Tài liệu Báo cáo khoa học: "Improving Pronoun Resolution Using Statistics-Based Semantic Compatibility Information" doc

... improve the resolution of neutral pronouns. 1 Introduction Semantic compatibility is an important factor for pronoun resolution. Since pronouns, especially neu- tral pronouns, carry little semantics ... candidate (i.e.,“the + candi”). 3 Applying the Semantic Compatibility In this section, we discuss how to incorporate the statistics-based semantic compatibility for pronoun...

Ngày tải lên: 20/02/2014, 15:20

... used to train semantic role labellers (Basili et al., 2009). In this paper, we generate high-quality broad- coverage semantic annotations using an automatic approach that does not rely on a semantic ... results on using joint syntactic -semantic learning to improve the quality of the semantic annotations from automatic cross- lingual transfer. Results on correlations between synt...

Ngày tải lên: 20/02/2014, 04:20

... and then prototypes are built using the contexts of the sense-labeled words. However, in order to cluster accurately, it is important to capture both the syntax and semantics of words. While many approaches ... models. 1 1 Introduction Vector-space models (VSM) represent word mean- ings with vectors that capture semantic and syntac- tic information of words. These representations can be u...

Ngày tải lên: 19/02/2014, 19:20

... that the systems using the improved bi-directional alignments achieve higher quality of translation than the baseline system. If the same alignment method is used, the systems using CM-3 got ... phrase table for phrase-based SMT. To improve BWA, we re-estimate the align- ment probabilities by using the collocation prob- abilities of words in the same cept. A cept is the set of so...

Ngày tải lên: 20/02/2014, 04:20

... suggest that by using rich features, a better SRC solver can be directly trained without using hierarchical architecture. There are also some attempts at re- laxing the necessity of using full syntactic ... Second, parsers provide semantic classifiers plenty of syntactic information, not to only recog- nize arguments from all candidate constituents but also to classify their detailed...

Ngày tải lên: 20/02/2014, 04:20

... romising performance. 1 Introduction Pronoun anaphora resolution is the task of find- ing the correct antecedent for a given pronominal anaphor in a document. It is a subtask of corefer- ence resolution, which is ... emPronouns. The FHMM-based pronoun resolution system does a better job than the global ranking technique and other approaches. This is a promising start for this novel FH...

Ngày tải lên: 20/02/2014, 04:20

... feature to represent the Section Header with a string value normalized using (Meystre and Haug, 2005). The system only using contextual features gave reasonable results: F 1 -measure overall ... Feature Pruning: We changed the pruning strategy to use document frequency values instead of corpus frequency for the lexical features, and used document frequency > 1 for normalized wor...

Ngày tải lên: 20/02/2014, 05:20

... lecture, using information retrieval tech- niques that exploit the lecture slides to automat- ically mine the World Wide Web for documents related to the presented topic. WEB adapts IC- SISWB using ... presentation slides, au- tomatically mining the World Wide Web for doc- uments related to the topic as attested by text on the slides, and using these to build a better- matching langua...

Ngày tải lên: 20/02/2014, 07:20

... first is employing a filtering process using a lightweight classifier to remove unnecessary state candidates beforehand (Figure 2 (2)), and the second is the using the fea- ture forest model (Miyao ... possible candidate states, and then filter out low probability states by using a light-weight classifier, and represent them by using feature forest. Table 2: Features used in the naive Baye...

Ngày tải lên: 20/02/2014, 12:20

... personal document collec- tion. We used the following four standard doc- ument collections: (i) MED (1033 document ab- stracts from the National Library of Medicine), (ii) CRAN (1400 documents ... corresponding counts for each document. The term vectors for a document collection can be organized into a term by document co-occurrence matrix. When di- rectly using these representations, syn...

Ngày tải lên: 22/02/2014, 02:20