Báo cáo khoa học: "Combining Coherence Models and Machine Translation Evaluation Metrics for Summarization Evaluation" doc

... for Computational Linguistics, pages 1006–1014, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Combining Coherence Models and Machine Translation Evaluation ... Figure 4a and 4b, evaluation metrics al- ways correlate better on the initial task than on the update task. This suggests that there is much room for improvement for...

Ngày tải lên: 07/03/2014, 18:20

... exist for adjectives and adverbs, and is very shallow for verbs. Essentially SALAAM relies on variability in translation as it is important to have multiple words in a typeset to allow for disambiguation. In ... results. 5.2 Evaluation Metrics We use the scorer2 software to report fine- grained (P)recision and (R)ecall and (F)-measure. 5.3 Baselines We consider here several...

Ngày tải lên: 17/03/2014, 00:20

... MK–EN, and Pr(b|e) and Pr(e|b) for EN–BG, where m, e, and b stand for a Macedonian, an English, and a Bulgarian word. Then, following (Callison-Burch et al., 2006; Wu and Wang, 2007; Utiyama and ... MK–EN and an EN–BG bitext. First, we induced IBM-model-4 word alignments for MK–EN and EN–BG, from which we extracted four conditional lexical translation probabilities: Pr...

Ngày tải lên: 23/03/2014, 14:20

... Syntactic, and Semantic Features with Maximum Entropy Models for Extracting Relations Nanda Kambhatla IBM T. J. Watson Research Center 1101 Kitchawan Road Route 134 Yorktown Heights, NY 10598 nanda@us.ibm.com Abstract Extracting ... 2000) augmented syn- tactic parse trees with semantic information corre- sponding to entities and relations and built genera- tive models for the au...

Ngày tải lên: 31/03/2014, 03:20

... disambiguation (Dorr and Jones, 1996; Kohomban and Lee, 2005), machine translation (Prescher et al., 2000; Koehn and Hoang, 2007), document classification (Klavans and Kan, 1998), and in statistical ... Figure 2. Both for 10 and 20 frames, the results are better for 50 than for 20 clusters, with small differences between 10 and 20 frames. The results vary between -11.85...

Ngày tải lên: 08/03/2014, 01:20

... relation between T1 and H (Example 1), and a contradiction between T2 and H (Example 2). As introduced before, our paper proposes an approach to support the participants in forums or debates to ... considered, and obtains an ac- curacy of 0.61 on the training set and 0.62 on the test set). Even using a basic configuration of EDITS, and a small data set (100 pairs for training) pe...

Ngày tải lên: 16/03/2014, 20:20

... GST-JAK1DN for pJAK1, JAK1, pTYK2 and TYK2, calnexin for pSTAT1, STAT1, pSTAT2, STAT2 and IRF9, in the cytoplasm and poly [ADP-ribose] polymerase 1 for pSTAT1, STAT1, pSTAT2, STAT2 and IRF9 in ... Hauser and Didier Trono (E ´ cole polytechnique fe ´ de ´ rale de Lausanne EPFL, Lab of virology and genetics, Switzerland) for the supplied reagents. We thank Sandra Manthey an...

Ngày tải lên: 23/03/2014, 03:20

... words (such as peace and piece, or quiet and quite) and also the problem of correcting particular word usage errors (such as amount and num- ber, or among and between). Such ... once and for all, and quite manageably, for all con- fusion sets; new confusion sets can be added later without any additional training. This feature makes Trigrams a very easily ex...

Ngày tải lên: 23/03/2014, 20:21

... Statistical Translation Models for Retrieval Statistical translation models for retrieval have first been introduced by Berger and Lafferty (1999). These models attempt to address syn- onymy and polysemy ... stemming and lemmati- sation, since the answers do not contain the ques- tion terms “mosquito” (for question 2) and “form” (for question 3), but only their inflecte...

Ngày tải lên: 20/02/2014, 07:20

... questions into given and new information. ~tore s~ectfically, an input question is divided into three parts, of which (2) and (3) form the new information. (1) given information (2) Function ... design and implementation of a paraphrase component for a natural language questlon-answer system (CO-OP) is presented. A major point made is the role of given and new informatio...

Ngày tải lên: 21/02/2014, 20:20