in the unpredictable channel context. We speculate from these observations that when there is no trial-by-trial variation of the levels of speech degradation, listeners adapt to speech quality at a long timescale; however, when there is a trial-by-trial variation of the high-level semantic feature (e.g., sentence predictability), listeners do not adapt to low-level perceptual property (e.g., speech quality) at a short timescale.

• https://www.frontiersin.org/articles/10.3389/fpsyg.2021.714485/full
• https://doi.org/10.3389/fpsyg.2021.714485

@article{bhandari2021semantic,
title = {Semantic Predictability Facilitates Comprehension of Degraded Speech in a Graded Manner},
author = {Pratik Bhandari and Vera Demberg and Jutta Kray},
url = {https://www.frontiersin.org/articles/10.3389/fpsyg.2021.714485/full},
doi = {https://doi.org/10.3389/fpsyg.2021.714485},
year = {2021},
date = {2021-09-09},
journal = {Frontiers in Psychology},
pages = {3769},
publisher = {Frontiers},
abstract = {Previous studies have shown that at moderate levels of spectral degradation, semantic predictability facilitates language comprehension. It is argued that when speech is degraded, listeners have narrowed expectations about the sentence endings; i.e., semantic prediction may be limited to only most highly predictable sentence completions. The main objectives of this study were to (i) examine whether listeners form narrowed expectations or whether they form predictions across a wide range of probable sentence endings, (ii) assess whether the facilitatory effect of semantic predictability is modulated by perceptual adaptation to degraded speech, and (iii) use and establish a sensitive metric for the measurement of language comprehension. For this, we created 360 German Subject-Verb-Object sentences that varied in semantic predictability of a sentence-final target word in a graded manner (high, medium, and low) and levels of spectral degradation (1, 4, 6, and 8 channels noise-vocoding). These sentences were presented auditorily to two groups: One group (n =48) performed a listening task in an unpredictable channel context in which the degraded speech levels were randomized, while the other group (n =50) performed the task in a predictable channel context in which the degraded speech levels were blocked. The results showed that at 4 channels noise-vocoding, response accuracy was higher in high-predictability sentences than in the medium-predictability sentences, which in turn was higher than in the low-predictability sentences. This suggests that, in contrast to the narrowed expectations view, comprehension of moderately degraded speech, ranging from low- to high- including medium-predictability sentences, is facilitated in a graded manner; listeners probabilistically preactivate upcoming words from a wide range of semantic space, not limiting only to highly probable sentence endings. Additionally, in both channel contexts, we did not observe learning effects; i.e., response accuracy did not increase over the course of experiment, and response accuracy was higher in the predictable than in the unpredictable channel context. We speculate from these observations that when there is no trial-by-trial variation of the levels of speech degradation, listeners adapt to speech quality at a long timescale; however, when there is a trial-by-trial variation of the high-level semantic feature (e.g., sentence predictability), listeners do not adapt to low-level perceptual property (e.g., speech quality) at a short timescale.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

• https://aclanthology.org/2021.konvens-1.11

@inproceedings{ortmann-2021b,
title = {Automatic Phrase Recognition in Historical German},
author = {Katrin Ortmann},
url = {https://aclanthology.org/2021.konvens-1.11},
year = {2021},
date = {2021-09-06},
booktitle = {Proceedings of the 17th Conference on Natural Language Processing (KONVENS 2021)},
publisher = {KONVENS 2021 Organizers},
address = {D{\"u}sseldorf, Germany},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

@inproceedings{Pylypenko2021comparing,
title = {Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification},
author = {Daria Pylypenko and Kwabena Amponsah-Kaakyire and Koel Dutta Chowdhury and Josef van Genabith and Cristina Espa{\~n}a i Bonet},
year = {2021},
date = {2021},
booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
address = {Online and in the Dominican Republic},
pubstate = {forthcoming},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Previous research has used linguistic features to show that translations exhibit traces of source language interference and that phylogenetic trees between languages can be reconstructed from the results of translations into the same language. Recent research has shown that instances of translationese (source language interference) can even be detected in embedding spaces, comparing embeddings spaces of original language data with embedding spaces resulting from translations into the same language, using a simple Eigenvectorbased divergence from isomorphism measure. To date, it remains an open question whether alternative graph-isomorphism measures can produce better results. In this paper, we (i) explore Gromov-Hausdorff distance, (ii) present a novel spectral version of the Eigenvectorbased method, and (iii) evaluate all approaches against a broad linguistic typological database (URIEL). We show that language distances resulting from our spectral isomorphism approaches can reproduce genetic trees on a par with previous work without requiring any explicit linguistic information and that the results can be extended to non-Indo-European languages. Finally, we show that the methods are robust under a variety of modeling conditions.

• https://ranlp.org/ranlp2021/proceedings.pdf

@inproceedings{Chowdhury2021tracing,
title = {Tracing Source Language Interference in Translation with Graph-Isomorphism Measures},
author = {Koel Dutta Chowdhury and Cristina Espa{\~n}a i Bonet and Josef van Genabith},
url = {https://ranlp.org/ranlp2021/proceedings.pdf},
year = {2021},
date = {2021},
booktitle = {Proceedings of Recent Advances in Natural Language Processing (RANLP 2021)},
issn = {2603-2813},
pages = {380-390},
address = {Online},
abstract = {Previous research has used linguistic features to show that translations exhibit traces of source language interference and that phylogenetic trees between languages can be reconstructed from the results of translations into the same language. Recent research has shown that instances of translationese (source language interference) can even be detected in embedding spaces, comparing embeddings spaces of original language data with embedding spaces resulting from translations into the same language, using a simple Eigenvectorbased divergence from isomorphism measure. To date, it remains an open question whether alternative graph-isomorphism measures can produce better results. In this paper, we (i) explore Gromov-Hausdorff distance, (ii) present a novel spectral version of the Eigenvectorbased method, and (iii) evaluate all approaches against a broad linguistic typological database (URIEL). We show that language distances resulting from our spectral isomorphism approaches can reproduce genetic trees on a par with previous work without requiring any explicit linguistic information and that the results can be extended to non-Indo-European languages. Finally, we show that the methods are robust under a variety of modeling conditions.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

@miscellaneous{Menzel2021epic,
title = {EPIC-UdS - ein mehrsprachiges Korpus als Grundlage f{\"u}r die korpusbasierte Dolmetsch- und {\"U}bersetzungswissenschaft},
author = {Katrin Menzel and Heike Przybyl and Ekaterina Lapshinova-Koltunski},
year = {2021},
date = {2021},
booktitle = {TRANSLATA IV - 4. Internationale Konferenz zur Translationswissenschaft},
address = {Innsbruck},
pubstate = {forthcoming},
type = {miscellaneous}
}

Copy BibTeX to Clipboard

Fine-tuning pre-trained transformer-based language models such as BERT has become a common practice dominating leaderboards across various NLP benchmarks. Despite the strong empirical performance of fine-tuned models, fine-tuning is an unstable process: training the same model with multiple random seeds can result in a large variance of the task performance. Previous literature (Devlin et al., 2019; Lee et al., 2020; Dodge et al., 2020) identified two potential reasons for the observed instability: catastrophic forgetting and small size of the fine-tuning datasets. In this paper, we show that both hypotheses fail to explain the fine-tuning instability. We analyze BERT, RoBERTa, and ALBERT, fine-tuned on commonly used datasets from the GLUE benchmark, and show that the observed instability is caused by optimization difficulties that lead to vanishing gradients. Additionally, we show that the remaining variance of the downstream task performance can be attributed to differences in generalization where fine-tuned models with the same training loss exhibit noticeably different test performance. Based on our analysis, we present a simple but strong baseline that makes fine-tuning BERT-based models significantly more stable than the previously proposed approaches.

• https://openreview.net/forum?id=nzpLWnVAyah

@inproceedings{mosbach2021on,
title = {On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines},
author = {Marius Mosbach and Maksym Andriushchenko and Dietrich Klakow},
url = {https://openreview.net/forum?id=nzpLWnVAyah},
year = {2021},
date = {2021},
booktitle = {International Conference on Learning Representations},
abstract = {Fine-tuning pre-trained transformer-based language models such as BERT has become a common practice dominating leaderboards across various NLP benchmarks. Despite the strong empirical performance of fine-tuned models, fine-tuning is an unstable process: training the same model with multiple random seeds can result in a large variance of the task performance. Previous literature (Devlin et al., 2019; Lee et al., 2020; Dodge et al., 2020) identified two potential reasons for the observed instability: catastrophic forgetting and small size of the fine-tuning datasets. In this paper, we show that both hypotheses fail to explain the fine-tuning instability. We analyze BERT, RoBERTa, and ALBERT, fine-tuned on commonly used datasets from the GLUE benchmark, and show that the observed instability is caused by optimization difficulties that lead to vanishing gradients. Additionally, we show that the remaining variance of the downstream task performance can be attributed to differences in generalization where fine-tuned models with the same training loss exhibit noticeably different test performance. Based on our analysis, we present a simple but strong baseline that makes fine-tuning BERT-based models significantly more stable than the previously proposed approaches.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

The disambiguation and processing of coherence relations is often investigated with a focus on explicit connectives, such as but or so. Other, non-connective cues from the context also facilitate discourse inferences, although their precise disambiguating role and interaction with connectives have been largely overlooked in the psycholinguistic literature so far. This study reports on two crowdsourcing experiments that test the role of contextual cues (parallelism, antonyms, resultative verbs) in the disambiguation of contrast and consequence relations. We compare the effect of contextual cues in conceptually different relations, and with connectives that differ in their semantic precision. Using offline tasks, our results show that contextual cues significantly help disambiguating contrast and consequence relations in the absence of connectives. However, when connectives are present in the context, the effect of cues only holds if the connective is acceptable in the target relation. Overall, our study suggests that cues are decisive on their own, but only secondary in the presence of connectives. These results call for further investigation of the complex interplay between connective types, contextual cues, relation types and other linguistic and cognitive factors.

@article{Crible2021,
title = {The role of non-connective discourse cues and their interaction with connectives},
author = {Ludivine Crible and Vera Demberg},
year = {2021},
date = {2021},
journal = {Pragmatics and Cognition},
abstract = {The disambiguation and processing of coherence relations is often investigated with a focus on explicit connectives, such as but or so. Other, non-connective cues from the context also facilitate discourse inferences, although their precise disambiguating role and interaction with connectives have been largely overlooked in the psycholinguistic literature so far. This study reports on two crowdsourcing experiments that test the role of contextual cues (parallelism, antonyms, resultative verbs) in the disambiguation of contrast and consequence relations. We compare the effect of contextual cues in conceptually different relations, and with connectives that differ in their semantic precision. Using offline tasks, our results show that contextual cues significantly help disambiguating contrast and consequence relations in the absence of connectives. However, when connectives are present in the context, the effect of cues only holds if the connective is acceptable in the target relation. Overall, our study suggests that cues are decisive on their own, but only secondary in the presence of connectives. These results call for further investigation of the complex interplay between connective types, contextual cues, relation types and other linguistic and cognitive factors.},
pubstate = {forthcoming},
type = {article}
}

Copy BibTeX to Clipboard

Speakers adapt their speech to increase clarity in the presence of back-ground noise (Lombard speech) [1, 2]. However, they also modify their speech tobe efficient by shortening word duration in more predictable contexts [3]. To meetthese two communicative functions, speakers will attempt to resolve any conflicting communicative demands. The present study focuses on how this can be resolvedin the acoustic domain. A total of 1520 target CV syllables were annotated andanalysed from 38 German speakers in 2 white-noise (no noise vs. -10 dB SNR) and 2 surprisal (H vs. L) contexts. Median fundamental frequency (F0), intensityrange, and syllable duration were extracted. Our results revealed effects of bothnoise and surprisal on syllable duration and intensity range, but only an effect ofnoise on F0. This might suggest redundant (multi-dimensional) acoustic coding in Lombard speech modification, but not so in surprisal modification.

• http://essv.de/essv2021/pdfs/22_ibrahim.pdf

@inproceedings{Ibrahim2021,
title = {The effect of Lombard speech modifications in different information density contexts},
author = {Omnia Ibrahim and Ivan Yuen and Marjolein van Os and Bistra Andreeva and Bernd M{\"o}bius},
url = {http://essv.de/essv2021/pdfs/22_ibrahim.pdf},
year = {2021},
date = {2021},
booktitle = {Elektronische Sprachsignalverarbeitung 2021, Tagungsband der 32. Konferenz (Berlin)},
pages = {185-191},
publisher = {TUDpress},
address = {Dresden},
abstract = {Speakers adapt their speech to increase clarity in the presence of back-ground noise (Lombard speech) [1, 2]. However, they also modify their speech tobe efficient by shortening word duration in more predictable contexts [3]. To meetthese two communicative functions, speakers will attempt to resolve any conflicting communicative demands. The present study focuses on how this can be resolvedin the acoustic domain. A total of 1520 target CV syllables were annotated andanalysed from 38 German speakers in 2 white-noise (no noise vs. -10 dB SNR) and 2 surprisal (H vs. L) contexts. Median fundamental frequency (F0), intensityrange, and syllable duration were extracted. Our results revealed effects of bothnoise and surprisal on syllable duration and intensity range, but only an effect ofnoise on F0. This might suggest redundant (multi-dimensional) acoustic coding in Lombard speech modification, but not so in surprisal modification.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

This paper summarizes the results of a Modified Rhyme Test conducted with masked stimuli to simulate two common types of hearing impairment: bilateral pulsatile and pure tinnitus. Two types of stimuli, meaningful German words (natural read speech and TTS output) differing in initial or final positioned minimal pairs were modified to correspond to six listening conditions. Results showed higher recognition scores for natural speech compared to synthetic and better intelligibility for pulsatile tinnitus noise over pure tone tinnitus. These insights are of relevance given the alarming rates of tinnitus in epidemiological reports.

• http://www.essv.de/essv2021/pdfs/15_kudera.pdf

@inproceedings{Kudera2021,
title = {Natural and synthetic speech comprehension in simulated tonal and pulsatile tinnitus: A pilot study},
author = {Jacek Kudera and Marjolein van Os and Bernd M{\"o}bius},
url = {http://www.essv.de/essv2021/pdfs/15_kudera.pdf},
year = {2021},
date = {2021},
booktitle = {Elektronische Sprachsignalverarbeitung 2021, Tagungsband der 32. Konferenz (Berlin)},
pages = {273-280},
publisher = {TUDpress},
address = {Dresden},
abstract = {This paper summarizes the results of a Modified Rhyme Test conducted with masked stimuli to simulate two common types of hearing impairment: bilateral pulsatile and pure tinnitus. Two types of stimuli, meaningful German words (natural read speech and TTS output) differing in initial or final positioned minimal pairs were modified to correspond to six listening conditions. Results showed higher recognition scores for natural speech compared to synthetic and better intelligibility for pulsatile tinnitus noise over pure tone tinnitus. These insights are of relevance given the alarming rates of tinnitus in epidemiological reports.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

This study contributes to a better understanding of reading intercomprehension as manifested in the intelligibility of East and South Slavic languages to Russian native speakers in contextualized cognate recognition experiments using Belarusian, Ukrainian, and Bulgarian stimuli. While the results mostly confirm the expected mutual intelligibility effects, we also register apparent processing difficulties in some of the cases. In search of an explanation, we examine the correlation of the experimentally obtained intercomprehension scores with various linguistic factors, which contribute to cognate intelligibility in a context, considering common predictors of intercomprehension associated with (i) morphology and orthography, (ii) lexis, and (iii) syntax.

• http://www.dialog-21.ru/media/5415/_-dialog2021scopus.pdf

@inproceedings{Stenger-dialog2021,
title = {On Slavic cognate recognition in context},
author = {Irina Stenger and Tania Avgustinova},
editor = {Vladimir P. Selegej et al.},
url = {http://www.dialog-21.ru/media/5415/_-dialog2021scopus.pdf},
year = {2021},
date = {2021},
booktitle = {Computational Linguistics and Intellectual Technologies: Papers from the Annual International Conference ‘Dialogue’},
pages = {660-668},
address = {Moscow, Russia},
abstract = {This study contributes to a better understanding of reading intercomprehension as manifested in the intelligibility of East and South Slavic languages to Russian native speakers in contextualized cognate recognition experiments using Belarusian, Ukrainian, and Bulgarian stimuli. While the results mostly confirm the expected mutual intelligibility effects, we also register apparent processing difficulties in some of the cases. In search of an explanation, we examine the correlation of the experimentally obtained intercomprehension scores with various linguistic factors, which contribute to cognate intelligibility in a context, considering common predictors of intercomprehension associated with (i) morphology and orthography, (ii) lexis, and (iii) syntax.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Receptive multilingualism is a multidimensional and multifactorial phenomenon that crucially depends on the mutual intelligibility of closely related languages. As a strategy, it predominantly capitalizes upon a dynamic integration of linguistic, communicative, contextual, and socio-cognitive aspects. Relevant linguistic determinants (especially linguistic distances) along with recognizable extra-linguistic influences (such as attitude and exposure) have recently enjoyed increased attention in the research community. In our online (web-based) intercomprehension experiments, we have observed learning effects that appear to be empirically associated with individual cognitive skills. For this study, we tested 185 Russian subjects in a written word recognition task which essentially involved cognate guessing in Belarusian, Bulgarian, Macedonian, Serbian, and Ukrainian. The subjects had to translate the stimuli presented online into their native language, i.e. Russian. To reveal implicit multilingual learnability, we correlate the obtained intercomprehension scores with the detected reaction times, taking into consideration the potential influence of the experiment rank on the reaction time too.

• https://ibl.bas.bg/wp-content/uploads/2021/06/Sbornik_s_dokladi_CONFIBL2021_tom_2_FINAL.pdf

@inproceedings{Stenger-CONFIBL2021,
title = {Multilingual learnability and reaction time in online Slavic intercomprehension experiments},
author = {Irina Stenger and Tania Avgustinova},
editor = {Svetla Koeva and Maksim Stamenov},
url = {https://ibl.bas.bg/wp-content/uploads/2021/06/Sbornik_s_dokladi_CONFIBL2021_tom_2_FINAL.pdf},
year = {2021},
date = {2021},
booktitle = {Proceedings of the International Annual Conference of the Institute for Bulgarian Language},
pages = {191-200},
publisher = {Marin Drinov Academic Publishers},
address = {Sofia, Bulgaria},
abstract = {Receptive multilingualism is a multidimensional and multifactorial phenomenon that crucially depends on the mutual intelligibility of closely related languages. As a strategy, it predominantly capitalizes upon a dynamic integration of linguistic, communicative, contextual, and socio-cognitive aspects. Relevant linguistic determinants (especially linguistic distances) along with recognizable extra-linguistic influences (such as attitude and exposure) have recently enjoyed increased attention in the research community. In our online (web-based) intercomprehension experiments, we have observed learning effects that appear to be empirically associated with individual cognitive skills. For this study, we tested 185 Russian subjects in a written word recognition task which essentially involved cognate guessing in Belarusian, Bulgarian, Macedonian, Serbian, and Ukrainian. The subjects had to translate the stimuli presented online into their native language, i.e. Russian. To reveal implicit multilingual learnability, we correlate the obtained intercomprehension scores with the detected reaction times, taking into consideration the potential influence of the experiment rank on the reaction time too.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

During the last years, much progress has been made in hierarchical planning towards domain-independent systems that
come with sophisticated techniques to solve planning problems instead of relying on advice in the input model. Several of
these novel methods have been integrated into the PANDA framework, which is a software system to reason about hierarchical planning tasks. Besides solvers for planning problems based on plan space search, progression search, and translation to propositional logic, it also includes techniques for related problems like plan repair, plan and goal recognition, or plan verifcation. These various techniques share a common infrastructure, like e.g. a standard input language or components for grounding and reachability analysis. This article gives an overview over the PANDA framework, introduces the basic techniques from a high level perspective, and surveys the literature describing the diverse components in detail.

• Höller2021_Article_ThePANDAFrameworkForHierarchic     (0.6MB)
• https://link.springer.com/article/10.1007/s13218-020-00699-y
• https://doi.org/10.1007/s13218-020-00699-y

@article{hoeller-etal-21-PANDA,
title = {The PANDA Framework for Hierarchical Planning},
author = {Daniel H{\"o}ller and Gregor Behnke and Pascal Bercher and Susanne Biundo},
url = {https://link.springer.com/article/10.1007/s13218-020-00699-y},
doi = {https://doi.org/10.1007/s13218-020-00699-y},
year = {2021},
date = {2021},
journal = {K{\"u}nstliche Intelligenz},
abstract = {During the last years, much progress has been made in hierarchical planning towards domain-independent systems that come with sophisticated techniques to solve planning problems instead of relying on advice in the input model. Several of these novel methods have been integrated into the PANDA framework, which is a software system to reason about hierarchical planning tasks. Besides solvers for planning problems based on plan space search, progression search, and translation to propositional logic, it also includes techniques for related problems like plan repair, plan and goal recognition, or plan verifcation. These various techniques share a common infrastructure, like e.g. a standard input language or components for grounding and reachability analysis. This article gives an overview over the PANDA framework, introduces the basic techniques from a high level perspective, and surveys the literature describing the diverse components in detail.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

@inproceedings{hoeller-bercher-21-LMs,
title = {Landmark Generation in HTN Planning},
author = {Daniel H{\"o}ller and Pascal Bercher},
year = {2021},
date = {2021},
booktitle = {Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI)},
publisher = {AAAI Press},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

The problem of spatiotemporal overlap between event-related potential (ERP) components is generally acknowledged in language research. However, its implications for the interpretation of experimental results are often overlooked. In a previous experiment on the functional interpretation of the N400 and P600, it was argued that a P600 effect to implausible words was largely obscured – in one of two implausible conditions – by an overlapping N400 effect of semantic association. In the present ERP study, we show that the P600 effect of implausibility is uncovered when the critical condition is tested against a proper baseline condition which elicits a similar N400 amplitude, while it is obscured when tested against a baseline condition producing an N400 effect. Our findings reveal that component overlap can result in the apparent absence or presence of an effect in the surface signal and should therefore be carefully considered when interpreting ERP patterns. Importantly, we show that, by factoring in the effects of spatiotemporal overlap between the N400 and P600 on the surface signal, which we reveal using rERP analysis, apparent inconsistencies in previous findings are easily reconciled, enabling us to draw unambiguous conclusions about the functional interpretation of the N400 and P600 components. Overall, our results provide compelling evidence that the N400 reflects lexical retrieval processes, while the P600 indexes compositional integration of word meaning into the unfolding utterance interpretation.

• https://www.sciencedirect.com/science/article/pii/S0006899321003711
• https://doi.org/10.1016/j.brainres.2021.147514

@article{DELOGU2021147514,
title = {When components collide: Spatiotemporal overlap of the N400 and P600 in language comprehension},
author = {Francesca Delogu and Harm Brouwer and Matthew W. Crocker},
url = {https://www.sciencedirect.com/science/article/pii/S0006899321003711},
doi = {https://doi.org/10.1016/j.brainres.2021.147514},
year = {2021},
date = {2021},
journal = {Brain Research},
pages = {147514},
volume = {1766},
abstract = {The problem of spatiotemporal overlap between event-related potential (ERP) components is generally acknowledged in language research. However, its implications for the interpretation of experimental results are often overlooked. In a previous experiment on the functional interpretation of the N400 and P600, it was argued that a P600 effect to implausible words was largely obscured – in one of two implausible conditions – by an overlapping N400 effect of semantic association. In the present ERP study, we show that the P600 effect of implausibility is uncovered when the critical condition is tested against a proper baseline condition which elicits a similar N400 amplitude, while it is obscured when tested against a baseline condition producing an N400 effect. Our findings reveal that component overlap can result in the apparent absence or presence of an effect in the surface signal and should therefore be carefully considered when interpreting ERP patterns. Importantly, we show that, by factoring in the effects of spatiotemporal overlap between the N400 and P600 on the surface signal, which we reveal using rERP analysis, apparent inconsistencies in previous findings are easily reconciled, enabling us to draw unambiguous conclusions about the functional interpretation of the N400 and P600 components. Overall, our results provide compelling evidence that the N400 reflects lexical retrieval processes, while the P600 indexes compositional integration of word meaning into the unfolding utterance interpretation.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

Several variants of deep neural networks have been successfully employed for building parametric models that project variable-duration spoken word segments onto fixed-size vector representations, or acoustic word embeddings (AWEs). However, it remains unclear to what degree we can rely on the distance in the emerging AWE space as an estimate of word-form similarity. In this paper, we ask: does the distance in the acoustic embedding space correlate with phonological dissimilarity? To answer this question, we empirically investigate the performance of supervised approaches for AWEs with different neural architectures and learning objectives. We train AWE models in controlled settings for two languages (German and Czech) and evaluate the embeddings on two tasks: word discrimination and phonological similarity. Our experiments show that (1) the distance in the embedding space in the best cases only moderately correlates with phonological distance, and (2) improving the performance on the word discrimination task does not necessarily yield models that better reflect word phonological similarity. Our findings highlight the necessity to rethink the current intrinsic evaluations for AWEs.

• https://arxiv.org/abs/2106.08686

@inproceedings{Abdullah2021DoAW,
title = {Do Acoustic Word Embeddings Capture Phonological Similarity? An Empirical Study},
author = {Badr M. Abdullah and Marius Mosbach and Iuliia Zaitova and Bernd M{\"o}bius and Dietrich Klakow},
url = {https://arxiv.org/abs/2106.08686},
year = {2021},
date = {2021},
booktitle = {Proceedings of Interspeech 2020},
abstract = {Several variants of deep neural networks have been successfully employed for building parametric models that project variable-duration spoken word segments onto fixed-size vector representations, or acoustic word embeddings (AWEs). However, it remains unclear to what degree we can rely on the distance in the emerging AWE space as an estimate of word-form similarity. In this paper, we ask: does the distance in the acoustic embedding space correlate with phonological dissimilarity? To answer this question, we empirically investigate the performance of supervised approaches for AWEs with different neural architectures and learning objectives. We train AWE models in controlled settings for two languages (German and Czech) and evaluate the embeddings on two tasks: word discrimination and phonological similarity. Our experiments show that (1) the distance in the embedding space in the best cases only moderately correlates with phonological distance, and (2) improving the performance on the word discrimination task does not necessarily yield models that better reflect word phonological similarity. Our findings highlight the necessity to rethink the current intrinsic evaluations for AWEs.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard