Báo cáo khoa học: "Experimenting with Distant Supervision for Emotion Classification" ppt

... Association for Computational Linguistics, pages 482–491, Avignon, France, April 23 - 27 2012. c 2012 Association for Computational Linguistics Experimenting with Distant Supervision for Emotion ... could bias results; for this experiment, therefore, we cre- ated datasets with an even balance of emotions among the negative instances. For each conven- tion type C and each...

Ngày tải lên: 08/03/2014, 21:20

... is other title word with the second high similarity score with the word W. This formula means that a word with high ranking in a category has a high similarity score with the title word of ... clustering technique for text categorization. Since our method does not use any labeled data, it cannot be fairly compared with the former approaches. Therefore, we compare our metho...

Ngày tải lên: 20/02/2014, 16:20

... 02-21 of CCGbank for training, sec- tion 00 for development, and section 23 for test- ing. The input is POS-tagged using the tagger of Ratnaparkhi (1996). However, since parsing with the new model ... (henceforth: SD) HWDep which captures word-word dependencies that are de- fined in terms of the derivation tree itself. It as- sumes that binary trees (with parent category ) have one he...

Ngày tải lên: 20/02/2014, 16:20

... described rules for generating Gapping, though none of them has made any effort to formulate a rule for detecting Gapping. (Ross 67b) is the first who suggested a rule for Gapping. The formalisation ... representation for the left clause can be constructed. Then we combine the two to get a representation for the sentence. Sentences llke the following may raise difficulty fo...

Ngày tải lên: 08/03/2014, 18:20

... Snow, and Daniel Juraf- sky. 2009. Distant supervision for relation extrac- tion without labeled data. In Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics (ACL-2009), ... Association for Computational Linguistics, pages 541–550, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Knowledge-Based Weak Supervi...

Ngày tải lên: 30/03/2014, 21:20

... paper, we formulate ex- tractive summarization as a two step learn- ing problem building a generative model for pattern discovery and a regression model for inference. We calculate scores for sentences ... and Eq.(8) 9: end for 10: end for 11: Obtain scores Y = {score(o m )} |O| m=1 The similarity between p o m ,l and p s n ,l is obtained by first calculating the divergence with in...

Ngày tải lên: 20/02/2014, 04:20

... category for input “meets the”. A sample phrase structure tree is shown before and after the right-corner transform in Figures 2 and 3. Our parser operates over a right-corner trans- formed probabilistic ... Association for Computational Linguistics, pages 849–857. Daniel Gildea. 2003. Loosely tree-based alignment for machine translation. In Proceedings of the 41st An- nual Meeting of t...

Ngày tải lên: 20/02/2014, 04:20

... translation with the corresponding target phrase for the unknown term. We propose using monolingual paraphrasing methods and resources for this task to obtain a more extensive set of rules for paraphrasing ... resource for entailment rules. Paraphrases are generated using synonyms. Directionally entailed texts are created using hypernyms, which typically conform with entailment. W...

Ngày tải lên: 20/02/2014, 07:20

... in inference/learning time and it is only suitable for representing constraints by enforcing label consis- tency. We wish to identify ambiguous labels with more general dependency without additional time cost in ... exploit non-local information in the next section. 3 Incorporating Non-local Information 3.1 Using Trigger Features To exploit non-local information to sequential la- beling...

Ngày tải lên: 20/02/2014, 12:20

... information. In terms of cognitive modeling, such as for acquisition, the model must be able to ac- count for how words can be successfully segmented and learned by a child/speaker without formal ... interval form as s I = ”c 1 I 1 c 2 I 2 c 3 I 3 c 4 I 4 ”. We store the co-occurrence character/word boundaries informa- tion in a fixed size (span) vector. For example, we collect the infor...

Ngày tải lên: 20/02/2014, 12:20