Enhanced English Universal Dependencies: An Improved Representation for Natural Language Understanding Tasks

What it is about

Shallow understanding tasks such as relation extraction need direct links between content words, which a strict basic tree lacks: in "Fred started to laugh" the controlled verb has no subject edge. The authors define an enhanced English UD graph that keeps all basic relations and adds controlled subjects, propagated conjuncts, augmented relation names with the preposition (nmod:in), and augmented conjunctions. Their enhanced++ graph goes further and may delete basic edges, to treat partitives ("both of the girls") and multiword prepositions ("in front of") as one head with a quantifier or a flat expression, and to copy conjoined prepositions. They also give a constituency-to-basic-UD converter, which on EWT v1.1 reaches LAS 92.6, UAS 96.1 and accuracy 93.9 over the whole corpus, with the lowest scores on email signatures and on learner-written reviews and questions. The limits they name are the controlled quantifier case ("Everybody wants to buy a house") and distributive readings of conjoined subjects.

Ideas

I1. en/src/convert.rs or a new enhancement pass: add the enhanced UD edges (controlled subject, propagated conjunct, relation with preposition) as a derived layer in MISC; measure the relation-extraction F1 of prag on EWT test with the basic tree and with the enhanced layer.
I2. Enhanced++ partitive and multiword-preposition rules, with the expression lists in en/seeds/lexicon; measure the share of nmod and det arcs in EWT test that change, and the triple precision on 100 sampled sentences checked by hand.
I3. en/src/parse.rs wh-attachment: a feature for the wh-word that tests the verb's selectional frame, which the paper uses to attach "what" to the embedded verb; measure LAS on wh-questions of EWT test, twice for determinism.
I4. en/src/convert.rs: report LAS per genre against EWT v1.1 in the same layout as the paper's table; this is the baseline for every change to the converter.

For Mova

Touches languages/en/22-phrases, 23-complementation, 24-coordination-subordination, 25-relative-clauses and 26-questions, and the en crate (convert.rs, parse.rs, lin.rs for the reverse direction) and the world/prag relation builder. The enhanced layer belongs in MISC, since the Mova dialect keeps the basic tree fixed. Measure first the prag relation-extraction F1 with and without enhanced edges.

Topics: Universal Dependencies

Cite

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

@inproceedings{schuster2016enhanced,
  title = {{Enhanced English Universal Dependencies: An Improved Representation for Natural Language Understanding Tasks}},
  author = {Schuster, Sebastian and Manning, Christopher D.},
  booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)},
  year = {2016},
  url = {https://aclanthology.org/L16-1376/}
}

References

27 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

Airola, A., Pyysalo, S., Björne, J., Pahikkala, T., Ginter, F., and Salakoski, T. (2008). All-paths graph kernel for protein-protein interaction extraction with evaluation of cross-corpus learning. BMC Bioinformatics, 9(Suppl 11):S2. find
Angeli, G., Premkumar, M. J., and Manning, C. D. (2015). Leveraging linguistic structure for open domain information extraction. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL. find
Banarescu, L., Bonial, C., Cai, S., Georgescu, M., Griffitt, K., Hermjakob, U., Knight, K., Koehn, P., Palmer, M., and Schneider, N. (2013). Abstract meaning representation for sembanking. In Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse. find our card
Barwise, J. and Cooper, R. (1981). Generalized quantifiers and natural language. Linguistics and Philosophy, 4(2):159–219. find
Chambers, N., Cer, D., Grenager, T., Hall, D., Kiddon, C., MacCartney, B., de Marneffe, M.-C., Ramage, D., Yeh, E., and Manning, C. D. (2007). Learning alignments and leveraging natural logic. In ACL-PASCAL Workshop on Textual Entailment and Paraphrasing. find
Chen, D. and Manning, C. D. (2014). A fast and accurate dependency parser using neural networks. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). find our card
Choi, J. D. and Palmer, M. (2012). Guidelines for the Clear style constituent to dependency conversion. Technical report, Technical Report 01-12, University of Colorado at Boulder. find
Collins, M. (1999). Head-driven statistical models for natural language processing. Ph.D. thesis, University of Pennsylvania. find
de Marneffe, M.-C., MacCartney, B., and Manning, C. D. (2006). Generating typed dependency parses from phrase structure parses. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC-2006). find our card
de Marneffe, M.-C., Dozat, T., Silveira, N., Haverinen, K., Ginter, F., Nivre, J., and Manning, C. D. (2014). Universal Stanford Dependencies: A cross-linguistic typology. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC-2014). find our card
Galanis, D. and Androutsopoulos, I. (2010). An extractive supervised two-stage method for sentence compression. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL). find
Genzel, D. (2010). Automatically learning source-side reordering rules for large scale machine translation. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING). find
Jespersen, O. (1954). A modern English grammar, volume 3. George Allen & Unwin Limited. find
Keenan, E. L. and Stavi, J. (1986). A semantic characterization of natural language determiners. Linguistics and Philosophy, 9(3):253–326. find
Levy, R. and Galen, A. (2006). Tregex and Tsurgeon: tools for querying and manipulating tree data structures. In 5th International Conference on Language Resources and Evaluation (LREC-2006). find
Marcus, M. P., Santorini, B., and Marcinkiewicz, M. A. (1993). Building a large annotated corpus of English: The Penn treebank. Computational Linguistics, 19(2). find our card
Mausam, Schmitz, M., Bart, R., Soderland, S., and Etzioni, O. (2012). Open language learning for information extraction. In Proceedings of Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CONLL). find
McDonald, R., Nivre, J., Quirmbach-Brundage, Y., Goldberg, Y., Das, D., Ganchev, K., Hall, K., Petrov, S., Zhang, H., Täckström, O., Bedini, C., Bertomeu Castelló, N., and Lee, J. (2013). Universal dependency annotation for multilingual parsing. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL). find
Nivre, J., Agić, Ž., Aranzabe, M. J., Atutxa, A., Bosco, C., Choi, J., de Marneffe, M.-C., Dozat, T., Farkas, R., Foster, J., Ginter, F., Goenaga, I., Gojenola, K., Goldberg, Y., Hajič, J., Johannsen, A. T., Kanerva, J., Kuokkala, J., Laippala, V., Lenci, A., Lindén, K., Ljubešić, N., Lynn, T., Manning, C. D., Martı́nez, H. A., McDonald, R., Missilä, A., Montemagni, S., Nurmi, H., Osenova, P., Petrov, S., Piitulainen, J., Plank, B., Prokopidis, P., Pyysalo, S., Seeker, W., Seraji, M., Silveira, N., Simi, M., Simov, K., Smith, A., Tsarfaty, R., Vincze, V., and Zeman, D. (2015). Universal Dependencies 1.1. http://hdl.handle.net/11234/LRT-1478. ↗
Nivre, J., de Marneffe, M.-C., Ginter, F., Goldberg, Y., Hajič, J., Manning, C. D., McDonald, R., Petrov, S., Pyysalo, S., Silveira, N., Tsarfaty, R., and Zeman, D. (2016). Universal dependencies v1: A multilingual treebank collection. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC-2016). find our card
Nyblom, J., Kohonen, S., Haverinen, K., Salakoski, T., and Ginter, F. (2013). Predicting conjunct propagation and other extended Stanford Dependencies. In Proceedings of the Second International Conference on Dependency Linguistics (DepLing 2013). find our card
Palmer, M., Gildea, D., and Kingsbury, P. (2005). The Proposition Bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71–106. find our card
Poon, H. and Domingos, P. (2009). Unsupervised semantic parsing. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP). find
Schuster, S., Krishna, R., Chang, A., Fei-Fei, L., and Manning, C. D. (2015). Generating semantically precise scene graphs from textual descriptions for improved image retrieval. In Proceedings of the Fourth Workshop on Vision and Language (VL15). find
Shieber, S. M. (1984). The design of a computer language for linguistic information. In Proceedings of the 10th International Conference on Computational Linguistics. find
Simone, R. and Masini, F. (2014). On light nouns. Word Classes: Nature, typology and representations, 332:51. find
Tsarfaty, R. (2013). A unified morpho-syntactic scheme of Stanford Dependencies. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL). find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/ud-2016-schuster-enhanced-english-universal-dependencies-improved/