Báo cáo khoa học: "Action representation for NL instructions" doc

Báo cáo khoa học: "Action representation for NL instructions" doc

Báo cáo khoa học: "Action representation for NL instructions" doc

... Action representation for NL instructions Barbara Di Eugenio* Department of Computer and Information Science University of Pennsylvania Philadelphia, ... the paper, I will argue that a hybrid representation formalism is best suited for the knowledge I need to represent. 2 A hybrid action representa- tion formalism As I have argued elsewhere ... in- structions in NL to...

Ngày tải lên: 17/03/2014, 08:20

2 187 0
Tài liệu Báo cáo khoa học: "A Framework for Syntactic Translation" docx

Tài liệu Báo cáo khoa học: "A Framework for Syntactic Translation" docx

... S 1 , which contains all of the information that is in the input sentence. The part of the information that is implicit in the sentence (tense, voice, and so forth) is made explicit in S 1 . ... certain German verb form into English, it is necessary to un- derstand the German verb form as part of a complex of features of German structure in- cluding possibly other verb forms within t...

Ngày tải lên: 19/02/2014, 19:20

7 509 1
Tài liệu Báo cáo khoa học: "Gestural Cohesion for Topic Segmentation" docx

Tài liệu Báo cáo khoa học: "Gestural Cohesion for Topic Segmentation" docx

... unlike formal sign language – rarely fol- lows any predefined form or grammar, and may vary dramatically by speaker. A key implementational challenge is automati- cally extracting gestural information ... gesture only .486 .502 2. ASR only .462 .476 3. ASR + gesture .388 .401 4. transcript only .382 .397 5. transcript + gesture .332 .349 6. random .473 .526 7. equal-width .508 .515 Table 1: F...

Ngày tải lên: 20/02/2014, 09:20

9 511 0
Tài liệu Báo cáo khoa học: "Self-Training for Biomedical Parsing" doc

Tài liệu Báo cáo khoa học: "Self-Training for Biomedical Parsing" doc

... June 2008. c 2008 Association for Computational Linguistics Self-Training for Biomedical Parsing David McClosky and Eugene Charniak Brown Laboratory for Linguistic Information Processing (BLLIP) Brown ... al., 2006a; McClosky et al., 2006b). One possible use for this technique is for parser adaptation — initially training the parser on one type of data for which hand-labeled tree...

Ngày tải lên: 20/02/2014, 09:20

4 374 0
Tài liệu Báo cáo khoa học: "PLANNING TEXT FOR ADVISORY DIALOGUES" docx

Tài liệu Báo cáo khoa học: "PLANNING TEXT FOR ADVISORY DIALOGUES" docx

... • apply-local-1;rans f orma1~ions-thal;-enhance-mainl;ainability apply-1~ransforma¢ ions-1~hal;-enhanc e-mainl; ainabili~y enhanc e-mainl; ainabili1: y enhance-program Figure 6: System goals ... ers. This is necessary for linguis- tic reasons (e.g., to generate the appropriate clausal connectives in multi-sentential responses) and for responding to requests for elabora- tion/...

Ngày tải lên: 21/02/2014, 20:20

9 330 0
Báo cáo khoa học: "A Procedure for Morphological Encoding" doc

Báo cáo khoa học: "A Procedure for Morphological Encoding" doc

... that form of the vocabu- lary element CANTARE which has all and only the morphosyntactic properties non-Past, Future, Indica- tive, third Person, and singular. For such a syntactic representation ... an “arrangement” solution for the strong verbs in English, for example, by enlarging the inven- tory of morphophonemes and associated phonological rules. Again, therefore, one has...

Ngày tải lên: 07/03/2014, 18:20

7 439 0
Báo cáo khoa học: "Ensemble Methods for Unsupervised WSD" doc

Báo cáo khoa học: "Ensemble Methods for Unsupervised WSD" doc

... Association for Computational Linguistics Ensemble Methods for Unsupervised WSD Samuel Brody School of Informatics University of Edinburgh s.brody@sms.ed.ac.uk Roberto Navigli Dipartimento di Informatica Universit ` a ... WSD method can act as an arbiter for adjudicating dis- agreements among component systems. It makes sense for the adjudicator to have reasonable performance on its o...

Ngày tải lên: 08/03/2014, 02:21

8 343 0
Báo cáo khoa học: "Reinforcement Learning for Mapping Instructions to Actions" pdf

Báo cáo khoa học: "Reinforcement Learning for Mapping Instructions to Actions" pdf

... the annotation for the document being analyzed, and zero otherwise. Policy gradient performs stochas- tic gradient ascent on the objective from equa- tion 2, performing one update per document. For document ... 128 documents, divided into 70 for training, 18 for development, and 40 for test. In the puzzle game domain, we use 50 tutorials, divided into 40 for training and 10 for...

Ngày tải lên: 17/03/2014, 01:20

9 350 0
Từ khóa:
w