Báo cáo khoa học: "Improving Decoding Generalization for Tree-to-String Translation" docx

... similar source parse trees for decoding at the decoding time, which aims to increase the tree-to-string search space for decoding, and improve decoding gener- alization for tree-to-string translation. ... Association for Computational Linguistics:shortpapers, pages 418–423, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Improving...

Ngày tải lên: 17/03/2014, 00:20

... available for choosing values for these parameters. For En- glish we use the parameters reported in (Liang, 1983). For Dutch we use the parameters reported in (Tutelaers, 1999). Preliminary informal ... train- ing sets for English and Dutch from the CELEX European lexical resource, and achieve error rates for English of less than 0.1% for correctly allowed hyphens, and less than...

Ngày tải lên: 20/02/2014, 04:20

... assignment γ for a network N is a function from W ∪ S to the set P. Let γ be a polarity assignment for N. We say that γ is consistent if it satisfies the following condition for each w ∈ W: For p ∈ ... logic formulas, we can reduce it to C(s) = ¬s + ∨ ¬s − (1) For each word w with polarity p ∈ {−, +, 0 } in D we need a clause C(w, p) that states that w has polarity p. So, the Boolean...

Ngày tải lên: 07/03/2014, 18:20

... N for i = 1; i ≤ M; i = i +1 do for j = 1; j ≤ N; j = j +1 do for k = 1; k ≤ i; k = k +1 do for m = 1; m ≤ j; m = m +1 do score i,j,k,m = max{score i−1,j,k,m ,score i,j−1,k,m } ; end for end for score i,j,i,j = max n=1,M;p=1,N {score i,j,i,j , ... |ref|; for i = 1; i ≤ M; i = i +1 do for j = 1; j ≤ N; j = j +1 do for k = 1; k ≤ i; k = k +1 do for m = 1; m ≤ j; m = m +1 do...

Ngày tải lên: 08/03/2014, 02:21

... turns input text ~ format into standard format for discourse referents. Coreference [Semantic type matching 1 nalysis for [lbr pronouns J efinite NPS Hobbs naive lagreement for | algorithm ... especially problematic for designers of dialogue systems trying to pre- dict how anaphora resolution techniques devel- oped for written monologue will perform when adapted for s...

Ngày tải lên: 08/03/2014, 21:20

... of several formats. Format S (specifiers) in- volves whole constituents, including symbols and subscripts. Format A is for text, and in- volves only symbols. Both format S and for- mat A ... that calls for reading in format S from a designated channel, the next constituent from the input is brought into the workspace where it replaces the designated numbered constituent. For ex...

Ngày tải lên: 16/03/2014, 19:20

... the av- erage accuracy for each reordering distance d. It shows that even for long distance reordering, the DPR model still performs well, while the MLE baseline usually performs badly (more than ... the PSL algo- rithm. During the decoding, the DPR model finds the corresponding sub-DPR model for a source phrase ¯ f j and generates the reordering probability for each orientation class...

Ngày tải lên: 17/03/2014, 02:20

... be re-enforced across the model. For instance (see Fig. 1), if cymru and gymru are clustered to- gether, the parameter for feature ψ 1 , shown above, may increase. This induces a prior preference for car ... Table 4). For each language pair the MRF learned features that capture intuitively redundant patterns: adjectival endings for French, case mark- ings for Czech, and mutation p...

Ngày tải lên: 17/03/2014, 04:20

... framework, it is straightforward to encode the morphological properties of a word, in addition to its surface inflected form. For example, for a particular inflected word form y t and its con- text, ... 12,670 distinct stems and 89,360 inflected forms. For the generation of word features, we only con- sider one dominant analysis for any surface word for simplicity. In case of ambiguity...

Ngày tải lên: 17/03/2014, 04:20

... of 7th NTCIR Workshop Meeting on Evaluation of Information Access Technolo- gies: Information Retrieval, Question Answer- ing and Cross-lingual Information Access, 389– 400. Gregor Leusch, Nicola ... the Association for Computational Linguistics, pages 108–117, Uppsala, Sweden, 11-16 July 2010. c 2010 Association for Computational Linguistics Automatic Evaluation Method for Machine Tra...

Ngày tải lên: 23/03/2014, 16:20