Tài liệu Báo cáo khoa học: "An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming" pdf

... all models, and for the LM we use an interpolated Kneser-Ney 5-gram model. For GIZA ++, we use the standard training reg- imen up to Model 4, and combine alignments with grow-diag-final-and. For ... noted that forcing align- ments smaller than the model suggests is only used for generating alignments for use in heuristic extrac- tion, and does not affect the training process....

Ngày tải lên: 20/02/2014, 04:20

... ordinary entity-mention model with heuris- tic first-order features. 6 Conclusions This paper presented an expressive entity-mention model for coreference resolution by using Inductive Logic Programming. ... co-refer with “she”. The entity-mention model based on Eq. (2) per- forms coreference resolution at an entity-level. For simplicity, the framework considere...

Ngày tải lên: 20/02/2014, 09:20

... using it as a platform for research including the use of new information sources (which can be easily incorporated into the coreference resolution process as features), different resolution algorithms ... decision trees for coreference resolution. In Proc. IJCAI 1995. Morton, T. S. (2000). Coreference for NLP applications. In Proc. ACL 2000. Moschitti, A. (2006). Making tree...

Ngày tải lên: 20/02/2014, 09:20

... en- tity. Coreference resolution on text datasets is well- studied (e.g., (Cardie and Wagstaff, 1999)). This prior work provides the departure point for our in- vestigation of coreference resolution ... intermittently. Our model treats the relevance of the non-verbal modality as a hidden variable, learned jointly with the class labels. Ap- plied to coreference resolution, thi...

Ngày tải lên: 20/02/2014, 12:20

... Experimental Setup We performed experiments with two parsing mod- els, the Collins (1999) generative model number 2 and the Charniak and Johnson (2005) reranking model. For the first we used a reimplementation (?). ... higher. Figure 1 demonstrates these phenomena for two leading models, Collins (1999) model 2, a generative model, and Charniak and Johnson (2005), a reranking model...

Ngày tải lên: 20/02/2014, 12:20

... degree d. For exam- 66 Proceedings of the ACL 2007 Demo and Poster Sessions, pages 65–68, Prague, June 2007. c 2007 Association for Computational Linguistics An Approximate Approach for Training ... the training and testing time costs for polynomial kernel SVM is far slow than the linear kernel. For example, it took one day to train the CoNLL-2000 task with polynomial kernel...

Ngày tải lên: 20/02/2014, 12:20

... of expectation-maximization algorithms. The DOP model has also been tested as a model for human sentence processing (Bod 2000d). This paper presents ongoing work on DOP models for Lexical-Functional Grammar representations, ... Homecentre An Improved Parser for Data-Oriented Lexical-Functional Analysis Rens Bod Informatics Research Institute, University of Leeds, Leeds LS2 9JT, UK,...

Ngày tải lên: 20/02/2014, 18:20

... higher-level aspects such as analy- sis models and methodological concerns. Finally, when other platforms usually enforce the use of a dedicated document format, LinguaStream is able to process ... (tag set for a given language ), it is impossible to fundamentally modify their be- haviour. Others, on the contrary, provide an anal- ysis model, that is to say, firstly, a formalism for repre...

Ngày tải lên: 22/02/2014, 02:20

... tree description and/or of semantic formu- las. The XMG formalism furthermore supports the sharing of identifiers across dimension hence al- lowing for a straightforward encoding of the syn- tax/semantics ... presented a system, XMG 8 , for produc- ing broad-coverage grammars, system that offers an expressive description language along with an efficient compiler taking advantages from lo...

Ngày tải lên: 22/02/2014, 02:20

... work as basis of or support for own work? Figure 2: Decision tree for annotation Our materials consist of 48 computational lin- guistics papers (22 for Study I, 26 for Study II), taken from ... to be most reproducible in Study II, performed almost as well as trained annotators; Group 1, which performed worst, also happened to have the paper with the lowest reproducibil- ity...

Ngày tải lên: 22/02/2014, 03:20