Publications

We present a new workflow to create components for the MaryTTS text-to-speech synthesis platform, which is popular with researchers and developers, extending it to support new languages and custom synthetic voices. This workflow replaces the previous toolkit with an efficient, flexible process that leverages modern build automation and cloud-hosted infrastructure. Moreover, it is compatible with the updated MaryTTS architecture, enabling new features and state-of-the-art paradigms such as synthesis based on deep neural networks (DNNs). Like MaryTTS itself, the new tools are free, open source software (FOSS), and promote the use of open data.

• 1045     (0.14MB)
• https://arxiv.org/abs/1712.04787

@inproceedings{Steiner2018LREC,
title = {Creating New Language and Voice Components for the Updated MaryTTS Text-to-Speech Synthesis Platform},
author = {Ingmar Steiner and S{\'e}bastien Le Maguer},
url = {https://arxiv.org/abs/1712.04787},
year = {2018},
date = {2018-05-10},
booktitle = {11th Language Resources and Evaluation Conference (LREC)},
pages = {3171-3175},
address = {Miyazaki, Japan},
abstract = {We present a new workflow to create components for the MaryTTS text-to-speech synthesis platform, which is popular with researchers and developers, extending it to support new languages and custom synthetic voices. This workflow replaces the previous toolkit with an efficient, flexible process that leverages modern build automation and cloud-hosted infrastructure. Moreover, it is compatible with the updated MaryTTS architecture, enabling new features and state-of-the-art paradigms such as synthesis based on deep neural networks (DNNs). Like MaryTTS itself, the new tools are free, open source software (FOSS), and promote the use of open data.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Collocations have been identified as an interesting field to study the effects of frequency of occurrence in language and speech. We report results of a production experiment including a duration analysis based on the production of German collocations. The collocations occurred in a condition where the phrase was produced with a literal meaning and in another condition where it was idiomatic. A durational difference was found for the collocations, which were reduced in the idiomatic condition. This difference was also observed for the function word und (‘and’) in collocations like Mord und Totschlag (‘murder and manslaughter’). However, an analysis of the vowel /U/ of the function word did not show a durational difference. Some explanations as to why speakers showed different patterns of reduction (not all collocations were produced with a shorter duration in the idiomatic condition by all speakers) and why not all speakers use the durational cue (one out of eight speakers produced the conditions identically) are proposed.

• zimmerer_etal_sp2018-1     (0.21MB)
• https://www.isca-speech.org/archive/speechprosody_2018/zimmerer18_speechprosody.html
• https://doi.org/10.21437/SpeechProsody.2018-87

@inproceedings{Zimmerer2018SpPro,
title = {Idiomatic or literal? Production of collocations in German read speech},
author = {Frank Zimmerer and Erika Brandt and Bistra Andreeva and Bernd M{\"o}bius},
url = {https://www.isca-speech.org/archive/speechprosody_2018/zimmerer18_speechprosody.html},
doi = {https://doi.org/10.21437/SpeechProsody.2018-87},
year = {2018},
date = {2018},
booktitle = {Proc. Speech Prosody 2018},
pages = {428-432},
address = {Poznan},
abstract = {Collocations have been identified as an interesting field to study the effects of frequency of occurrence in language and speech. We report results of a production experiment including a duration analysis based on the production of German collocations. The collocations occurred in a condition where the phrase was produced with a literal meaning and in another condition where it was idiomatic. A durational difference was found for the collocations, which were reduced in the idiomatic condition. This difference was also observed for the function word und (‘and’) in collocations like Mord und Totschlag (‘murder and manslaughter’). However, an analysis of the vowel /U/ of the function word did not show a durational difference. Some explanations as to why speakers showed different patterns of reduction (not all collocations were produced with a shorter duration in the idiomatic condition by all speakers) and why not all speakers use the durational cue (one out of eight speakers produced the conditions identically) are proposed.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

This study investigated the influence of prosodic structure and information density (ID), defined as contextual predictability, on vowel-inherent spectral change (VISC). We extracted formant measurements from the onset and offset of the vowels of a large German corpus of newspaper read speech. Vector length (VL), the Euclidean distance between F1 and F2 trajectory, and F1 and F2 slope, formant deltas of onset and offset relative to vowel duration, were calculated as measures of formant change. ID factors were word frequency and phoneme-based surprisal measures, while the prosodic factors contained global and local articulation rate, primary lexical stress, and prosodic boundary. We expected that vowels increased in spectral change when they were difficult to predict from the context, or stood in low-frequency words while controlling for known effects of prosodic structure. The ID effects were assumed to be modulated by prosodic factors to a certain extent. We confirmed our hypotheses for VL, and found expected independent effects of prosody and ID on F1 slope and F2 slope.

• brandt_etal_sp2018     (0.31MB)
• https://www.researchgate.net/publication/325744530_Impact_of_prosodic_structure_and_information_density_on_dynamic_formant_trajectories_in_German
• https://doi.org/10.22028/D291-32050

@inproceedings{Brandt2018SpPro,
title = {Impact of prosodic structure and information density on dynamic formant trajectories in German},
author = {Erika Brandt and Frank Zimmerer and Bistra Andreeva and Bernd M{\"o}bius},
editor = {Katarzyna Klessa and Jolanta Bachan and Agnieszka Wagner and Maciej Karpiński and Daniel Śledziński},
url = {https://www.researchgate.net/publication/325744530_Impact_of_prosodic_structure_and_information_density_on_dynamic_formant_trajectories_in_German},
doi = {https://doi.org/10.22028/D291-32050},
year = {2018},
date = {2018},
booktitle = {Speech Prosody 2018},
issn = {2333-2042},
pages = {119-123},
publisher = {Speech Prosody Special Interest Group},
address = {Urbana},
abstract = {This study investigated the influence of prosodic structure and information density (ID), defined as contextual predictability, on vowel-inherent spectral change (VISC). We extracted formant measurements from the onset and offset of the vowels of a large German corpus of newspaper read speech. Vector length (VL), the Euclidean distance between F1 and F2 trajectory, and F1 and F2 slope, formant deltas of onset and offset relative to vowel duration, were calculated as measures of formant change. ID factors were word frequency and phoneme-based surprisal measures, while the prosodic factors contained global and local articulation rate, primary lexical stress, and prosodic boundary. We expected that vowels increased in spectral change when they were difficult to predict from the context, or stood in low-frequency words while controlling for known effects of prosodic structure. The ID effects were assumed to be modulated by prosodic factors to a certain extent. We confirmed our hypotheses for VL, and found expected independent effects of prosody and ID on F1 slope and F2 slope.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and decoding, yielding the KL-vanishing problem and inconsistent training objective. In this paper, we separate the training step into two phases: The first phase learns to autoencode discrete texts into continuous embeddings, from which the second phase learns to generalize latent representations by reconstructing the encoded embedding. In this case, latent variables are sampled by transforming Gaussian noise through multi-layer perceptrons and are trained with a separate VED model, which has the potential of realizing a much more flexible distribution. We compare our model with current popular models and the experiment demonstrates substantial improvement in both metric-based and human evaluations.

• 1802.02032     (0.54MB)
• https://arxiv.org/abs/1802.02032

@inproceedings{Shen2018,
title = {Improving Variational Encoder-Decoders in Dialogue Generation},
author = {Xiaoyu Shen and Hui Su and Shuzi Niu and Vera Demberg},
url = {https://arxiv.org/abs/1802.02032},
year = {2018},
date = {2018-02-02},
publisher = {32nd AAAI Conference on Artificial Intelligence (AAAI-18)},
address = {New Orleans, USA},
abstract = {Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and decoding, yielding the KL-vanishing problem and inconsistent training objective. In this paper, we separate the training step into two phases: The first phase learns to autoencode discrete texts into continuous embeddings, from which the second phase learns to generalize latent representations by reconstructing the encoded embedding. In this case, latent variables are sampled by transforming Gaussian noise through multi-layer perceptrons and are trained with a separate VED model, which has the potential of realizing a much more flexible distribution. We compare our model with current popular models and the experiment demonstrates substantial improvement in both metric-based and human evaluations.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

We present an end-to-end text-to-speech (TTS) synthesis system that generates audio and synchronized tongue motion directly from text. This is achieved by adapting a 3D model of the tongue surface to an articulatory dataset and training a statistical parametric speech synthesis system directly on the tongue model parameters. We evaluate the model at every step by comparing the spatial coordinates of predicted articulatory movements against the reference data. The results indicate a global mean Euclidean distance of less than 2.8 mm, and our approach can be adapted to add an articulatory modality to conventional TTS applications without the need for extra data.

• https://arxiv.org/abs/1612.09352

@article{Steiner2017TASLP,
title = {Synthesis of Tongue Motion and Acoustics from Text using a Multimodal Articulatory Database},
author = {Ingmar Steiner and S{\'e}bastien Le Maguer and Alexander Hewer},
url = {https://arxiv.org/abs/1612.09352},
year = {2017},
date = {2017},
journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
pages = {2351-2361},
volume = {25},
number = {12},
abstract = {We present an end-to-end text-to-speech (TTS) synthesis system that generates audio and synchronized tongue motion directly from text. This is achieved by adapting a 3D model of the tongue surface to an articulatory dataset and training a statistical parametric speech synthesis system directly on the tongue model parameters. We evaluate the model at every step by comparing the spatial coordinates of predicted articulatory movements against the reference data. The results indicate a global mean Euclidean distance of less than 2.8 mm, and our approach can be adapted to add an articulatory modality to conventional TTS applications without the need for extra data.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

• http://www.cys.cic.ipn.mx/ojs/index.php/CyS/article/view/2865

@article{Fischer2017,
title = {Beyond Pairwise Similarity: Quantifying and Characterizing Linguistic Similarity between Groups of Languages by MDL},
author = {Andrea Fischer and Jilles Vreeken and Dietrich Klakow},
url = {http://www.cys.cic.ipn.mx/ojs/index.php/CyS/article/view/2865},
year = {2017},
date = {2017},
journal = {Computación y Systems},
pages = {829-839},
volume = {21},
number = {4},
abstract = {

Copy BibTeX to Clipboard

• olinco-2016-proceedings     (4.67MB)

@inproceedings{Klára2017,
title = {Lexical and orthographic distances between Bulgarian, Czech, Polish, and Russian: A comparative analysis of the most frequent nouns},
author = {Kl{\'a}ra J{\'a}grov{\'a} and Irina Stenger and Roland Marti and Tania Avgustinova},
year = {2017},
date = {2017},
booktitle = {Joseph Emonds & Mark{\'e}ta Janebov{\'a} (eds.), Language Use and Linguistic Structure. Proceedings of the Olomouc Linguistics Colloquium 2016},
pages = {401–416},
address = {Olomouc: Palacký University},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

• https://www.cambridge.org/core/journals/nordic-journal-of-linguistics/article/modeling-the-impact-of-orthographic-coding-on-czechpolish-and-bulgarianrussian-reading-intercomprehension/363BEB5C556DFBDAC7FEED0AE06B06AA

@article{Stenger2017b,
title = {Modeling the Impact of Orthographic Coding on Czech-Polish and Bulgarian-Russian Reading Intercomprehension},
author = {Irina Stenger and Kl{\'a}ra J{\'a}grov{\'a} and Andrea Fischer and Tania Avgustinova and Dietrich Klakow and Roland Marti},
url = {https://www.cambridge.org/core/journals/nordic-journal-of-linguistics/article/modeling-the-impact-of-orthographic-coding-on-czechpolish-and-bulgarianrussian-reading-intercomprehension/363BEB5C556DFBDAC7FEED0AE06B06AA},
year = {2017},
date = {2017},
journal = {Nordic Journal of Linguistic},
pages = {175-199},
volume = {40},
number = {2},
abstract = {

Copy BibTeX to Clipboard

In this article we validate two measuring methods: Levenshtein distance and word adaptation surprisal as potential predictors of success in reading intercomprehension. We investigate to what extent orthographic distances between Russian and other East Slavic (Ukrainian, Belarusian) and South Slavic (Bulgarian, Macedonian, Serbian) languages found by means of the Levenshtein algorithm and word adaptation surprisal correlate with comprehension of unknown Slavic languages on the basis of data obtained from Russian native speakers in online free translation task experiments. We try to find an answer to the following question: Can measuring methods such as Levenshtein distance and word adaptation surprisal be considered as a good approximation of orthographic intelligibility of unknown Slavic languages using the Cyrillic script?

• dialogue2017_v1     (6.95MB)
• https://www.semanticscholar.org/paper/Levenshtein-Distance-anD-WorD-aDaptation-surprisaL-Distance/6103d388cb0398b89dec8ca36ec0be025bb6dea2

@inproceedings{Stenger2017,
title = {Levenshtein distance and word adaptation surprisal as methods of measuring mutual intelligibility in reading comprehension of Slavic languages},
author = {Irina Stenger and Tania Avgustinova and Roland Marti},
url = {https://www.semanticscholar.org/paper/Levenshtein-Distance-anD-WorD-aDaptation-surprisaL-Distance/6103d388cb0398b89dec8ca36ec0be025bb6dea2},
year = {2017},
date = {2017},
booktitle = {Computational Linguistics and Intellectual Technologies: International Conference "Dialogue 2017"},
pages = {304-317},
abstract = {In this article we validate two measuring methods: Levenshtein distance and word adaptation surprisal as potential predictors of success in reading intercomprehension. We investigate to what extent orthographic distances between Russian and other East Slavic (Ukrainian, Belarusian) and South Slavic (Bulgarian, Macedonian, Serbian) languages found by means of the Levenshtein algorithm and word adaptation surprisal correlate with comprehension of unknown Slavic languages on the basis of data obtained from Russian native speakers in online free translation task experiments. We try to find an answer to the following question: Can measuring methods such as Levenshtein distance and word adaptation surprisal be considered as a good approximation of orthographic intelligibility of unknown Slavic languages using the Cyrillic script?},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Ein Text in einer unbekannten Sprache wird erst durch das Vorhandensein von Bekanntem verständlich. Das Vorhandensein von Internationalismen oder auch Wörtern mit gemeinsamer Etymologie und Bedeutung ist ausschlaggebend für das Phänomen der Interkomprehension – der Fähigkeit, eine verwandte, aber unbekannte Sprache zu verstehen, ohne sie jedoch aktiv zu beherrschen (vgl. z.B. Doyé 2005). Dies ist in der Praxis je nach Nähe der Sprachen mehr oder weniger erfolgreich innerhalb einer Sprachgruppe möglich, etwa zwischen dem Tschechischen und Slovakischen (Nábělková 2007, Golubović 2016) oder zwischen Bosnisch, Kroatisch, Montenegrinisch und Serbisch (Gooskens, Golubović 2015, Golubović 2016). Dasselbe Prinzip funktioniert, jedoch nicht gleichermaßen unkompliziert, zwischen dem Polnischen und anderen slavischen Sprachen (ibid.). Auch eine sprachfamilienübergreifende Interkomprehension durch Rückgriff auf Internationalismen und Entlehnungen oder Wörter mit gemeinsamer etymologischer Herkunft (vgl. EuroComSlav und die Sieben Siebe; Mehlhorn 2014) ist längst Thema sprachvergleichender und fremdsprachendidaktischer Forschung geworden (Mehlhorn 2014, Doyé 2008, Ollivier 2007, Klein, Reissner 2006). Filomena Capucho (2002, übersetzt und zitiert nach Mehlhorn 2014) versteht Interkomprehension „nicht nur als ein Resultat linguistischen Transfers zwischen Sprachen derselben Familie, sondern als ein Resultat von Transferstrategien im Rahmen eines allgemeinen Interpretationsprozesses, der jeder kommunikativen Aktivität unterliegtˮ. Dieser Artikel stellt eine Weiterführung einer vorhergehenden Studie dar, die die vergleichende Bestimmung der lexikalischen (auf den Wortschatz bezogenen) und orthographischen Distanz (aktuelle Konvention der Verschriftlichung) zwischen slavischen Sprachen zum Ziel hatte. Die in jener Studie gemessenen linguistischen Distanzen sollen Prädiktoren dafür sein, wie schwierig es für slavische Lesende ist, eine andere slavische Sprache zu lesen und zu verstehen, wobei die beiden Ebenen Lexik und Orthographie getrennt betrachtet werden. Die Weiterführung dieser Studie besteht darin, dass die Methoden der sprachlichen Distanzmessungen nicht nur innerhalb der slavischen Sprachfamilie angewandt werden, sondern auch über ihre Grenzen hinaus. Eine solche sprachfamilienübergreifende Messung soll ein Interkomprehensionsszenario repräsentieren, bei dem z.B. Lesende mit Deutsch als L1 versuchen Polnisch zu verstehen – eine Situation, wie sie auch zu Beginn des Polnisch-Unterrichts an deutschen Bildungseinrichtungen auftreten könnte. Konkret ist hier die Fragestellung: Was sind die empirischen Voraussetzungen dafür, dass Interkomprehension im Polnischunterricht in Deutschland funktioniert? Welche Schlüsse erlauben die Methoden und Resultate linguistischer Distanzmessungen auf das Polnische? Gibt es für das Polnische eventuell sogar sprachliche Voraussetzungen, die Vorteile gegenüber anderen potentiell zu erlernenden Sprachen darstellen und ein Argument für die Wahl des Polnischen als L2/L3/LX wären?

Der Gebrauch von Internationalismen und verwandtem Vokabular ist außerdem eine der Grundvoraussetzungen dafür, dass moderner Fremdsprachenunterricht von Anfang an in der Zielsprache stattfinden kann. Es wird davon ausgegangen, dass die zwischensprachliche Ähnlichkeit nicht nur ein entscheidender Faktor für den Erfolg der Interkomprehension ist (Golubović 2016, Gooskens 2007), sondern auch den Fremdsprachenerwerb erleichtert, wobei Lernende gezielt auf bereits vorhandenes Wissen in einer Sprache zurückgreifen und aufbauen können (Mehlhorn 2014, Ringbom, Jarvis 2007).

Wir demonstrieren die Methoden und Ergebnisse lexikalischer und orthographischer Distanzmessungen des Polnischen gegenüber anderen Sprachen. Anschließend präsentieren wir die Resultate einer Pilotstudie mit einem bezüglich der Sprachkenntnisse sehr heterogenen Sample an Versuchspersonen, deren Aufgabe es war, polnische Internationalismen und Kognaten (Def. unten) mit gemeinsamer indoeuropäischer Herkunft möglichst korrekt in ihre Sprache zu übersetzen. Wir vergleichen die Resultate der Studie hinsichtlich der Art der Stimuli sowie des Sprachenrepertoires der Versuchspersonen.

@article{Jágrová2017,
title = {POLSKI TO JEZYK NIESKOMPLIKOWANY? Theoretische und praktische Interkomprehension der 100 h{\"a}ufigsten polnischen Substantive},
author = {Kl{\'a}ra J{\'a}grov{\'a} and Irina Stenger and Tania Avgustinova and Roland Marti},
year = {2017},
date = {2017},
journal = {In Polnisch in Deutschland. Zeitschrift der Bundesvereinigung der Polnischlehrkr{\"a}fte},
pages = {5-19},
volume = {4/2016},
abstract = {Ein Text in einer unbekannten Sprache wird erst durch das Vorhandensein von Bekanntem verst{\"a}ndlich. Das Vorhandensein von Internationalismen oder auch W{\"o}rtern mit gemeinsamer Etymologie und Bedeutung ist ausschlaggebend f{\"u}r das Ph{\"a}nomen der Interkomprehension – der F{\"a}higkeit, eine verwandte, aber unbekannte Sprache zu verstehen, ohne sie jedoch aktiv zu beherrschen (vgl. z.B. Doy{\'e} 2005). Dies ist in der Praxis je nach N{\"a}he der Sprachen mehr oder weniger erfolgreich innerhalb einer Sprachgruppe m{\"o}glich, etwa zwischen dem Tschechischen und Slovakischen (N{\'a}bělkov{\'a} 2007, Golubović 2016) oder zwischen Bosnisch, Kroatisch, Montenegrinisch und Serbisch (Gooskens, Golubović 2015, Golubović 2016). Dasselbe Prinzip funktioniert, jedoch nicht gleicherma{\ss}en unkompliziert, zwischen dem Polnischen und anderen slavischen Sprachen (ibid.). Auch eine sprachfamilien{\"u}bergreifende Interkomprehension durch R{\"u}ckgriff auf Internationalismen und Entlehnungen oder W{\"o}rter mit gemeinsamer etymologischer Herkunft (vgl. EuroComSlav und die Sieben Siebe; Mehlhorn 2014) ist l{\"a}ngst Thema sprachvergleichender und fremdsprachendidaktischer Forschung geworden (Mehlhorn 2014, Doy{\'e} 2008, Ollivier 2007, Klein, Reissner 2006). Filomena Capucho (2002, {\"u}bersetzt und zitiert nach Mehlhorn 2014) versteht Interkomprehension „nicht nur als ein Resultat linguistischen Transfers zwischen Sprachen derselben Familie, sondern als ein Resultat von Transferstrategien im Rahmen eines allgemeinen Interpretationsprozesses, der jeder kommunikativen Aktivit{\"a}t unterliegtˮ. Dieser Artikel stellt eine Weiterf{\"u}hrung einer vorhergehenden Studie dar, die die vergleichende Bestimmung der lexikalischen (auf den Wortschatz bezogenen) und orthographischen Distanz (aktuelle Konvention der Verschriftlichung) zwischen slavischen Sprachen zum Ziel hatte. Die in jener Studie gemessenen linguistischen Distanzen sollen Pr{\"a}diktoren daf{\"u}r sein, wie schwierig es f{\"u}r slavische Lesende ist, eine andere slavische Sprache zu lesen und zu verstehen, wobei die beiden Ebenen Lexik und Orthographie getrennt betrachtet werden. Die Weiterf{\"u}hrung dieser Studie besteht darin, dass die Methoden der sprachlichen Distanzmessungen nicht nur innerhalb der slavischen Sprachfamilie angewandt werden, sondern auch {\"u}ber ihre Grenzen hinaus. Eine solche sprachfamilien{\"u}bergreifende Messung soll ein Interkomprehensionsszenario repr{\"a}sentieren, bei dem z.B. Lesende mit Deutsch als L1 versuchen Polnisch zu verstehen – eine Situation, wie sie auch zu Beginn des Polnisch-Unterrichts an deutschen Bildungseinrichtungen auftreten k{\"o}nnte. Konkret ist hier die Fragestellung: Was sind die empirischen Voraussetzungen daf{\"u}r, dass Interkomprehension im Polnischunterricht in Deutschland funktioniert? Welche Schl{\"u}sse erlauben die Methoden und Resultate linguistischer Distanzmessungen auf das Polnische? Gibt es f{\"u}r das Polnische eventuell sogar sprachliche Voraussetzungen, die Vorteile gegen{\"u}ber anderen potentiell zu erlernenden Sprachen darstellen und ein Argument f{\"u}r die Wahl des Polnischen als L2/L3/LX w{\"a}ren? Der Gebrauch von Internationalismen und verwandtem Vokabular ist au{\ss}erdem eine der Grundvoraussetzungen daf{\"u}r, dass moderner Fremdsprachenunterricht von Anfang an in der Zielsprache stattfinden kann. Es wird davon ausgegangen, dass die zwischensprachliche {\"A}hnlichkeit nicht nur ein entscheidender Faktor f{\"u}r den Erfolg der Interkomprehension ist (Golubović 2016, Gooskens 2007), sondern auch den Fremdsprachenerwerb erleichtert, wobei Lernende gezielt auf bereits vorhandenes Wissen in einer Sprache zur{\"u}ckgreifen und aufbauen k{\"o}nnen (Mehlhorn 2014, Ringbom, Jarvis 2007). Wir demonstrieren die Methoden und Ergebnisse lexikalischer und orthographischer Distanzmessungen des Polnischen gegen{\"u}ber anderen Sprachen. Anschlie{\ss}end pr{\"a}sentieren wir die Resultate einer Pilotstudie mit einem bez{\"u}glich der Sprachkenntnisse sehr heterogenen Sample an Versuchspersonen, deren Aufgabe es war, polnische Internationalismen und Kognaten (Def. unten) mit gemeinsamer indoeurop{\"a}ischer Herkunft m{\"o}glichst korrekt in ihre Sprache zu {\"u}bersetzen. Wir vergleichen die Resultate der Studie hinsichtlich der Art der Stimuli sowie des Sprachenrepertoires der Versuchspersonen.},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

In situated communication, reference can be established with expressions conveying either precise (Minimally-Specified, MS) or redundant (Over-Specified, OS) information. For example, while in Figure 1, “Find the blue ball” identifies exactly one object in all panels, only in the top displays is the adjective required. There is no consensus, however, concerning whether OS hinders processing (e.g., Engelhardt et al., 2011) or not (e.g., Tourtouri et al., 2015). Additionally, as incoming words incrementally restrict the referential domain, they contribute to the reduction of uncertainty regarding the target (i.e., referential entropy). Depending on the distribution of objects, the same utterance results in different entropy reduction profiles: “blue” reduces entropy by 1.58 bits in the right panels, and by .58 bits in the left ones, while “ball” reduces entropy by 1 and 2 bits, respectively. Thus, the adjective modulates the distribution of entropy reduction, resulting in uniform (UR) or non-uniform (NR) reduction profiles. This study seeks to establish whether referential processing is facilitated: a) by the use of redundant pre-nominal modification (OS), b) by the uniform reduction of entropy (cf. Jaeger, 2010), and c) when these two factors interact. Results from inspection probabilities and the Index of Cognitive Activity — a pupillometric measure of cognitive workload (Demberg & Sayeed, 2016) — indicate that processing was facilitated for both OS and UR, while fixation probabilities show a greater advantage for OS-UR. In conclusion, efficient processing is determined by both informativity of the reference and the rate of entropy reduction.

• https://www.researchgate.net/publication/322556329_The_interplay_of_specificity_and_referential_entropy_reduction_in_situated_communication

@inproceedings{Tourtourietal2017d,
title = {The interplay of specificity and referential entropy reduction in situated communication},
author = {Elli Tourtouri and Francesca Delogu and Matthew W. Crocker},
url = {https://www.researchgate.net/publication/322556329_The_interplay_of_specificity_and_referential_entropy_reduction_in_situated_communication},
year = {2017},
date = {2017},
booktitle = {10th Annual Embodied and Situated Language (ESLP) Conference},
publisher = {Higher School of Economics},
address = {Moscow, Russia},
abstract = {In situated communication, reference can be established with expressions conveying either precise (Minimally-Specified, MS) or redundant (Over-Specified, OS) information. For example, while in Figure 1, “Find the blue ball” identifies exactly one object in all panels, only in the top displays is the adjective required. There is no consensus, however, concerning whether OS hinders processing (e.g., Engelhardt et al., 2011) or not (e.g., Tourtouri et al., 2015). Additionally, as incoming words incrementally restrict the referential domain, they contribute to the reduction of uncertainty regarding the target (i.e., referential entropy). Depending on the distribution of objects, the same utterance results in different entropy reduction profiles: “blue” reduces entropy by 1.58 bits in the right panels, and by .58 bits in the left ones, while “ball” reduces entropy by 1 and 2 bits, respectively. Thus, the adjective modulates the distribution of entropy reduction, resulting in uniform (UR) or non-uniform (NR) reduction profiles. This study seeks to establish whether referential processing is facilitated: a) by the use of redundant pre-nominal modification (OS), b) by the uniform reduction of entropy (cf. Jaeger, 2010), and c) when these two factors interact. Results from inspection probabilities and the Index of Cognitive Activity — a pupillometric measure of cognitive workload (Demberg & Sayeed, 2016) — indicate that processing was facilitated for both OS and UR, while fixation probabilities show a greater advantage for OS-UR. In conclusion, efficient processing is determined by both informativity of the reference and the rate of entropy reduction.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Over-specifications (OS) are expressions that provide more information than minimally required for the identification of a referent, thereby violating Grice’s 2nd Quantity Maxim [1]. In Figure 1, for example, the expression “Find the blue ball” identifies exactly one object in all panels, but only in the top displays is the adjective required to disambiguate the target. In recent years, psycholinguistic research has tried to test the empirical validity of Grice’s Maxim, resulting in conflicting findings. That is, there is evidence both that OS hinders [2,3] and that it facilitates [4,5] referential processing. The current study investigates the influence of OS on visually-situated processing, when the context allows both a minimally-specified (MS) and an OS interpretation of pre-nominal adjectives (cf. Fig.1). Additionally, as the utterance unfolds over time, incoming words incrementally restrict the search space. In this sense, information on “blue” and “ball” is determined not only by their probability to occur in this context, but also by the amount of uncertainty about the target they reduce — in information theoretic terms [6]. A greater reduction of the referential set size on the adjective (A&C) results in a more uniform reduction profile (Uniform Reduction, UR), as the adjective reduces entropy by 1.58 bits and the noun by 1 bit. On the other hand, a moderate reduction of the set size on the adjective (B&D) results in a less uniform reduction profile (Nonuniform Reduction, NR): the adjective reduces entropy by .58 bits and the noun by 2 bits. This study examines whether, above and beyond any effects of specificity, the rate at which incoming words reduce visual entropy also affects referential processing.

• TourtouriDeloguCrocker     (0.54MB)
• https://www.researchgate.net/publication/322571202_Over-specification_Uniform_Reduction_of_Visual_Entropy_Facilitate_Referential_Processing

@inproceedings{Tourtourietal2017b,
title = {Overspecification and uniform reduction of visual entropy facilitate referential processing},
author = {Elli Tourtouri and Francesca Delogu and Matthew W. Crocker},
url = {https://www.researchgate.net/publication/322571202_Over-specification_Uniform_Reduction_of_Visual_Entropy_Facilitate_Referential_Processing},
year = {2017},
date = {2017},
booktitle = {XPrag2017},
address = {Cologne, Germany},
abstract = {Over-specifications (OS) are expressions that provide more information than minimally required for the identification of a referent, thereby violating Grice’s 2nd Quantity Maxim [1]. In Figure 1, for example, the expression “Find the blue ball” identifies exactly one object in all panels, but only in the top displays is the adjective required to disambiguate the target. In recent years, psycholinguistic research has tried to test the empirical validity of Grice’s Maxim, resulting in conflicting findings. That is, there is evidence both that OS hinders [2,3] and that it facilitates [4,5] referential processing. The current study investigates the influence of OS on visually-situated processing, when the context allows both a minimally-specified (MS) and an OS interpretation of pre-nominal adjectives (cf. Fig.1). Additionally, as the utterance unfolds over time, incoming words incrementally restrict the search space. In this sense, information on “blue” and “ball” is determined not only by their probability to occur in this context, but also by the amount of uncertainty about the target they reduce — in information theoretic terms [6]. A greater reduction of the referential set size on the adjective (A&C) results in a more uniform reduction profile (Uniform Reduction, UR), as the adjective reduces entropy by 1.58 bits and the noun by 1 bit. On the other hand, a moderate reduction of the set size on the adjective (B&D) results in a less uniform reduction profile (Nonuniform Reduction, NR): the adjective reduces entropy by .58 bits and the noun by 2 bits. This study examines whether, above and beyond any effects of specificity, the rate at which incoming words reduce visual entropy also affects referential processing.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Behavioral studies demonstrate the influence of speaker gaze in visually-situated spoken language comprehension. We present an ERP experiment examining the influence of speaker’s gaze congruency on listeners’ comprehension of referential expressions related to a shared visual scene. We demonstrate that listeners exploit speakers’ gaze toward objects in order to form sentence continuation expectations: Compared to a congruent gaze condition, we observe an increased N400 when (a) the lack of gaze (neutral) does not allow for upcoming noun prediction, and (b) when the noun violates gaze-driven expectations (incongruent). The later also results in a late (sustained) positivity, reflecting the need to update the assumed situation model. We take the combination of the N400 and late positivity as evidence that speaker gaze influences both lexical retrieval and integration processes, respectively (Brouwer et al., in press). Moreover, speaker gaze is interpreted as reflecting referential intentions (Staudte & Crocker, 2011).

• CogSci2017     (0.24MB)
• https://www.researchgate.net/publication/325969989_The_Influence_of_Speaker%27s_Gaze_on_Sentence_Comprehension_An_ERP_Investigation

@inproceedings{Jachmann2017,
title = {The Influence of Speaker's Gaze on Sentence Comprehension: An ERP Investigation},
author = {Torsten Jachmann and Heiner Drenhaus and Maria Staudte and Matthew W. Crocker},
url = {https://www.researchgate.net/publication/325969989_The_Influence_of_Speaker%27s_Gaze_on_Sentence_Comprehension_An_ERP_Investigation},
year = {2017},
date = {2017},
booktitle = {Proceedings of the 39th Annual Conference of the Cognitive Science Society},
pages = {2261-2266},
abstract = {Behavioral studies demonstrate the influence of speaker gaze in visually-situated spoken language comprehension. We present an ERP experiment examining the influence of speaker’s gaze congruency on listeners’ comprehension of referential expressions related to a shared visual scene. We demonstrate that listeners exploit speakers’ gaze toward objects in order to form sentence continuation expectations: Compared to a congruent gaze condition, we observe an increased N400 when (a) the lack of gaze (neutral) does not allow for upcoming noun prediction, and (b) when the noun violates gaze-driven expectations (incongruent). The later also results in a late (sustained) positivity, reflecting the need to update the assumed situation model. We take the combination of the N400 and late positivity as evidence that speaker gaze influences both lexical retrieval and integration processes, respectively (Brouwer et al., in press). Moreover, speaker gaze is interpreted as reflecting referential intentions (Staudte & Crocker, 2011).},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

In situated communication, reference to an entity in the shared visual context can be established using eitheranexpression that conveys precise (minimally specified) or redundant (over-specified) information. There is, however, along-lasting debate in psycholinguistics concerningwhether the latter hinders referential processing. We present evidence from an eyetrackingexperiment recordingfixations as well asthe Index of Cognitive Activity –a novel measure of cognitive workload –supporting the view that over-specifications facilitate processing. We further present originalevidence that, above and beyond the effect of specificity,referring expressions thatuniformly reduce referential entropyalso benefitprocessing

• Tourtouri, Delogu, Crocker - 2017 - Specificity and Entropy Reduction in situated referential processing     (2.47MB)
• https://www.mpi.nl/publications/item3309545/specificity-and-entropy-reduction-situated-referential-processing

@inproceedings{Tourtouri2017,
title = {Specificity and entropy reduction in situated referential processing},
author = {Elli Tourtouri and Francesca Delogu and Matthew W. Crocker},
url = {https://www.mpi.nl/publications/item3309545/specificity-and-entropy-reduction-situated-referential-processing},
year = {2017},
date = {2017},
booktitle = {39th Annual Conference of the Cognitive Science Society},
address = {Austin, Texas, USA},
abstract = {In situated communication, reference to an entity in the shared visual context can be established using eitheranexpression that conveys precise (minimally specified) or redundant (over-specified) information. There is, however, along-lasting debate in psycholinguistics concerningwhether the latter hinders referential processing. We present evidence from an eyetrackingexperiment recordingfixations as well asthe Index of Cognitive Activity –a novel measure of cognitive workload –supporting the view that over-specifications facilitate processing. We further present originalevidence that, above and beyond the effect of specificity,referring expressions thatuniformly reduce referential entropyalso benefitprocessing},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

The Uniform Information Density (UID) hypothesis links production strategies with comprehension processes, predicting that speakers will utilize flexibility in encoding in order to increase uniformity in the rate of information transmission, as measured by surprisal (Jaeger, 2010). Evidence in support of UID comes primarily from studies focusing on word-level effects, e.g. demonstrating that surprisal predicts the omission/inclusion of optional words. Here we investigate whether comprehenders are sensitive to the information density of alternative encodings that are more syntactically complex. We manipulated the syntactic encoding of complex noun phrases in German via meaning-preserving pre-nominal and post-nominal modification in contexts that were either predictive or non-predictive. We then used the G-maze reading task to measure online comprehension during self-paced reading. The results are consistent with the UID hypothesis. Length-adjusted reading times were facilitated for pre-nominally modified head nouns, and this effect was larger in non-predictive contexts.

• https://www.semanticscholar.org/paper/Information-density-of-encodings%3A-The-role-of-in-Sikos-Greenberg/06a47324b53bc53e0e4762fd1547091d8b2392f1

@inproceedings{Sikos2017,
title = {Information density of encodings: The role of syntactic variation in comprehension},
author = {Les Sikos and Clayton Greenberg and Heiner Drenhaus and Matthew W. Crocker},
url = {https://www.semanticscholar.org/paper/Information-density-of-encodings%3A-The-role-of-in-Sikos-Greenberg/06a47324b53bc53e0e4762fd1547091d8b2392f1},
year = {2017},
date = {2017},
booktitle = {Proceedings of the 39th Annual Conference of the Cognitive Science Society(CogSci 2017)},
pages = {3168-3173},
address = {Austin, Texas, USA},
abstract = {The Uniform Information Density (UID) hypothesis links production strategies with comprehension processes, predicting that speakers will utilize flexibility in encoding in order to increase uniformity in the rate of information transmission, as measured by surprisal (Jaeger, 2010). Evidence in support of UID comes primarily from studies focusing on word-level effects, e.g. demonstrating that surprisal predicts the omission/inclusion of optional words. Here we investigate whether comprehenders are sensitive to the information density of alternative encodings that are more syntactically complex. We manipulated the syntactic encoding of complex noun phrases in German via meaning-preserving pre-nominal and post-nominal modification in contexts that were either predictive or non-predictive. We then used the G-maze reading task to measure online comprehension during self-paced reading. The results are consistent with the UID hypothesis. Length-adjusted reading times were facilitated for pre-nominally modified head nouns, and this effect was larger in non-predictive contexts.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

A model of sentence production is presented, which implements a strategy that produces sentences with more uniform surprisal profiles, as compared to other strategies, and in accordance to the Uniform Information Density Hypothesis (Jaeger, 2006; Levy & Jaeger, 2007). The model operates at the algorithmic level combining information concerning word probabilities and sentence lengths, representing a first attempt to model UID as resulting from underlying factors during language production. The sentences produced by this model showed indeed the expected tendency, having more uniform surprisal profiles and lower average word surprisal, in comparison to other production strategies.

• https://cogsci.mindmodeling.org/2017/papers/0333/paper0333.pdf

@inproceedings{Calvillo2017,
title = {Fast and Easy: Approximating uniform information density in language production},
author = {Jesús Calvillo},
url = {https://cogsci.mindmodeling.org/2017/papers/0333/paper0333.pdf},
year = {2017},
date = {2017},
publisher = {39th Annual Conference of the Cognitive Science Society},
address = {Austin, Texas, USA},
abstract = {A model of sentence production is presented, which implements a strategy that produces sentences with more uniform surprisal profiles, as compared to other strategies, and in accordance to the Uniform Information Density Hypothesis (Jaeger, 2006; Levy & Jaeger, 2007). The model operates at the algorithmic level combining information concerning word probabilities and sentence lengths, representing a first attempt to model UID as resulting from underlying factors during language production. The sentences produced by this model showed indeed the expected tendency, having more uniform surprisal profiles and lower average word surprisal, in comparison to other production strategies.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

For many real-word applications, the considered data is given as a time sequence that becomes available in an orderly fashion, where the order incorporates important information about the entities of interest. The work presented in this thesis deals with two such cases by introducing new sequential estimation solutions. More precisely, we introduce a: I. Sequential Bayesian estimation framework to solve the multiple speaker localization, detection and tracking problem. This framework is a complete pipeline that includes 1) new observation estimators, which extract a fixed number of potential locations per time frame; 2) new unsupervised Bayesian detectors, which classify these estimates into noise/speaker classes and 3) new Bayesian filters, which use the speaker class estimates to track multiple speakers.

This framework was developed to tackle the low overlap detection rate of multiple speakers and to reduce the number of constraints generally imposed in standard solutions. II. Sequential neural estimation framework for language modeling, which overcomes some of the shortcomings of standard approaches through merging of different models in a hybrid architecture. That is, we introduce two solutions that tightly merge particular models and then show how a generalization can be achieved through a new mixture model. In order to speed-up the training of large vocabulary language models, we introduce a new extension of the noise contrastive estimation approach to batch training.

• http://nbn-resolving.de/urn:nbn:de:bsz:291-scidok-ds-272280
• https://doi.org/http://dx.doi.org/10.22028/D291-27228

@phdthesis{Oualil2017b,
title = {Sequential estimation techniques and application to multiple speaker tracking and language modeling},
author = {Youssef Oualil},
url = {http://nbn-resolving.de/urn:nbn:de:bsz:291-scidok-ds-272280},
doi = {https://doi.org/http://dx.doi.org/10.22028/D291-27228},
year = {2017},
date = {2017},
school = {Saarland University},
address = {Saarbruecken, Germany},
abstract = {For many real-word applications, the considered data is given as a time sequence that becomes available in an orderly fashion, where the order incorporates important information about the entities of interest. The work presented in this thesis deals with two such cases by introducing new sequential estimation solutions. More precisely, we introduce a: I. Sequential Bayesian estimation framework to solve the multiple speaker localization, detection and tracking problem. This framework is a complete pipeline that includes 1) new observation estimators, which extract a fixed number of potential locations per time frame; 2) new unsupervised Bayesian detectors, which classify these estimates into noise/speaker classes and 3) new Bayesian filters, which use the speaker class estimates to track multiple speakers. This framework was developed to tackle the low overlap detection rate of multiple speakers and to reduce the number of constraints generally imposed in standard solutions. II. Sequential neural estimation framework for language modeling, which overcomes some of the shortcomings of standard approaches through merging of different models in a hybrid architecture. That is, we introduce two solutions that tightly merge particular models and then show how a generalization can be achieved through a new mixture model. In order to speed-up the training of large vocabulary language models, we introduce a new extension of the noise contrastive estimation approach to batch training.},
pubstate = {published},
type = {phdthesis}
}

Copy BibTeX to Clipboard

The performance of Neural Network (NN)-based language models is steadily improving due to the emergence of new architectures, which are able to learn different natural language characteristics. This paper presents a novel framework, which shows that a significant improvement can be achieved by combining different existing heterogeneous models in a single architecture. This is done through 1) a feature layer, which separately learns different NN-based models and 2) a mixture layer, which merges the resulting model features. In doing so, this architecture benefits from the learning capabilities of each model with no noticeable increase in the number of model parameters or the training time. Extensive experiments conducted on the Penn Treebank (PTB) and the Large Text Compression Benchmark (LTCB) corpus showed a significant reduction of the perplexity when compared to state-of-the-art feedforward as well as recurrent neural network architectures.

• https://arxiv.org/abs/1708.06989

@inproceedings{Oualil2017b,
title = {A neural network approach for mixing language models},
author = {Youssef Oualil and Dietrich Klakow},
url = {https://arxiv.org/abs/1708.06989},
year = {2017},
date = {2017},
publisher = {ICASSP 2017},
abstract = {The performance of Neural Network (NN)-based language models is steadily improving due to the emergence of new architectures, which are able to learn different natural language characteristics. This paper presents a novel framework, which shows that a significant improvement can be achieved by combining different existing heterogeneous models in a single architecture. This is done through 1) a feature layer, which separately learns different NN-based models and 2) a mixture layer, which merges the resulting model features. In doing so, this architecture benefits from the learning capabilities of each model with no noticeable increase in the number of model parameters or the training time. Extensive experiments conducted on the Penn Treebank (PTB) and the Large Text Compression Benchmark (LTCB) corpus showed a significant reduction of the perplexity when compared to state-of-the-art feedforward as well as recurrent neural network architectures.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Traditionally, short-range Language Models (LMs) like the conventional n-gram models have been used for language model adaptation. Recent work has improved performance for such tasks using adapted long-span models like Recurrent Neural Network LMs (RNNLMs). With the first pass performed using a large background n-gram LM, the adapted RNNLMs are mostly used to rescore lattices or N-best lists, as a second step in the decoding process. Ideally, these adapted RNNLMs should be applied for first-pass decoding. Thus, we introduce two ways of applying adapted long-short-term-memory (LSTM) based RNNLMs for first-pass decoding. Using available techniques to convert LSTMs to approximated versions for first-pass decoding, we compare approximated LSTMs adapted in a Fast Marginal Adaptation framework (FMA) and an approximated version of architecture-based-adaptation of LSTM. On a conversational speech recognition task, these differently approximated and adapted LSTMs combined with a trigram LM outperform other adapted and unadapted LMs. Here, the architecture-adapted LSTM combination obtains a 35.9 % word error rate (WER) and is outperformed by FMA-based LSTM combination obtaining the overall lowest WER of 34.4 %

• https://www.researchgate.net/publication/319185101_Approximated_and_Domain-Adapted_LSTM_Language_Models_for_First-Pass_Decoding_in_Speech_Recognition

@inproceedings{Singh2017,
title = {Approximated and domain-adapted LSTM language models for first-pass decoding in speech recognition},
author = {Mittul Singh and Youssef Oualil and Dietrich Klakow},
url = {https://www.researchgate.net/publication/319185101_Approximated_and_Domain-Adapted_LSTM_Language_Models_for_First-Pass_Decoding_in_Speech_Recognition},
year = {2017},
date = {2017},
publisher = {18th Annual Conference of the International Speech Communication Association (INTERSPEECH)},
address = {Stockholm, Sweden},
abstract = {Traditionally, short-range Language Models (LMs) like the conventional n-gram models have been used for language model adaptation. Recent work has improved performance for such tasks using adapted long-span models like Recurrent Neural Network LMs (RNNLMs). With the first pass performed using a large background n-gram LM, the adapted RNNLMs are mostly used to rescore lattices or N-best lists, as a second step in the decoding process. Ideally, these adapted RNNLMs should be applied for first-pass decoding. Thus, we introduce two ways of applying adapted long-short-term-memory (LSTM) based RNNLMs for first-pass decoding. Using available techniques to convert LSTMs to approximated versions for first-pass decoding, we compare approximated LSTMs adapted in a Fast Marginal Adaptation framework (FMA) and an approximated version of architecture-based-adaptation of LSTM. On a conversational speech recognition task, these differently approximated and adapted LSTMs combined with a trigram LM outperform other adapted and unadapted LMs. Here, the architecture-adapted LSTM combination obtains a 35.9 % word error rate (WER) and is outperformed by FMA-based LSTM combination obtaining the overall lowest WER of 34.4 %},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Word embeddings are high-dimensional vector representations of words and are thus difficult to interpret. In order to deal with this, we introduce an unsupervised parameter free method for creating a hierarchical graphical clustering of the full ensemble of word vectors and show that this structure is a geometrically meaningful representation of the original relations between the words. This newly obtained representation can be used for better understanding and thus improving the embedding algorithm and exhibits semantic meaning, so it can also be utilized in a variety of language processing tasks like categorization or measuring similarity.

• https://aclanthology.org/W17-2404
• https://doi.org/10.18653/v1/W17-2404"

@inproceedings{TroKla2017,
title = {Parameter Free Hierarchical Graph-Based Clustering for Analyzing Continuous Word Embeddings},
author = {Dietrich Klakow and Thomas Trost},
url = {https://aclanthology.org/W17-2404},
doi = {https://doi.org/10.18653/v1/W17-2404"},
year = {2017},
date = {2017},
booktitle = {Proceedings of TextGraphs-11: Graph-based Methods for Natural Language Processing (Workshop at ACL 2017)},
pages = {30-38},
publisher = {Association for Computational Linguistics},
address = {Vancouver, Canada},
abstract = {Word embeddings are high-dimensional vector representations of words and are thus difficult to interpret. In order to deal with this, we introduce an unsupervised parameter free method for creating a hierarchical graphical clustering of the full ensemble of word vectors and show that this structure is a geometrically meaningful representation of the original relations between the words. This newly obtained representation can be used for better understanding and thus improving the embedding algorithm and exhibits semantic meaning, so it can also be utilized in a variety of language processing tasks like categorization or measuring similarity.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard