"Talk to me with left, right, and angles": Lexical entrainment in spoken Hebrew dialogue

What it is about

The question is whether Hebrew speakers adapt their word choice to each other in a Map Task, as English speakers do. The corpus is the Open University of Israel Map Task Corpus (MaTaCOp): 16 dyads, about six hours, with words lemmatized by a hand-made list of forms. Two existing measures are used: a word-fraction similarity over a fixed word list, and a negated perplexity of one speaker's trigram model on the partner's words. Each similarity is compared with non-partners of the same gender, and the multiple tests are corrected with Benjamini–Hochberg within families. Speakers entrain on the 25 most frequent lemmas, on directional terms (t(15) = 6.64, p = 7.9e-06) and on overall language; they do not entrain on hedge words or imperative forms, which differs from English, and followers entrain more than leaders.

Ideas

• I1. Group related measurements into families and correct within each family (Benjamini–Hochberg), then report the corrected and raw results side by side. This is a rule for any Mova comparison that runs several tests at once, and it belongs in the measurement notes in docs/.
• I2. A closed list of direction words (four compass terms and six relative terms, such as "left" and "right") with every grammatical form counted per lemma. The paper's hand-made form-to-lemma list is the same mechanism as a lexicon table, and it gives a small Modern Hebrew lexical test.
• I3. An imperative class that includes the second-person prefix forms (te-lex) and leaves out the reduced future, which the paper excludes as ambiguous (citing Bat-El 2002). The Modern Hebrew verb tables should keep the reduced future in a separate class, not in the imperatives.

For Mova

I1 is a measurement rule for docs/ and the test harness. I2 goes into 8. Lexicon and register. I3 goes into 05b. Verb paradigms: the strong verb in seven binyanim and the weak roots. The dialogue setting itself is outside Mova's current text scope, so no entrainment measure is built into the parser.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/2021.eacl-main.23

@inproceedings{weise2021talk,
  title = {{"Talk to me with left, right, and angles": Lexical entrainment in spoken Hebrew dialogue}},
  author = {Weise, Andreas and Silber-Varod, Vered and Lerner, Anat and Hirschberg, Julia and Levitan, Rivka},
  booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume},
  year = {2021},
  doi = {10.18653/v1/2021.eacl-main.23},
  url = {https://doi.org/10.18653/v1/2021.eacl-main.23}
}

References

35 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abdel-Rahman H Abu-Melhim, Mohammad H Abood, and Taysir M Shehadeh. 2016. Interpreting types and functions of Arabic-English code-switching in light of modern principles of social psychology. British Journal of Humanities and Social Sciences, 15(1). find
2. Anne H Anderson, Miles Bader, Ellen Gurman Bard, Elizabeth Boyle, Gwyneth Doherty, Simon Garrod, Stephen Isard, Jacqueline Kowtko, Jan McAllister, Jim Miller, et al. 1991. The HCRC map task corpus. Language and speech, 34(4):351–366. find
3. Jacob Azogui, Anat Lerner, and Vered Silber-Varod. 2016. The Open University of Israel Map Task Corpus (MaTaCOp). https://www.openu.ac.il/ en/academicstudies/matacop/ . ↗
4. Outi Bat-El. 2002. True truncation in colloquial hebrew imperatives. Language, pages 651–683. find
5. Yoav Benjamini and Yosef Hochberg. 1995. Controlling the false discovery rate: a practical and powerful approach to multiple testing. Journal of the Royal Statistical Society, Series B, 57(1):289–300. find
6. Susan E. Brennan and Herbert H. Clark. 1996. Conceptual pacts and lexical choice in conversation. Journal of experimental psychology: Learning, memory, and cognition, 22(6):1482–1493. find
7. Hendrik Buschmeier, Kirsten Bergmann, and Stefan Kopp. 2009. An Alignment-capable Microplanner for Natural Language Generation. In Proceedings of the 12th European Workshop on Natural Language Generation, pages 82–89. find
8. Vera Cabarrão, Isabel Trancoso, Ana Isabel Mata, Helena Moniz, and Fernando Batista. 2016. Global analysis of entrainment in dialogues. In International Conference on Advances in Speech and Language Technologies for Iberian Languages, pages 215–223. Springer. find
9. Howard Giles, Nikolas Coupland, and Justine Coupland. 1991. Accommodation theory: Communication, context, and consequence. In Contexts of accommodation: Developments in applied sociolinguistics, pages 1–68. Cambridge University Press. find
10. Amy L. Gonzales, Jeffrey T. Hancock, and James W. Pennebaker. 2010. Language Style Matching as a Predictor of Social Dynamics in Small Groups. Communication Research, 37(1):3–19. find
11. Agustı́n Gravano, Štefan Beňuš, Rivka Levitan, and Julia Hirschberg. 2014. Three ToBI-based measures of prosodic entrainment and their correlations with speaker engagement. In Spoken Language Technology (SLT), 2014 IEEE Workshop on, pages 578–583. find
12. Nancy Hawker. 2018. The mirage of Arabrew: Ideologies for understanding Arabic-Hebrew contact. Language in Society, 47(2):219–244. find
13. Tamar Katriel. 2004. Dialogic moments: From soul talks to talk radio in Israeli culture. Wayne State University Press. find
14. Mitsuhiko Kimoto, Takamasa Iio, Masahiro Shiomi, Ivan Tanev, Katsunori Shimohara, and Norihiro Hagita. 2017. Gender effects on lexical alignment in human-robot interaction. IEEJ Transactions on Electronics, Information and Systems, 137(12):1625–1632. find
15. Rivka Levitan and Julia Hirschberg. 2011. Measuring acoustic-prosodic entrainment with respect to multiple levels and dimensions. In INTERSPEECH 2011, pages 3081–3084. find
16. Rivka Levitan, Laura Willson, Agustı́n Gravano, Štefan Beňuš, Julia Hirschberg, and Ani Nenkova. 2012. Acoustic-Prosodic Entrainment and Social Behavior. In NAACL HLT, pages 11–19. find
17. Sarah Ita Levitan, Jessica Xiang, and Julia Hirschberg. 2018. Acoustic-Prosodic and Lexical Entrainment in Deceptive Dialogue. In Speech Prosody, pages 532–536. find
18. Cristian Danescu-Niculescu-Mizil, Michael Gamon, and Susan Dumais. 2011. Mark My Words! Linguistic Style Accommodation in Social Media. In WWW, pages 745–754. find
19. José Lopes, Maxine Eskenazi, and Isabel Trancoso. 2015. From rule-based to data-driven lexical entrainment models in spoken dialog systems. Computer Speech and Language, 31(1):87–112. find
20. Markus De Jong, Mariët Theune, and Dennis Hofs. 2008. Politeness and alignment in dialogues with a virtual guide. In AAMAS ’08: Proceedings of the 7th International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 1, pages 207–214. find
21. Ani Nenkova, Agustı́n Gravano, and Julia Hirschberg. 2008. High Frequency Word Entrainment in Spoken Dialogue. In ACL HLT, pages 169–172. find
22. Heather Friedberg, Diane Litman, and Susannah B F Paletz. 2012. Lexical entrainment and success in student engineering groups. In Spoken Language Technology (SLT), 2012 IEEE Workshop on, pages 404–409. find
23. Kate G. Niederhoffer and James W. Pennebaker. 2002. Linguistic Style Matching in Social Interaction. Journal of Language and Social Psychology, 21(4):337–360. find
24. Jennifer S. Pardo. 2006. On phonetic convergence during conversational interaction. The Journal of the Acoustical Society of America, 119(4):2382–2393. find
25. Jennifer S Pardo, Adelya Urmanche, Sherilyn Wilman, Jaclyn Wiener, Nicholas Mason, Keagan Francis, and Melanie Ward. 2018. A comparison of phonetic convergence in conversational interaction and speech shadowing. Journal of Phonetics, 69:1–11. find
26. Zahra Rahimi, Anish Kumar, Diane Litman, Susannah Paletz, and Mingzhi Yu. 2017. Entrainment in Multi-Party Spoken Dialogues at Multiple Linguistic Levels. Interspeech 2017, pages 1696–1700. find
27. David Reitter and Johanna D. Moore. 2007. Predicting Success in Dialogue. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 808–815. find
28. David Reitter, Johanna D. Moore, and Frank Keller. 2006. Priming of Syntactic Rules in Task-Oriented Dialogue and Spontaneous Conversation. In CogSci, pages 685–690. find
29. Vered Silber-Varod, Sarit Malayev, and Anat Lerner. 2020. Positioning oneself in different roles: Structural and lexical measures of power relations between speakers in map task corpus. Speech Communication, 117:1 – 12. find
30. Andreas Stolcke. 2002. SRILM - an extensible language modeling toolkit. In ICSLP, pages 901–904. find
31. Khiet P Truong and Dirk Heylen. 2012. Measuring prosodic alignment in cooperative task-based conversations. In Interspeech 2012, pages 843–846. find
32. Teun A. Van Dijk. 1997. Discourse as social interaction, volume 2. Sage. find
33. Andreas Weise and Rivka Levitan. 2018. Looking for structure in lexical and acoustic-prosodic entrainment behaviors. In NAACL HLT, pages 297–302. find
34. Andreas Weise, Sarah Ita Levitan, Julia Hirschberg, and Rivka Levitan. 2019. Individual differences in acoustic-prosodic entrainment in spoken dialogue. Speech Communication, 115(April):78–87. find
35. Andreas Weise, Vered Silber-Varod, Anat Lerner, Julia Hirschberg, and Rivka Levitan. 2020. Entrainment in spoken Hebrew dialogues. Journal of Phonetics, 83(11):1–16. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/eacl-2021-weise-talk-me-left-right-angles/