A Corpus and Model Integrating Multiword Expressions and Supersenses

What it is about

The paper defines one task: find lexical expressions in running text, single- or multi-word, and label the noun and verb ones with a supersense (41 coarse classes). The data is the reviews section of the English Web Treebank, about 55,000 words, annotated in phases, with two independent annotations for every sentence. Inter-annotator F1 is 76% for noun expressions, 93% for verb expressions and 88% for all after the combined phase. A first-order structured perceptron tags the tokens in BIO style, and it identifies the MWEs and labels the supersenses jointly. The joint model reaches about 70% class-labelling F1 on the reviews data. An off-the-shelf supersense tagger gets 49.97% F1 on the same reviews, so the domain gap is large.

Ideas

• I1. Add a coarse semantic class to nouns and verbs in en/src/lexgen.rs and data/lemmas.tsv, filled from WordNet through onto. Measure: the share of correct senses in onto/src/wsd.rs on a hand-checked sample of 200 EWT review tokens, with and without the class.
• I2. A deterministic span pass for MWEs in en: greedy longest match over the lexicon, with the gaps the paper marks. Measure: link-based F1 on the paper's reviews annotation. That annotation (STREUSLE, over EWT reviews) is CC BY-SA like EWT; keep it as the test, not as a source for the span list.
• I3. Use the paper's first-sense baseline as the reference in onto/src/wsd.rs: the predominant sense on the same data must be reported before any claim about the context model. The paper reports a 10-point F1 gain of its SemCor model over first sense.

For Mova

The chapters are 19. The lexicon: vocabulary, multiword expressions and register and 10. Word classes. The code is en/src/lexgen.rs (class column), onto/src/wsd.rs (sense baseline) and prag expressions. The reviews corpus is test-only. Gains on the paper's data do not transfer to Mova's numbers; measure on EWT test.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.3115/v1/n15-1177

@inproceedings{schneider2015corpus,
  title = {{A Corpus and Model Integrating Multiword Expressions and Supersenses}},
  author = {Schneider, Nathan and Smith, Noah A.},
  booktitle = {Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  year = {2015},
  doi = {10.3115/v1/n15-1177},
  url = {https://doi.org/10.3115/v1/n15-1177}
}

References

29 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Giuseppe Attardi, Luca Baronti, Stefano Dei Rossi, and Maria Simi. 2013. SuperSense Tagging with a Maximum Entropy Markov Model. In Bernardo Magnini, Francesco Cutugno, Mauro Falcone, and Emanuele Pianta, editors, Evaluation of Natural Language and Speech Tools for Italian, number 7689 in Lecture No… find
2. Giuseppe Attardi, Stefano Dei Rossi, Giulia Di Pietro, Alessandro Lenci, Simonetta Montemagni, and Maria Simi. 2010. A resource and tool for super-sense tagging of Italian texts. In Nicoletta Calzolari, Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odijk, Stelios Piperidis, Mike Rosner, and Da… find
3. Timothy Baldwin and Su Nam Kim. 2010. Multiword expressions. In Nitin Indurkhya and Fred J. Damerau, editors, Handbook of Natural Language Processing, Second Edition, pages 267–292. CRC Press, Taylor and Francis Group, Boca Raton, FL. find
4. Ann Bies, Justin Mott, Colin Warner, and Seth Kulick. 2012. English Web Treebank. Technical Report LDC2012T13, Linguistic Data Consortium, Philadelphia, PA. URL http: //www.ldc.upenn.edu/Catalog/catalogEntry. jsp?catalogId=LDC2012T13 . find
5. Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit. O’Reilly Media, Inc., Sebastopol, CA. find
6. Peter F. Brown, Peter V. deSouza, Robert L. Mercer, Vincent J. Della Pietra, and Jenifer C. Lai. 1992. Class-based n-gram models of natural language. Computational Linguistics, 18(4):467–479. find
7. Massimiliano Ciaramita and Yasemin Altun. 2006. Broad-coverage sense disambiguation and information extraction with a supersense sequence tagger. In Proc. of EMNLP, pages 594–602. Sydney, Australia. find
8. Massimiliano Ciaramita and Mark Johnson. 2003. Supersense tagging of unknown nouns in WordNet. In Michael Collins and Mark Steedman, editors, Proc. of EMNLP, pages 168–175. Sapporo, Japan. find our card
9. Michael Collins. 2002. Discriminative training methods for Hidden Markov Models: theory and experiments with perceptron algorithms. In Proc. of EMNLP, pages 1–8. Philadelphia, PA, USA. find our card
10. Christiane Fellbaum. 1990. English verbs as a semantic net. International Journal of Lexicography, 3(4):278– 301. find
11. Christiane Fellbaum, editor. 1998. WordNet: an electronic lexical database. MIT Press, Cambridge, MA. find
12. Edouard Grave, Guillaume Obozinski, and Francis Bach. 2013. Hidden Markov tree models for semantic class induction. In Proc. of CoNLL, pages 94–103. Sofia, Bulgaria. find
13. Michael Heilman. 2011. Automatic factual question generation from text. Ph.D. dissertation, Carnegie Mellon University, Pittsburgh, Pennsylvania. URL http://www.ark.cs.cmu.edu/mheilman/questions/papers/heilman-question-generation-dissertation.pdf . ↗
14. Anders Johannsen, Dirk Hovy, Héctor Martínez Alonso, Barbara Plank, and Anders Søgaard. 2014. More or less supervised supersense tagging of Twitter. In Proc. of *SEM, pages 1–11. Dublin, Ireland. find
15. George A. Miller. 1990. Nouns in WordNet: a lexical inheritance system. International Journal of Lexicography, 3(4):245–264. find
16. Gerhard Paaß and Frank Reichartz. 2009. Exploiting semantic constraints for estimating supersenses with CRFs. In Proc. of the Ninth SIAM International Conference on Data Mining, pages 485–496. Sparks, Nevada. find
17. Scott S. L. Piao, Paul Rayson, Dawn Archer, Andrew Wilson, and Tony McEnery. 2003. Extracting multiword expressions with a semantic tagger. In Proc. of the ACL 2003 Workshop on Multiword Expressions: Analysis, Acquisition and Treatment, pages 49–56. Sapporo, Japan. find
18. Scott Songlin Piao, Paul Rayson, Dawn Archer, and Tony McEnery. 2005. Comparing and combining a semantic tagger and a statistical tool for MWE extraction. Computer Speech & Language, 19(4):378–397. find
19. Davide Picca, Alfio Massimiliano Gliozzo, and Simone Campora. 2009. Bridging languages by SuperSense entity tagging. In Proc. of NEWS, pages 136–142. Suntec, Singapore. find
20. Davide Picca, Alfio Massimiliano Gliozzo, and Massimiliano Ciaramita. 2008. Supersense Tagger for Italian. In Nicoletta Calzolari, Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, and Daniel Tapias, editors, Proc. of LREC, pages 2386–2390. Marrakech, Morocco. find
21. Likun Qiu, Yunfang Wu, Yanqiu Shao, and Alexander Gelbukh. 2011. Combining contextual and structural information for supersense tagging of Chinese unknown words. In Computational Linguistics and Intelligent Text Processing: Proceedings of the 12th International Conference (CICLing’11), volume 6608 o… find
22. Lance A. Ramshaw and Mitchell P. Marcus. 1995. Text chunking using transformation-based learning. In Proc. of the Third ACL Workshop on Very Large Corpora, pages 82–94. Cambridge, MA. find
23. Stefano Dei Rossi, Giulia Di Pietro, and Maria Simi. 2013. Description and results of the SuperSense tagging task. In Bernardo Magnini, Francesco Cutugno, Mauro Falcone, and Emanuele Pianta, editors, Evaluation of Natural Language and Speech Tools for Italian, number 7689 in Lecture Notes in Compute… find
24. Nathan Schneider. 2014. Lexical Semantic Analysis in Natural Language Text. Ph.D. dissertation, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA. URL http://www.cs.cmu.edu/~nschneid/thesis/thesis-print.pdf . ↗
25. Nathan Schneider, Emily Danchik, Chris Dyer, and Noah A. Smith. 2014a. Discriminative lexical semantic segmentation with gaps: running the MWE gamut. Transactions of the Association for Computational Linguistics, 2:193–206. find
26. Nathan Schneider, Behrang Mohit, Chris Dyer, Kemal Oflazer, and Noah A. Smith. 2013. Supersense tagging for Arabic: the MT-in-the-middle attack. In Proc. of NAACL-HLT, pages 661–667. Atlanta, Georgia, USA. find
27. Nathan Schneider, Behrang Mohit, Kemal Oflazer, and Noah A. Smith. 2012. Coarse lexical semantic annotation with supersenses: an Arabic case study. In Proc. of ACL, pages 253–258. Jeju Island, Korea. find our card
28. Nathan Schneider, Spencer Onuffer, Nora Kazour, Emily Danchik, Michael T. Mordowanec, Henrietta Conrad, and Noah A. Smith. 2014b. Comprehensive annotation of multiword expressions in a social web corpus. In Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph… find our card
29. Yulia Tsvetkov, Nathan Schneider, Dirk Hovy, Archna Bhatia, Manaal Faruqui, and Chris Dyer. 2014. Augmenting English adjective senses with supersenses. In Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, and Stelios Pi… find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/missing-2015-schneider-corpus-model-integrating-multiword-expressions/