Anaphora Processing and Applications: 8th Discourse Anaphora by Iris Hendrickx, Orphée De Clercq, Veronique Hoste (auth.), PDF

By Iris Hendrickx, Orphée De Clercq, Veronique Hoste (auth.), Iris Hendrickx, Sobha Lalitha Devi, António Branco, Ruslan Mitkov (eds.)

ISBN-10: 3642259162

ISBN-13: 9783642259166

This ebook constitutes the refereed complaints of the eighth Discourse Anaphora and Anaphor answer Colloquium, DAARC 2011, held in Faro, Portugal, in October 2011. The sixteen revised complete papers awarded have been conscientiously reviewed and chosen from forty five preliminary submissions. The papers are equipped in topical sections on computational answer method and platforms; language research and illustration; and human processing and performance.

Show description

Read or Download Anaphora Processing and Applications: 8th Discourse Anaphora and Anaphor Resolution Colloquium, DAARC 2011, Faro, Portugal, October 6-7, 2011. Revised Selected Papers PDF

Best nonfiction_5 books

Warriner's handbook: second course : grammar, usage, - download pdf or read online

Lecturers version of Warriners instruction manual Fourth direction

Extra info for Anaphora Processing and Applications: 8th Discourse Anaphora and Anaphor Resolution Colloquium, DAARC 2011, Faro, Portugal, October 6-7, 2011. Revised Selected Papers

Sample text

Static databases like WordNet suffer from a low coverage impacting the performance in bridging resolution. In French, similar databases are even smaller than in English, which further motivates the need for automatic lexical relation extraction methods. fragment/pot, about archeology) so that we cannot expect to find some of those relations in a static lexicon, but perhaps in texts if their usage is frequent enough. 1 A Static Lexical Database As there is no free equivalent to the Princeton Wordnet 2 for French, we use the WOLF database3 [23], a resource built from WordNet and several multilingual resources.

For years, the coreference resolution task has been treated with classification approaches. Denis and Baldridge [3] showed that the task is more reasonable and even better in performance if it is cast as a ranking task. In such an approach, the competition between individual candidates is captured directly in the trained model, which does not hold for classification models. In recent years unsupervised approaches made significant performance progress as well. Indeed, Haghighi and Klein [7] created an unsupervised system based on inference in Bayesian networks, which outperforms best known supervised resolvers.

LIBLINEAR: A library for large linear classification. Mach. Learn. Res. 9, 1871–1874 (2008) 14. : A statistical approach to anaphora resolution. In: Proceedings of the Sixth Workshop on Very Large Corpora, pp. 161–170 (1998) 15. : Storing the web in memory: Space efficient language models with constant time retrieval. In: EMNLP, pp. 262–272 (2010) 16. : A bayesian classifier for the identification of non-referential pronouns in Arabic. In: INFOS, Special Track On Natural Language Processing and Knowledge Mining (2010) 17.

Download PDF sample

Anaphora Processing and Applications: 8th Discourse Anaphora and Anaphor Resolution Colloquium, DAARC 2011, Faro, Portugal, October 6-7, 2011. Revised Selected Papers by Iris Hendrickx, Orphée De Clercq, Veronique Hoste (auth.), Iris Hendrickx, Sobha Lalitha Devi, António Branco, Ruslan Mitkov (eds.)


by Mark
4.3

Rated 4.97 of 5 – based on 26 votes