Báo cáo khoa học: "Character-Based Pivot Translation for Under-Resourced Languages and Domains" ppt

... techniques for question reformulation, including rule-based syntactic and semantic refor- mulation patterns (Hermjakob et al., 2002), refor- mulations based on shared dependency parses (Lin and Pantel, ... lexical correla- tions between words and phrases in questions and answers, for example by allowing for multiple un- aligned words in automatic word alignment, and dis- regar...

Ngày tải lên: 08/03/2014, 02:21

... has seven cases and four grammatical gen- ders: masculine animate (for people and animals), masculine inanimate (for inanimate objects), fem- inine and neuter. (With feminine and neuter gen- ders, ... pronoun translation for both sys- tems. These results for the “Development” and “Final” test sets (see Table 3) suggest that the per- formance of the Annotated system is compar...

Ngày tải lên: 17/03/2014, 22:20

... granularity. For each set of annotations, we therefore performed two sets of segmentations: one in which the threshold was set for each meeting to give the known gold- standard number of segments, and ... where S 1 u is S u for the segmen- tation when c u = 1, S 0 u is S u for the segmentation when c u = 0, and all counts (e.g. n 1 ) exclude c u . For this paper, we fixed α, β a...

Ngày tải lên: 20/02/2014, 11:21

... grammatical and pro- cessing framework for handling the repairs, hesitations, and other interruptions in nat- ural human dialog. The proposed frame- work has proved adequate for a collection ... (urn) and speech re- pairs (I mean) and give meta-comments on the ut- terance (right). specify how speech repairs should be handled by the parser. (Hindle, 1983) and (Bear et al...

Ngày tải lên: 20/02/2014, 19:20

... our forced alignment procedure that is the basic training pro- cedure for the models proposed here. 3.1 Forced Alignment The idea of forced alignment is to perform a phrase segmentation and alignment ... Association for Machine Translation (EAMT), Barcelona, Spain, May. European Association for Machine Translation. Reinhard Kneser and Hermann Ney. 1995. Improved Backing-Off for...

Ngày tải lên: 07/03/2014, 22:20

... the final translation re- sult. In this example, a measure word candidate set consisting of “本” and “只” can be generated by bilingual phrases (or synchronous translation rules), and the best ... Chinese translation, in which positions for measure word generation are identified. Based on contextual information con- tained in both input source sentence and SMT sys- tem’s outp...

Ngày tải lên: 08/03/2014, 01:20

... that we use for expert identification. In the step 2) and 3), the rules use frequency and context discourse for re- solving ambiguities respectively. With frequency, each expert candidate actually ... <Title> and the expert candidate appears in the <Author>. 918 Section Title-Body Relation (R STB ): The que- ried topic and the expert candidate appear in the <Se...

Ngày tải lên: 08/03/2014, 01:20

... is 67.09% for break index, 54.10% for pitch accent, 66.23% for phrase accent and 79.37% for boundary tone based on the speech corpus from one speaker. The relatively high baseline for boundary ... linguistic features and intonation, more knowledge is needed. The NLG compo- nent provides very rich syntactic and semantic information which has not been explored before for...

Ngày tải lên: 08/03/2014, 05:21

... rule important information is ob- tained about the left-hand-side and the other elements of the right-hand-side. We have used two different head-driven parsers and a number of standard parsers ... for a singular NP, and need not consider other categories. The head-relation holds between two categories h and m with respect to a grammar G iff G contains a rule with left hand sid...

Ngày tải lên: 09/03/2014, 01:20

... and two candidate translations (boldface and underline indicate non- matched items in candidate 1 and 2, respectively). Similarly, metrics in another category measure the edit distance of a translation, ... creating 141 Figure 2: PoS, chunk and named entity annota- tions on the source, reference and two translation hypotheses Figure 3: Constituency trees for the reference and...

Ngày tải lên: 16/03/2014, 20:20