Báo cáo khoa học: "Reducing the Annotation Effort for Letter-to-Phoneme Conversion" ppt

Báo cáo khoa học: "Reducing the Annotation Effort for Letter-to-Phoneme Conversion" ppt

Báo cáo khoa học: "Reducing the Annotation Effort for Letter-to-Phoneme Conversion" ppt

... Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, pages 127–135, Suntec, Singapore, 2-7 August 2009. c 2009 ACL and AFNLP Reducing the Annotation Effort for Letter-to-Phoneme ... random from the learning set; these constituted the data on which an initial classifier was trained. The rest of the words in the learning set formed the...

Ngày tải lên: 23/03/2014, 16:21

9 314 0
Báo cáo khoa học: "Towards the Unsupervised Acquisition of Discourse Relations" pptx

Báo cáo khoa học: "Towards the Unsupervised Acquisition of Discourse Relations" pptx

... triple consisting of the event type of the utterance, the relation word, and the event type of the preceding utterance. – add the candidate triple to the BKB, if it found in the BKB, increase its ... files; the last portion was left untouched for forthcoming eval- uation experiments. The portion analyzed here com- prises 33.2M sentences, 75.9% of the corpus. The extra...

Ngày tải lên: 16/03/2014, 20:20

5 342 0
Báo cáo khoa học: "Signalling the Interpretation of Indirect Speech Acts" pptx

Báo cáo khoa học: "Signalling the Interpretation of Indirect Speech Acts" pptx

... performing the action of putting the spout over the hole. The novice, therefore, is acting on her own, evaluating the reasonableness of the plan inferred for the expert using private beliefs about the ... pass the salt. The remainder of this paper attempts to illustrate the kinds of predictlons made by the theory,.and the use of anaphora to support one such pre...

Ngày tải lên: 17/03/2014, 19:20

2 408 1
Báo cáo khoa học: "Coding the Russian Alphabet for the Purpose of Mechanical Translation" pptx

Báo cáo khoa học: "Coding the Russian Alphabet for the Purpose of Mechanical Translation" pptx

... not to make use of them at the time, it has seemed worthwhile putting them forward for discussion. 1 The asterisk is used throughout this paper to distinguish the trans- formed spellings assumed ... transformation of the form (6) until we are perfectly certain that the information thus lost is of no further use to us. Another possibility which suggests itself is that of i...

Ngày tải lên: 23/03/2014, 13:20

4 260 0
Báo cáo khoa học: "On the Applicability of Global Index Grammars" ppt

Báo cáo khoa học: "On the Applicability of Global Index Grammars" ppt

... to the interpretation of the derives relation relative to the behavior of the stack of indices. In IGs the stacks of indices are distributed over the non-terminals of the right- hand side of the ... structural description for the language ww R It should be noted that the operations on indices follow the reverse order as in the LIG case. On the other hand, it can be...

Ngày tải lên: 23/03/2014, 19:20

8 348 0
Báo cáo khoa học: "Bridging the Gap between Dictionary and Thesaurus" pptx

Báo cáo khoa học: "Bridging the Gap between Dictionary and Thesaurus" pptx

... matrix B for the WN synsets and the ROGET classes. A simi- larity score B(j, k) is computed for the jth WN synset (taking the synset itself, the hypernyms, and the coordinate terms) and the ... corpora. Among the attempts to enrich lexical information, many have been directed to the analysis of dictio- nary definitions and the transformation of the im- pl...

Ngày tải lên: 31/03/2014, 04:20

3 401 0
Tài liệu Báo cáo khoa học: "Direct Word Sense Matching for Lexical Substitution" ppt

Tài liệu Báo cáo khoa học: "Direct Word Sense Matching for Lexical Substitution" ppt

... improvement in retrieval perfor- mance. While all these works clearly show the potential usefulness of WSD in practical tasks, nonetheless they do not necessarily justify the efforts for refin- ing fine-grained ... we derived gold standard annotations for all the examples in the Senseval- 3 training section for our 25 target words. For the test set we took up to 40 test exampl...

Ngày tải lên: 20/02/2014, 12:20

8 362 0
Tài liệu Báo cáo khoa học: "A structure-sharing parser for lexicalized grammars" pptx

Tài liệu Báo cáo khoa học: "A structure-sharing parser for lexicalized grammars" pptx

... chor the same input symbol. The input to the parser takes the form of a se- quence of minimized automata, one for each of the symbols in the input. Let the input string be w = at ar~ and the ... are valid for the item: initially this is all the valid trees for the automaton, but gets intersected with the annotation of any transition followed; also if two p...

Ngày tải lên: 20/02/2014, 18:20

7 406 0
Tài liệu Báo cáo khoa học: "An Efficient Generation Algorithm for Lexicalist MT" ppt

Tài liệu Báo cáo khoa học: "An Efficient Generation Algorithm for Lexicalist MT" ppt

... which tests them for grammatical well-formedness. If they are well-formed, the system halts indicating success. If not, another permutation is tried and the process repeated. The complexity ... necessary for correctness or even tractability. 4 The Complexity of the Generator The theoretical complexity of the generator is O (n4), where n is the size of the input. We...

Ngày tải lên: 20/02/2014, 22:20

7 411 0
Tài liệu Báo cáo khoa học: "Performance Confidence Estimation for Automatic Summarization" ppt

Tài liệu Báo cáo khoa học: "Performance Confidence Estimation for Automatic Summarization" ppt

... representative examples can be applied for the pairwise formulation of the task as well the larger the difference in system perfor- mance is, the better example the pair represents. Very small score ... im- proves results. The absolute largest improvement of 10% is for the logistic regression classifier. For this classifier, prediction accuracy for the non- normalized d...

Ngày tải lên: 22/02/2014, 02:20

8 342 0
Từ khóa:
w