More Constructions, More Genres: Extending Stanford Dependencies

What it is about

The Stanford scheme was built on newswire and gives little analysis to constructions that are rare there but common in web text: tough adjectives, free relatives, comparatives, small clauses, questions, imperatives, fragments and lists. The paper proposes principled analyses for these. A tough-adjective object gets an xobj relation to the verb it is raised from, and free relatives take the wh-word as head with a relative-clause modifier. Comparatives of the as...as type attach to the gradable word, and loose-joining relations (list, parataxis) and goeswith handle informal text. The data is the Google English Web Treebank, about 250,000 words in five web domains, which the authors were annotating. The converter had no quantitative evaluation yet, and the paper says so.

Ideas

• I1. prag (world frames): derive the verb's object in a tough-adjective sentence ("this address was hard to find") as an event argument, and measure how many such events are recovered on 100 EWT test sentences by hand count (test only).
• I2. en/src/convert.rs: mark the wh-word of a free relative as head with the relative-clause label, and measure LAS of en parse-eval on EWT test before and after, two runs each.
• I3. en/seeds/errors/: add a rule family for web-text repairs (split words such as "hand some", reparandum in speech repairs), and measure rule hits on 200 web sentences from the school corpus against hand-checked labels.
• I4. en/src/morph.rs and en/src/tok.rs: test whether the tokenizer keeps split words and hyphenated compounds apart correctly, counting errors per 1,000 tokens on web text.

For Mova

Touches 23. Complementation (tough adjectives, xcomp/ccomp), 25. Relative clauses (free relatives), 21. The simple clause and 37. Register and variation. Start with I2, since it changes only the converter and is measured by one run of en parse-eval.

Cite

The paper itself, not this card. BibTeX from the library's record of the work.

@inproceedings{marneffe2013more,
  title = {{More Constructions, More Genres: Extending Stanford Dependencies}},
  author = {Marneffe, Marie-Catherine de and Connor, Miriam and Silveira, Natalia and Bowman, Samuel R. and Dozat, Timothy and Manning, Christopher D.},
  booktitle = {Proceedings of the Second International Conference on Dependency Linguistics (DepLing 2013)},
  year = {2013},
  url = {https://aclanthology.org/W13-3721/}
}

References

26 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Bender, Emily M., Dan Flickinger, Stephan Oepen, and Yi Zhang. 2011. Parser evaluation over local and non-local deep dependencies in a large corpus. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 397–408. find our card
2. Bies, Ann, Mark Ferguson, Karen Katz, Robert MacIntyre, Victoria Tredinnick, Grace Kim, Mary Ann Marcinkiewicz, and Britta Schasberger, 1995. Bracketing guidelines for Treebank II style Penn Treebank project. find
3. Borsley, Robert D. 1991. Syntactic Theory: A Unified Approach. Edward Arnold. find
4. Bresnan, Joan. 1973. Syntax of the comparative clause construction in English. Linguistic Inquiry 4. find
5. Bresnan, Joan. 1982. Control and complementation. In Joan Bresnan (ed.), The Mental Representation of Grammatical Relations, pp. 282– 390. MIT Press. find
6. Bresnan, Joan. 2001. Lexical-functional syntax. Blackwell. find
7. Bresnan, Joan, and Jane Grimshaw. 1978. The syntax of free relatives in English. Linguistic Inquiry 9(3):331–391. Buchholz, Sabine, and Erwin Marsi. CoNLL-X shared task on multilingual dependency parsing. In Proceedings of the Tenth Conference on Computational Natural Language Learning, pp. 149–164. find our card
8. Choi, Jinho D., and Martha Palmer. 2012. Guidelines for the Clear style constituent to dependency conversion. Technical report, University of Colorado Boulder, Institute of Cognitive Science. find
9. Chomsky, Noam. 1973. Conditions on transformations. In Stephen Anderson and Paul Kiparsky (eds.), A Festschrift for Morris Halle, pp. 232–286. New York: Holt, Rinehart & Winston. find
10. Culicover, Peter W., and Ray Jackendoff. 2005. Simpler syntax. Oxford University Press. find
11. de Marneffe, Marie-Catherine, Bill MacCartney, and Christopher D. Manning. 2006. Generating typed dependency parses from phrase structure parses. In Proceedings of the 5th International Conference on Language Resources and Evaluation, pp. 449–454. find our card
12. de Marneffe, Marie-Catherine, and Christopher D. Manning. 2008a. Stanford typed dependencies manual. Technical report, Stanford University. find
13. de Marneffe, Marie-Catherine, and Christopher D. Manning. 2008b. The Stanford typed dependencies representation. In Proceedings of the COLING Workshop on Cross-framework and Cross-domain Parser Evaluation, pp. 1–8. find our card
14. Huddleston, Rodney, and Geoffrey K. Pullum. 2002. The Cambridge Grammar of the English Language. Cambridge University Press. ↗ our card
15. Hudson, Richard A. 2010. An Introduction to Word Grammar. Cambridge University Press. ↗
16. Johansson, Richard, and Pierre Nugues. 2007. Extended constituent-to-dependency conversion for English. In Proceedings of NODALIDA 2007. find our card
17. Kübler, Sandra, Ryan McDonald, and Joakim Nivre. 2009. Dependency Parsing, volume 2 of Synthesis Lectures on Human Language Technologies. Morgan & Claypool. find
18. Matthews, Peter H. 2007. Syntactic relations: A critical survey. Cambridge University Press. find
19. Mel’cuk, Igor A. 1988. Dependency syntax: Theory and practice. find
20. SUNY Press. 2006. Perlmutter, David M. (ed.). 1983. Studies in Relational Grammar, volume 1. University of Chicago Press. find
21. Petrov, Slav, and Ryan McDonald. 2012. Overview of the 2012 shared task on parsing the web. In First Workshop on Syntactic Analysis of Non-Canonical Language. find
22. Pollard, Carl, and Ivan A. Sag. 1994. Head-driven Phrase Structure Grammar. University of Chicago Press. find
23. Pyysalo, Sampo, Filip Ginter, Katri Haverinen, Juho Heimonen, Tapio Salakoski, and Veronika Laippala. 2007. On the unification of syntactic annotations under the Stanford dependency scheme: A case study on BioInfer and GENIA. In Proceedings of BioNLP 2007: Biological, translational, and clinical language processing (ACL07), pp. 25–32. find
24. Rimell, Laura, Stephen Clark, and Mark Steedman. 2009. Unbounded dependency recovery for parser evaluation. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pp. 813–821. find our card
25. Sgall, Petr, Eva Hajičová, and Jarmila Panevová. 1986. The meaning of the sentence in its semantic and pragmatic aspects. D. Reidel Publishing Company. find
26. Tesnière, Lucien. 1959. Éléments de syntaxe structurale. Librairie C. Klincksieck. ↗

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/bank-2013-marneffe-more-constructions-more-genres-extending/