| </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. | |
| various <term> rhetorical functions </term> . The | method | involves automatically gathering a large | #11738 The method involves automatically gathering a large number of abstracts from the Web and building a language model of abstract moves. | |
| 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. | |
| homophone errors </term> . This paper proposes a | method | for detecting and correcting <term> Japanese | #20408 This paper proposes a method for detecting and correcting Japanese homophone errors in compound nouns. | |
| pronouns </term> . <term> Boosting </term> , the | method | in question , combines the moderately accurate | #7037 Boosting, the method in question, combines the moderately accurate hypotheses of several classifiers to form a highly accurate one. | |
| tech,1-7-J05-1003,bq | Street Journal treebank </term> . The <term> | method | </term> combined the <term> log-likelihood </term> | #8800 Themethod combined the log-likelihood under a baseline model (that of Collins [1999]) with evidence from an additional 500,000 features over parse trees that were not included in the original model. |
| 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. | |
| boosting approach </term> . We argue that the | method | is an appealing alternative — in terms | #8909 We argue that the method is an appealing alternative—in terms of both simplicity and efficiency—to work on feature selection methods within log-linear (maximum-entropy) models. | |
| tech,1-2-H05-1095,bq | i.e. <term> phrases </term> with gaps . A <term> | method | </term> for producing such <term> phrases </term> | #7358 Amethod for producing such phrases from a word-aligned corpora is proposed. |
| particular scenario . This paper introduces a | method | for <term> computational analysis of move | #11700 This paper introduces a method for computational analysis of move structures in abstracts of research articles. | |
| the whole <term> sentence </term> again . This | method | is also capable of handling <term> unknown | #18226 This method is also capable of handling unknown words, which is important in practical systems. | |
| tech,1-2-P05-1034,bq | <term> phrasal translation </term> . This <term> | method | </term> requires a <term> source-language </term> | #9226 Thismethod requires a source-language dependency parser, target language word segmentation and an unsupervised word alignment component. |
| 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. | |
| 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. |
| tech,4-1-C94-1077,bq | </term> . A new , flexible <term> inference | method | </term> for <term> Horn logic program </term> | #20883 A new, flexible inference method for Horn logic program is proposed. |
| bilingual or multMingual texts </term> . A | method | for <term> error correction </term> of <term> | #13989 A method for error correction of ill-formed input is described that acquires dialogue patterns in typical usage and uses these patterns to predict new inputs. | |
| pragmatics processing </term> , we describe how the | method | of <term> abductive inference </term> is inherently | #17496 For pragmatics processing, we describe how the method of abductive inference is inherently robust, in that an interpretation is always possible, so that in the absence of the required world knowledge, performance degrades gracefully. | |
| 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. |
| tech,6-3-I05-5008,bq | paraphrase </term> sets produced by this <term> | method | </term> thus seem adequate as <term> reference | #8551 The paraphrase sets produced by thismethod thus seem adequate as reference sets to be used for MT evaluation. |
| tech,8-1-P05-1069,bq | paper , we present a novel <term> training | method | </term> for a <term> localized phrase-based | #9558 In this paper, we present a novel training method for a localized phrase-based prediction model for statistical machine translation (SMT). |
