| performance </term> further . We suggest a | method | that mimics the behavior of the <term> oracle | #1155 We suggest a method that mimics the behavior of the oracle using a neural network or a decision tree. | |
| </term> or a <term> decision tree </term> . The | method | amounts to tagging <term> LMs </term> with <term> | #1173 The method amounts to tagging LMs with confidence measures and picking the best hypothesis corresponding to the LM with the best confidence. | |
| tech,8-6-P01-1007,bq | </term><term> evaluation </term> of this <term> | method | </term> on a <term> wide coverage English grammar | #1743 The results of a practical evaluation of thismethod on a wide coverage English grammar are given. |
| target variables . This paper describes a | method | for <term> utterance classification </term> | #2209 This paper describes a method for utterance classification that does not require manual transcription of training data. | |
| </term> of <term> training data </term> . The | method | combines <term> domain independent acoustic | #2224 The method combines domain independent acoustic models with off-the-shelf classifiers to give utterance classification performance that is surprisingly close to what can be achieved using conventional word-trigram recognition requiring manual transcription. | |
| <term> manual transcription </term> . In our | method | , <term> unsupervised training </term> is first | #2257 In our method, unsupervised training is first used to train a phone n-gram model for a particular domain; the output of recognition with this model is then passed to a phone-string classifier. | |
| tech,5-4-N03-1001,bq | classification accuracy </term> of the <term> | method | </term> is evaluated on three different <term> | #2295 The classification accuracy of themethod is evaluated on three different spoken language system domains. |
| <term> HDAGs </term> . We applied the proposed | method | to <term> question classification </term> and | #3843 We applied the proposed method to question classification and sentence alignment tasks to evaluate its performance as a similarity measure and a kernel function. | |
| </term> can be improved . This paper proposes a | method | for resolving this <term> ambiguity </term> | #4220 This paper proposes a method for resolving this ambiguity based on statistical information obtained from dialogue corpora. | |
| tech,10-6-P03-1031,bq | hand-crafted rules </term> , the proposed <term> | method | </term> enables easy design of the <term> discourse | #4244 Unlike conventional methods that use hand-crafted rules, the proposedmethod enables easy design of the discourse understanding process. |
| tech,11-7-P03-1031,bq | system </term> that exploits the proposed <term> | method | </term> performs sufficiently and that holding | #4265 Experiment results have shown that a system that exploits the proposedmethod performs sufficiently and that holding multiple candidates for understanding results is effective. |
| occurrences of a <term> morpheme </term> ) . Our | method | is seeded by a small <term> manually segmented | #4639 Our method is seeded by a small manually segmented Arabic corpus and uses it to bootstrap an unsupervised algorithm to build the Arabic word segmenter from a large unsegmented Arabic corpus. | |
| tech,5-3-P03-1058,bq | Our investigation reveals that this <term> | method | of acquiring sense-tagged data </term> is | #4861 Our investigation reveals that thismethod of acquiring sense-tagged data is promising. |
| the <term> algorithms </term> , we present a | method | of <term> HMM training </term> that improves | #5580 Observing that the quality of the lexicon greatly impacts the accuracy that can be achieved by the algorithms, we present a method of HMM training that improves accuracy when training of lexical probabilities is unstable. | |
| this limitation , this paper proposes a | method | utilizing the perceptual groups of <term> | #5658 To overcome this limitation, this paper proposes a method utilizing the perceptual groups of objects and n-ary relations among them. | |
| another 23 subjects showed that the proposed | method | could effectively generate proper <term> | #5721 The evaluation using another 23 subjects showed that the proposed method could effectively generate proper referring expressions. | |
| </term> . Our study reveals that the proposed | method | not only reduces an extensive system development | #5825 Our study reveals that the proposed method not only reduces an extensive system development effort but also improves the transliteration accuracy significantly. | |
| approach </term> . The advantage of this novel | method | is that it clusters all <term> inflected | #6029 The advantage of this novel method is that it clusters all inflected forms of an ambiguous word in one classifier, therefore augmenting the training material available to the algorithm. | |
| tech,3-1-C04-1116,bq | more robust . We present a <term> text mining | method | </term> for finding <term> synonymous expressions | #6097 We present a text mining method for finding synonymous expressions based on the distributional hypothesis in a set of coherent corpora. |
| synonymous expressions </term> . Our proposed | method | improves the <term> accuracy </term> of our | #6185 Our proposed method improves the accuracy of our term aggregation system, showing that our approach is successful. |
