Báo cáo khoa học: "Statistical Machine Translation for Query Expansion in Answer Retrieval" pptx

... experiments. Expansion terms are taken from those terms in the n-best translations of the query that have not been seen in the original query string. For paraphrasing-based query expansion, a ... decisions in the case of ambiguous transla- tions. Query expansion is performed by adding con- tent words that have not been seen in the original query from the n-best transl...

Ngày tải lên: 08/03/2014, 02:21

... a parsing logic can be combined with various semirings to compute dif- ferent kinds of information about the input. De- pending on the chosen semiring, a parsing logic can compute the single ... segments, as in . The (“join”) operator rearranges the non- terminals in each component according to their role template. The nonterminals on the RHS are writ- ten in columns called links. Links...

Ngày tải lên: 20/02/2014, 16:20

... models as well as provide a framework for incorporating rich morpho-syntactic information. Statistical machine translation can be formulated as a search for the best target sequence that maxi- mizes ... can use a conditional model (instead of a joint model as before) and the parameters are determined using discriminant train- ing which allows for richer conditioning context. P (T|S)...

Ngày tải lên: 17/03/2014, 04:20

... come by. Two factors could increase the performance of statistical machine translation for new language pairs and domains: a reduction in the cost of cre- ating new training data, and the development ... additionally including word- aligned data during training. Incorporating word- level alignments into the parameter estimation of the IBM models reduces alignment error rate and increa...

Ngày tải lên: 31/03/2014, 03:20

... present the training corpus be- fore describing the approach in more detail. Training corpus To train the translation model, we translated a subset of the Europarl corpus using Its-2. The translations ... correspond- ing reference translations, resulting in a paral- lel corpus for each language pair, composed of 976 sentences for IT→FR and 1,005 sentences for ES→FR. We opted for...

Ngày tải lên: 24/03/2014, 03:20

... improvement through query expansion using information only from man- ually created lexical resources. In this paper, we re-examine the problem of query expansion using lexical resources in recently pro- posed ... Holo., Lin and Combined. Furthermore, we examine the query expansion method using co-occurrence-based resources. In particular, we evaluate the retrieval performanc...

Ngày tải lên: 17/03/2014, 02:20

... Issues in Machine Translation, July 5-7, Leuven, Belgium, pages 5–7. Ruslan Mitkov. 1999. Introduction: Special Issue on Anaphora Resolution in Machine Translation and Multilingual NLP. Machine Translation, ... 2012. c 2012 Association for Computational Linguistics Improving Pronoun Translation for Statistical Machine Translation Liane Guillou School of Informatics Un...

Ngày tải lên: 17/03/2014, 22:20

... train- ing corpus. The actual translation of the pa- per is performed using adapted translation as described in Section 4. • The translation process generates a bilingual TEI format preserving ... physics). In- cluding the theses abstracts in the parallel training corpus, a further gain of 2.3 BLEU points is ob- served for computer science, and 3.1 points for physics. The last...

Ngày tải lên: 22/02/2014, 03:20

... JAPAN {kevin.duh,fujino.akinori,nagata.masaaki}@lab.ntt.co.jp Abstract Recent advances in Machine Translation (MT) have brought forth a new paradigm for build- ing NLP applications in low-resource ... 2011. c 2011 Association for Computational Linguistics Is Machine Translation Ripe for Cross-lingual Sentiment Classification? Kevin Duh and Akinori Fujino and Masaaki Nagata N...

Ngày tải lên: 17/03/2014, 00:20

... University pado@ims.uni-stuttgart.de Michel Galley, Dan Jurafsky, Chris Manning Stanford University {mgalley,jurafsky,manning}@stanford.edu Abstract Existing evaluation metrics for machine translation lack crucial robustness: their ... confirma- tion for the usefulness of entailment features in MT evaluation, and for their robustness. 5 In addition, the combined model MT+RTER is...

Ngày tải lên: 20/02/2014, 07:20