| tech,17-1-H92-1095,bq | spoken language understanding </term> , <term> | text | understanding </term> , and <term> document | #19654 Language understanding work at Paramax focuses on applying general-purpose language understanding technology to spoken language understanding,text understanding, and document processing, integrating language understanding with speech recognition, knowledge-based information retrieval and image understanding. |
| tech,3-1-C04-1116,bq | smaller and more robust . We present a <term> | text | mining method </term> for finding <term> synonymous | #6095 We present atext mining method for finding synonymous expressions based on the distributional hypothesis in a set of coherent corpora. |
| tech,26-3-P04-2005,bq | Sense Disambiguation ( WSD ) </term> and <term> | Text | Summarisation </term> . Our method takes | #6955 Topic signatures can be useful in a number of Natural Language Processing (NLP) applications, such as Word Sense Disambiguation (WSD) andText Summarisation. |
| other,2-1-C94-1026,bq | homophone errors </term> . To align <term> bilingual | texts | </term> becomes a crucial issue recently | #20535 To align bilingual texts becomes a crucial issue recently. |
| tech,6-1-P84-1078,bq | describes <term> Paul </term> , a <term> computer | text | generation system </term> designed to create | #13751 This report describes Paul, a computer text generation system designed to create cohesive text through the use of lexical substitutions. |
| other,24-1-N03-4010,bq | answering capability </term> on <term> free | text | </term> . The demonstration will focus on | #3660 The JAVELIN system integrates a flexible, planning-based architecture with a variety of language processing modules to provide an open-domain question answering capability on free text. |
| tech,15-2-N06-4001,bq | researchers who are not experts in <term> | text | mining </term> . As evidence of its usefulness | #10891 InfoMagnets aims at making exploratory corpus analysis accessible to researchers who are not experts intext mining. |
| other,10-2-A88-1001,bq | heuristically-produced complete <term> sentences </term> in <term> | text | </term> or <term> text-to-speech form </term> | #14892 Multimedia answers include videodisc images and heuristically-produced complete sentences intext or text-to-speech form. |
| other,13-1-P82-1035,bq | under the assumption that the input <term> | text | </term> will be in reasonably neat form , | #12957 Most large text-understanding systems have been designed under the assumption that the inputtext will be in reasonably neat form, e.g., newspaper stories and other edited texts. |
| other,0-1-A94-1026,bq | language translation </term> . <term> Japanese | texts | </term> frequently suffer from the <term> homophone | #20367 Japanese texts frequently suffer from the homophone errors caused by the KANA-KANJI conversion needed to input the text. |
| lr-prod,15-3-H94-1014,bq | <term> word </term><term> Wall Street Journal | text | corpus </term> . Using the <term> BU recognition | #21260 The models were constructed using a 5K vocabulary and trained using a 76 million word Wall Street Journal text corpus. |
| other,12-3-C92-4207,bq | </term> , which takes <term> natural language | texts | </term> and produces a <term> model </term> of | #18444 It is done by an experimental computer program SPRINT, which takes natural language texts and produces a model of the described world. |
| other,35-1-I05-4010,bq | numbering system </term> in the <term> legal | text | hierarchy </term> . Basic methodology and | #8239 In this paper we present our recent work on harvesting English-Chinese bitexts of the laws of Hong Kong from the Web and aligning them to the subparagraph level via utilizing the numbering system in the legal text hierarchy. |
| tech,8-1-C90-3072,bq | have become an integral part of most <term> | text | processing software </term> . From different | #16730 Spelling-checkers have become an integral part of mosttext processing software. |
| other,11-7-H01-1042,bq | six extracts of <term> translated newswire | text | </term> . Some of the extracts were <term> | #695 Subjects were given a set of up to six extracts of translated newswire text. |
| other,6-2-C88-1044,bq | </term> . We examine a broad range of <term> | texts | </term> to show how the distribution of <term> | #15199 We examine a broad range oftexts to show how the distribution of demonstrative forms and functions is genre dependent. |
| papers in English , many systems to run off | texts | have been developed . In this paper , we | #12231 In order to meet the needs of a publication of papers in English, many systems to run off texts have been developed. | |
| lr,1-3-P03-1050,bq | training resources </term> . No <term> parallel | text | </term> is needed after the <term> training | #4478 No parallel text is needed after the training phase. |
| other,12-4-P06-1013,bq | are derived automatically from <term> raw | text | </term> . Experiments using the <term> SemCor | #11022 Our combination methods rely on predominant senses which are derived automatically from raw text. |
| other,20-2-P01-1008,bq | translations </term> of the same <term> source | text | </term> . Our approach yields <term> phrasal | #1798 We present an unsupervised learning algorithm for identification of paraphrases from a corpus of multiple English translations of the same source text. |
