@inproceedings{Roark:1999, abstract = {This paper examines efficient predictive broad-coverage parsing without dynamic programming. In contrast to bottom-up methods, depth-first top-down parsing produces partial parses that are fully connected trees spanning the entire left context, from which any kind of non-local dependency or partial semantic interpretation can in principle be read. We contrast two predictive parsing approaches, top-down and left-corner parsing, and find both to be viable. In addition, we find that enhancement with non-local information not only improves parser accuracy, but also substantially improves the search efficiency.}, added-at = {2007-12-14T02:45:54.000+0100}, author = {Roark, Brian and Johnson, Mark}, biburl = {http://www.bibsonomy.org/bibtex/2ecb48cd1d1818a0015f7128de2257088/diego_ma}, booktitle = {Proc. ACL'99}, interhash = {79c00970e4c4ca6552ba2fa3b149f3c9}, intrahash = {ecb48cd1d1818a0015f7128de2257088}, keywords = {parsers statistic_nlp}, note = {\myurl{http://arXiv.org/abs/cs/0008017}}, pages = {421-428}, timestamp = {2007-12-14T02:45:54.000+0100}, title = {Efficient Probabilistic Top-down and Left-corner Parsing}, url = {http://arXiv.org/abs/cs/0008017}, year = 1999 } @book{Manning:1999, added-at = {2007-12-14T02:42:52.000+0100}, address = {Cambridge, MA}, author = {Manning, Christopher D. and Sch{{\"u}}tze, Hinrich}, biburl = {http://www.bibsonomy.org/bibtex/22fad675aa6ae88082af2507c16d54343/diego_ma}, interhash = {a81df02f92f266a51183fe936f588a08}, intrahash = {2fad675aa6ae88082af2507c16d54343}, keywords = {statistic_nlp}, publisher = {MIT Press}, timestamp = {2007-12-14T02:42:52.000+0100}, title = {Foundations of Statistical Natural Language Processing}, year = 1999 } @inproceedings{Lapata:2001, abstract = {In this paper we investigate polysemous adjectives whose meaning varies depending on the nouns they modify (e.g., fast ). We acquire the meanings of these adjectives from a large corpus and propose a probabilistic model which provides a ranking on the set of possible interpretations. We identify lexical semantic information automatically by exploiting the consistent correspondences between surface syntactic cues and lexical meaning. We evaluate our results against paraphrase judgments elicited experimentally from humans and show that the model's ranking of meanings correlates reliably with human intuitions: meanings that are found highly probable by the model are also rated as plausible by the subjects.}, added-at = {2007-12-14T02:41:59.000+0100}, address = {Pittsburgh}, author = {Lapata, Maria}, biburl = {http://www.bibsonomy.org/bibtex/2286bd5351488a152431d27dccdea1b7c/diego_ma}, booktitle = {Proceedings NAACL 2001}, interhash = {c6348a9663cd7edb317052dfb0ac5919}, intrahash = {286bd5351488a152431d27dccdea1b7c}, keywords = {statistic_nlp}, timestamp = {2007-12-14T02:41:59.000+0100}, title = {A Corpus-based Account of Regular Polysemy: The Case of Context-sensitive Adjectives}, url = {http://ucrel.lancs.ac.uk/acl/N/N01/N01-1009.pdf}, year = 2001 } @inproceedings{Collins:1996, added-at = {2007-12-14T02:37:34.000+0100}, author = {Collins, Michael John}, biburl = {http://www.bibsonomy.org/bibtex/2ecd94c145e7e59310fc267ce90b70e73/diego_ma}, booktitle = {Proc. ACL}, interhash = {2515afecb4be6a345908def7d8674308}, intrahash = {ecd94c145e7e59310fc267ce90b70e73}, keywords = {parsers statistic_nlp}, publisher = {Santa Cruz}, timestamp = {2007-12-14T02:37:34.000+0100}, title = {A New Statistical Parser Based on Bigram Lexical Dependencies}, url = {http://www.research.att.com/\~{}mcollins/}, year = 1996 } @phdthesis{Brill:1993, added-at = {2007-12-14T02:36:34.000+0100}, author = {Brill, Eric}, biburl = {http://www.bibsonomy.org/bibtex/25c58ec5cb110920272d7de02dd45f15d/diego_ma}, interhash = {fbdae652acc463932e434d89f54c5bb3}, intrahash = {5c58ec5cb110920272d7de02dd45f15d}, keywords = {statistic_nlp}, school = {University of Pennsylvania}, timestamp = {2007-12-14T02:36:34.000+0100}, title = {A Corpus-Based Approach to Language Learning}, url = {http://www.cs.jhu.edu/~brill/acadpubs.html}, year = 1993 }