Báo cáo khoa học: "Coreference Resolution with World Knowledge" docx

... (2003)). With recent ad- vances in lexical semantics research and the devel- opment of large-scale knowledge bases, researchers have begun to employ world knowledge for corefer- ence resolution. World ... Ponzetto and Strube (2006). 3.2 World Knowledge from Annotated Data Since world knowledge is needed for coreference resolution, a human annotator must have employed world knowl...

Ngày tải lên: 07/03/2014, 22:20

... resolution, called Reconcile, that can serve as a software infrastructure to sup- port the creation of, experimentation with, and evaluation of coreference resolvers. Reconcile was designed with ... architecture of the system includes five major steps. Starting with a corpus of docu- ments together with a manually annotated corefer- ence resolution answer key 1 , Reconcile performs 1...

Ngày tải lên: 20/02/2014, 04:20

... Proceedings of CoNLL 2003, pages 142–147. Edmonton, Canada. Olga Uryupina. 2006. Coreference resolution with and without linguistic knowledge. In Proceedings of LREC 2006. Kees van Deemter and Rodger ... and variations of the resolution model al- lows us to reveal biases of the metrics. Coreference resolution systems have been tested on languages other than English only within the ACE...

Ngày tải lên: 07/03/2014, 22:20

... by ellipsis resolution. (1) Harry sank a destroyer and so did Bill and they both went down with all hands. (Grinder and Postal, 1971, 279) Most approaches to ellipsis and anaphora resolution, e.g. ... specified representa- tions (Dalrymple et al., 1991) scope resolution can- not simply precede ellipsis resolution but rather is interleaved with it. Crouch (1995) considers order- sen...

Ngày tải lên: 08/03/2014, 07:20

... system with the sin- gle semantic relatedness feature beats those with other solutions. Compared with the baseline, the system can get improvement in recall (up to 2.9% as in NWire), with a similar ... E j with at most three words (or symbols) in between are retrieved. For each retrieved string, we extract a surface pat- tern by replacing expression E i with a mark <#t1#> an...

Ngày tải lên: 17/03/2014, 04:20

... resolution Compared with the gains in pronoun resolution, the improvement in non-pronoun resolution is slight. As shown in Table 3, our approach resolves non-pronominal anaphors with the recall ... pronoun resolution and non- pronoun resolution. The main reason is the absence of candidate filtering strategy in their approach (this is why the recall equals to the precision...

Ngày tải lên: 23/03/2014, 19:20

... resolve bridging references when supplied with an adequate lexicon; the best results have been obtained by restricting the domain and feeding the system with specific knowledge (Carter, 1987). ... collection of 20 Wall Street Jour- nal articles from the Penn Treebank Cor- pus and our experiments with WordNet to identify relations between bridging descrip- tions and their anteceden...

Ngày tải lên: 08/03/2014, 21:20

... are augmented with latent variables. Fine- grained CFG rules are automatically in- duced from a parsed corpus by training a PCFG-LA model using an EM-algorithm. Because exact parsing with a PCFG-LA ... model of parse trees that we call PCFG with latent annotations (PCFG-LA). This model is an extension of PCFG models in which non-terminal symbols are anno- tated with latent variables....

Ngày tải lên: 31/03/2014, 03:20

... activities combine with top-down, expectation-driven ones to cooperatively determine the most I~ely interpretation of the input (Lesgoid and Perfetti, 1981). Roughly speaking, humans begin with a set ... discourse) and on non-linguistic world knowledge. As information from the text becomes available, the reader strengthens those hypotheses that are consistent with the input and...

Ngày tải lên: 01/04/2014, 00:20

... preferences that we have used for anaphor resolution with partial parsing. Introduction Nowadays there are two different approaches to anaphor resolution: integrated and alternative. The ... anaphor resolution with a high rate of correct analyses: 85%. This one operates primarily on syntactic information only. In Kennedy and Boguraev (1996) it is proposed an algorithm for a...

Ngày tải lên: 08/03/2014, 05:21