Báo cáo khoa học: " Translating Named Entities Using Monolingual and Bilingual Resources" ppt

... for translating named entity phrases using easily obtain- able monolingual and bilingual resources. We report on the application and evalua- tion of this algorithm in translatingArabic named entities ... Translating Named Entities Using Monolingual and Bilingual Resources Yaser Al-Onaizan and Kevin Knight Information Sciences Institute University ... phrases,...

Ngày tải lên: 08/03/2014, 07:20

... things: entities and events. From their definitions in WordNet, an entity is anything having existence (living or nonliving) and an event is something that happens at a given place and time. ... uses the knowledge of both the Web and WordNet to expand the original query. This is done by first using the original query to search the web for top N,„ documents and extract- ing a...

Ngày tải lên: 22/02/2014, 02:20

... understanding, and customizing complex rule-based named- entity annotators for different domains. Ratinov and Roth (2009) systematically study the challenges in NER, compare several solutions and ... drop non-English tweets and get about 11,371,389, from which 15,800 tweets are randomly sampled, and are then labeled by two independent annotators, so that the beginning and the end...

Ngày tải lên: 17/03/2014, 00:20

... the sum, or centroid of a and b (Landauer and Dumais, 1997). Kintsch (2001) considers a variant of this simple model. By using vector representations of a predi- cate p and an argument a , Kintsch ... identifying paraphrase candidates and ranking them according to the context. We follow E&P and evaluate it only on the second subtask: we extract paraphrase candidates from the g...

Ngày tải lên: 07/03/2014, 22:20

... substrings and 875 mil- lions unique French (word-) substrings. And things get much worse if we want to try to work with characters substrings. To handle this problem, we decided not to try and ... cases and will be neglected). We can now compute pf and pl for a substring S such as previously, and retrieve the sentence indexes corresponding to every suffix between positions...

Ngày tải lên: 17/03/2014, 04:20

... determining boundaries of named entities, we called this process Named Entity Delimitation (NED). Once we have determined which words belong to named entities, we then get to the task of classifying the named en- tities ... different kinds of named entities: core NEs, which contain a trig- ger word as nucleus, syntactically simple weak NEs, formed by single noun phrases, and s...

Ngày tải lên: 17/03/2014, 06:20

... L-BFGS algorithm (Nocedal and Wright, 1999). And finally, we show that the parsing algo- rithm described in Clark and Curran (2003) is ex- tremely slow in some cases, and suggest an efficient alternative ... for estimation, and resulting in an extremely efficient parser. This paper assumes a basic understanding of CCG; see Steedman (2000) for an introduction, and Clark et al. (2002)...

Ngày tải lên: 23/03/2014, 19:20

... several super- vised and unsupervised evaluation metrics and (iii) of various existing syntactic and semantic lexical resources. We evaluate our approach on an established test set and show that it outperforms ... (Sun et al., 2010) and to a lesser extent for German (Brew and Schulte im Walde, 2002; Schulte im Walde, 2003; Schulte im Walde, 2006), Japanese (Oishi and Matsumoto,...

Ngày tải lên: 30/03/2014, 17:20

... estimated using Equation (4) and the translation probabilities estimated using EM algorithm, we can compute the best triple translation for a given Chinese triple using Equations (1) and (7). ... achieves good results in word translation selection. In addition, (Dagan and Itai, 1994) and (Li, 2002) propose using two monolingual corpora for word sense disambiguation. (...

Ngày tải lên: 31/03/2014, 03:20

... language generation and machine translation (Dorr, 1997), and document classifica- tion (Klavans and Kan, 1998). Manual classifica- tion of large numbers of verbs is a difficult and resource intensive ... means that the system randomly divides the data into ten parts, and runs ten times on a different 90%-training-data/t0%-test-data split, yielding an average accuracy and s...

Ngày tải lên: 31/03/2014, 21:20