@inproceedings{Voorhees:2000:2, added-at = {2007-12-14T02:47:55.000+0100}, author = {Voorhees, Ellen M. and Tice, Dawn M.}, biburl = {http://www.bibsonomy.org/bibtex/2c927d029fd5d4bb57ab873f21229ce0b/diego_ma}, booktitle = {Proc. SIGIR-2000, July, 2000, pp. 200-207}, interhash = {ef062b3afd0e8bb509ece6635755fe05}, intrahash = {c927d029fd5d4bb57ab873f21229ce0b}, keywords = {question_answering resources}, month = {July}, pages = {200-207}, timestamp = {2007-12-14T02:47:55.000+0100}, title = {Building a Question Answering Test Collection}, url = {http://trec.nist.gov/data/qa/qa_main/qa.ps}, year = 2000 } @inproceedings{Szpektor:2004, abstract = {Paraphrase recognition is a critical step for natural language interpretation. Accordingly, many NLP applications would benefit from high coverage knowledge bases of paraphrases. However, the scalability of state-of-the-art paraphrase acquisition approaches is still limited. We present a fully unsupervised learning algorithm for Web-based extraction of entailment relations, an extended model of paraphrases. We focus on increased scalability and generality with respect to prior work, eventually aiming at a full scale knowledge base. Our current implementation of the algorithm takes as its input a verb lexicon and for each verb searches the Web for related syntactic entailment templates. Experiments show promising results with respect to the ultimate goal, achieving much better scalability than prior Web-based methods.}, added-at = {2007-12-14T02:47:13.000+0100}, address = {Barcelona}, author = {Szpektor, Idan and Tanev, Hristo and Dagan, Ido and Coppola, Bonaventura}, biburl = {http://www.bibsonomy.org/bibtex/20ac6c3623a4de9e4d7f00d1b7277c82f/diego_ma}, booktitle = {Proc. Empirical Methods in Natural Language Processing (EMNLP)}, interhash = {94bb0ef9c6b7f501153d84d28c1aa20e}, intrahash = {0ac6c3623a4de9e4d7f00d1b7277c82f}, keywords = {entailment web resources}, timestamp = {2007-12-14T02:47:13.000+0100}, title = {Scaling Web-based Acquisition of Entailment Relations}, url = {http://eprints.pascal-network.org/archive/00000797/}, year = 2004 } @inproceedings{Richardson:1998, abstract = {As a lexical knowledge base constructed automatically from the definitions and example sentences in two machine-readable dictionaries (MRDs), MindNet embodies several features that distinguish it from prior work with MRDs. It is, however, more than this static resource alone. MindNet represents a general methodology for acquiring, structuring, accessing, and exploiting semantic information from natural language text. This paper provides an overview of the distinguishing characteristics of MindNet, the steps involved in its creation, and its extension beyond dictionary text.}, added-at = {2007-12-14T02:45:45.000+0100}, author = {Richardson, Stephen D. and Dolan, William B. and Vanderwende, Lucy}, biburl = {http://www.bibsonomy.org/bibtex/2a0bac759c5d4a5296f0992e9dc6997d6/diego_ma}, booktitle = {Proc. ACL'98}, interhash = {4d364240268c59492df59ae76f23a20d}, intrahash = {a0bac759c5d4a5296f0992e9dc6997d6}, keywords = {NLP resources}, note = {Also Microsoft's technical report MSR-TR-98-23}, pages = {1098-1102}, timestamp = {2007-12-14T02:45:45.000+0100}, title = {MindNet: Acquiring and Structuring Semantic Information from Text}, url = {http://research.microsoft.com/scripts/pubs/view.asp?TR\_ID=MSR-TR-98-23}, year = 1998 } @incollection{Resnik:1998, added-at = {2007-12-14T02:45:36.000+0100}, author = {Resnik, Philip}, biburl = {http://www.bibsonomy.org/bibtex/253fe26d5bfe934aa23d824fcd9c6a6f8/diego_ma}, booktitle = {Machine Translation and the Information Soup}, editor = {Farwell, D. and Gerber, L. and Hovy, E.}, interhash = {6cf36ae12c2daf331d4ce14f318e8af2}, intrahash = {53fe26d5bfe934aa23d824fcd9c6a6f8}, keywords = {machine_translation resources}, publisher = {Springer}, timestamp = {2007-12-14T02:45:36.000+0100}, title = {Parallel Strands: A Preliminary Investigation into Mining the Web for Bilingual Text}, url = {http://www.umiacs.umd.edu/\~{}resnik/pubs.html}, year = 1998 } @article{Palmer:2005, abstract = {The Proposition Bank project takes a practical approach to semantic representation, adding a layer of predicate-argument information, or semantic role labels, to the syntactic structures of the Penn Treebank. The resulting resource can be thought of as shallow, in that it does not represent coreference, quantification, and many other higher-order phenomena, but also broad, in that it covers every instance of every verb in the corpus and allows representative statistics to be calculated. We discuss the criteria used to define the sets of semantic roles used in the annotation process and to analyze the frequency of syntactic/semantic alternations in the corpus. We describe an automatic system for semantic role tagging trained on the corpus and discuss the effect on its performance of various types of information, including a comparison of full syntactic parsing with a flat representation and the contribution of the empty ??trace?? categories of the treebank.}, added-at = {2007-12-14T02:44:44.000+0100}, author = {Palmer, Martha and Gildea, Daniel and Kingsbury, Paul}, biburl = {http://www.bibsonomy.org/bibtex/2df6b4ece2b5ac88387946d7ada2a8162/diego_ma}, interhash = {24e0360bc797311db3dff8d5e38f130d}, intrahash = {df6b4ece2b5ac88387946d7ada2a8162}, journal = {Computational Linguistics}, keywords = {resources thematic_roles}, number = 1, pages = {71-105}, timestamp = {2007-12-14T02:44:44.000+0100}, title = {The Proposition Bank: An Annotated Corpus of Semantic Roles}, url = {http://mitpress.mit.edu/catalog/item/default.asp?ttype=6&tid=17957}, volume = 31, year = 2005 } @inproceedings{Lin:2005, abstract = {In contrast to traditional information retrieval systems, which return ranked lists of documents that users must manually browse through, a question answering system attempts to directly answer natural language questions posed by the user. Although such systems possess language processing capabilities, they still rely on traditional document retrieval techniques to generate an initial candidate set of documents. In this paper, we argue that document retrieval for question answering represents a different task than retrieving documents in response to more general retrospective information needs. Thus, to guide future system development, specialized question answering test collections must be constructed. We have shown that the current evaluation resources have major shortcomings, and to remedy the situation, we have manually created a small, reusable question answering test collection for research purposes. This article describes our methodology for building this test collection and discusses issues we encountered along the way regarding the notion of ?answer correctness?.}, added-at = {2007-12-14T02:42:33.000+0100}, author = {Lin, Jimmy}, biburl = {http://www.bibsonomy.org/bibtex/282a0e0c21ee324f677ac9dc34ef64812/diego_ma}, booktitle = {Proc. SIGIR'05}, interhash = {bedf8921e99bf7867e4bb6a165bf26dc}, intrahash = {82a0e0c21ee324f677ac9dc34ef64812}, keywords = {question_answering evaluation resources}, timestamp = {2007-12-14T02:42:33.000+0100}, title = {Evaluation of Resources for Question Answering Evaluation}, year = 2005 } @article{Lenat:1995, abstract = {Authors Doug Lenat, George Miller, and Toshio Yokoi critique and defend one another's systems, ideas, and approaches to AI developments}, added-at = {2007-12-14T02:42:18.000+0100}, author = {Lenat, Doug and Miller, George and Yokoi, Toshio}, biburl = {http://www.bibsonomy.org/bibtex/24c48efdd51e9b3df65dcdd5c81be4427/diego_ma}, interhash = {342ef44c78ec45bcf4c19071031c40a0}, intrahash = {4c48efdd51e9b3df65dcdd5c81be4427}, journal = {Communications of the ACM}, keywords = {resources Cyc WordNet}, number = 11, pages = {45-48}, timestamp = {2007-12-14T02:42:18.000+0100}, title = {{CYC}, {WordNet}, and {EDR}: Critiques and Responses}, volume = 38, year = 1995 } @article{Kilgarriff:2003, abstract = {The Web, teeming as it is with language data, of all manner of varieties and languages, in vast quantity and freely available, is a fabulous linguist's playground. This special issue of Computational Linguistics explores ways in which this dream is being explored.}, added-at = {2007-12-14T02:41:32.000+0100}, author = {Kilgarriff, Adam and Grefenstette, Gregory}, biburl = {http://www.bibsonomy.org/bibtex/2fe424bf3422feb1aefbe2ea9444a12e2/diego_ma}, interhash = {c8c19bbb5f9a4cfb78460ef0df6df797}, intrahash = {fe424bf3422feb1aefbe2ea9444a12e2}, journal = {Computational Linguistics}, keywords = {resources web}, number = 3, pages = {333-347}, timestamp = {2007-12-14T02:41:32.000+0100}, title = {Introduction to the Special Issue on the Web as Corpus}, volume = 29, year = 2003 } @article{Corley:2001, abstract = {The Gsearch system allows the selection of sentences by syntactic criteria from text corpora, even when these corpora contain no prior syntactic markup. This is achieved by means of a fast chart parser, which takes as input a grammar and a search expression specified by the user. Gsearch features a modular architecture that can be extended straightforwardly to give access to new corpora. The Gsearch architecture also allows interfacing with external linguistic resources (such as taggers and lexical databases). Gsearch can be used with graphical tools for visualizing the results of a query.}, added-at = {2007-12-14T02:37:41.000+0100}, author = {Corley, Steffan and Corley, Martin and Keller, Frank and Crocker, Matthew W. and Trewin, Shari}, biburl = {http://www.bibsonomy.org/bibtex/2d6806fd557cb6c5f6fb56dffc9714dfa/diego_ma}, interhash = {408f7cffdc622893f32593ceb60d73b2}, intrahash = {d6806fd557cb6c5f6fb56dffc9714dfa}, journal = {Computers and the Humanities}, keywords = {resources}, number = 2, pages = {81-94}, timestamp = {2007-12-14T02:37:41.000+0100}, title = {Finding Syntactic Structure in Unparsed Corpora}, volume = 35, year = 2001 }