Báo cáo khoa học: "An Empirical Study on Class-based Word Sense Disambiguation" pdf

... AN EMPIRICAL STUDY ON THEMATIC KNOWLEDGE ACQUISITION BASED ON SYNTACTIC CLUES AND HEURISTICS Rey-Long Liu* and Von-Wun Soo** Department of Computer Science National Tsing-Hua ... function, it can only satisfy the requirements of Go, So, Th, and Re. Because of the preposition "of", "th~ money" can only be Th. As a result, after con,;ulting the con- ... repor...

Ngày tải lên: 23/03/2014, 20:20

... lower. 5 Conclusions and discussion We explored on the WSD task the performance of different levels of abstraction and sense group- ings. We empirically demonstrated that Base Level Concepts are ... Rigau G. 2008. Complete and consistent annotation of wordnet using the top con- cept ontology. In 6th International Conference on Language Resources and Evaluation LREC, Mar- rakesh, Morroco...

Ngày tải lên: 24/03/2014, 03:20

... generated for the Tailored- Concise condition to be more effective than arguments generated for the Tailored-Verbose condition. We also expect the Tailored-Concise condition to be somewhat better ... content, organization, writing style and convincigness. However, evaluations based on Figure 6 Self -report on user’s satisfaction with houses in the HotList Figure 7 Hypotheses on...

Ngày tải lên: 08/03/2014, 05:20

... in Section 4, we an- alyze the outcome of the experiment, and Section 5 discusses related work. Finally, Section 6 draws the main conclusions of this work. 2 Creation of an Information Synthesis testbed We ... evaluation con- ferences such as TREC 2 , CLEF 3 or NTCIR 4 . The title/description/narrative topics commonly used in such evaluation exercises are specially well suited for an Informat...

Ngày tải lên: 20/02/2014, 15:20

... position. 5.3 Phrase-based Voting In chunking, one phrase includes one or more words, and the word tags in one phrase depend on each other. Therefore, we propose a novel vot- ing method based on ... Coordination: These problems are related to the conjunctions ”和(and), 与(and), 或(or), 暨(and)”. They can be divided into two types: chunks with conjunctions and chunks without conjunctions...

Ngày tải lên: 08/03/2014, 02:21

... International Conference on Machine Learning. Hiroyuki Shinnou. 2000. Deterministic Japanese word segmentation by decision list method. In Proceedings of the Sixth Pacific Rim International Conference ... Sixteenth International Conference on Machine Learning, pages 406–414. Simon Tong and Daphne Koller. 2000. Support vector machine active learning with applications to text clas- sificati...

Ngày tải lên: 17/03/2014, 08:20

... the Association for Computational Linguistics:shortpapers, pages 24–29, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics An Empirical Investigation of Discounting in ... perplexity. For evaluation, we train, tune, and test on three disjoint corpora. We consider two different train- ing sets: one of 110M words of NYT from 2000 and 2001 (NYT00+01), and o...

Ngày tải lên: 20/02/2014, 04:20

... Influence -on- Hearer (I -on- H). A Ui tagged with this dimension influences H's future action. DR/dis- tinguishes between S merely laying out options for H's future action (Open-Option), ... Influence -on- Hearer Influence -on- Speaker (I -on- S). A Ui tagged with this dimension potentially commits S (in varying de- grees of strength) to some future course of action. The on...

Ngày tải lên: 20/02/2014, 18:20

... content of the context. A context might consist entirely of articles, pre- positions, conjunctions, etc., and could be ex- pected to contribute less to a translation than one which also contained ... The context consisting of one preceding word appears to be least effective in reducing ambi- guity, being significantly worse than one word following. One word on each side of the...

Ngày tải lên: 16/03/2014, 19:20

... Jurafsky, 2002), WordNet super- sense in the phrase, combination features of frame evoking word & headword, combination features of frame evoking word & phrase type, and combination features ... ascer- tain the contributions of role groups. This dataset consists of the corpus of FrameNet release 1.3 (containing roughly 150,000 annotations), and an additional full-text annotation...

Ngày tải lên: 17/03/2014, 01:20