| other,9-6-E06-1035,bq | transcription errors </term> inevitable in <term> ASR | output | </term> have a negative impact on models | #10618 We also find that the transcription errors inevitable in ASR output have a negative impact on models that combine lexical-cohesion and conversational features, but do not change the general preference of approach for the two tasks. |
| other,9-4-E06-1035,bq | <term> performance </term> of using <term> ASR | output | </term> as opposed to <term> human transcription | #10519 We then explore the impact on performance of using ASR output as opposed to human transcription. |
| the <term> shared derivation forest </term> | output | by a prior <term> RCL parser </term> for a | #1723 The non-deterministic parsing choices of the main parser for a language L are directed by a guide which uses the shared derivation forestoutput by a prior RCL parser for a suitable superset of L. | |
| other,16-3-H01-1042,bq | the <term> intelligibility </term> of <term> MT | output | </term> . A <term> language learning experiment | #626 This, the first experiment in a series of experiments, looks at the intelligibility of MT output. |
| </term> of a <term> parser </term> 's multiple | output | . Some examples of <term> paraphrasing </term> | #15726 This paper presents a new interactive disambiguation scheme based on the paraphrasing of a parser's multiple output. | |
| other,38-1-N03-1018,bq | through its transformation into the <term> noisy | output | </term> of an <term> OCR system </term> . The | #2706 In this paper, we introduce a generative probabilistic optical character recognition (OCR) model that describes an end-to-end process in the noisy channel framework, progressing from generation of true text through its transformation into the noisy output of an OCR system. |
| sentence-plan-ranker ( SPR ) </term> ranks the list of | output | <term> sentence plans </term> , and then selects | #1411 Second, the sentence-plan-ranker (SPR) ranks the list of output sentence plans, and then selects the top-ranked plan. | |
| other,18-1-P06-4014,bq | pipeline </term> that capitalizes on <term> | output | quality </term> . The demonstrator embodies | #11807 The LOGON MT demonstrator assembles independently valuable general-purpose NLP components into a machine translation pipeline that capitalizes onoutput quality. |
| other,12-4-P05-2016,bq | </term> and plan to compare our <term> system 's | output | </term> with a <term> benchmark system </term> | #9825 We also refer to an evaluation method and plan to compare our system's output with a benchmark system. |
| determine whether they believed the sample | output | to be an <term> expert human translation </term> | #727 The subjects were given three minutes per extract to determine whether they believed the sample output to be an expert human translation or a machine translation. | |
| . In this paper we show how two standard | outputs | from <term> information extraction ( IE ) | #282 In this paper we show how two standard outputs from information extraction (IE) systems - named entity annotations and scenario templates - can be used to enhance access to text collections via a standard text browser. | |
| tech,26-2-N03-1026,bq | maximum-entropy model </term> for <term> stochastic | output | selection </term> . Furthermore , we propose | #2835 Our system incorporates a linguistic parser/generator for LFG, a transfer component for parse reduction operating on packed parse forests, and a maximum-entropy model for stochastic output selection. |
| measure(ment),6-3-H05-1117,bq | <term> methods </term> for <term> scoring system | output | </term> is an impediment to progress in the | #7578 The lack of automatic methods for scoring system output is an impediment to progress in the field, which we address with this work. |
| other,15-5-N03-1026,bq | <term> grammaticality </term> of the <term> system | output | </term> due to the use of a <term> constraint-based | #2899 Overall summarization quality of the proposed system is state-of-the-art, with guaranteed grammaticality of the system output due to the use of a constraint-based parser/generator. |
| directly compare commercial <term> systems </term> | outputting | <term> unsegmented texts </term> with , for | #7769 The use of BLEU at the character level eliminates the word segmentation problem: it makes it possible to directly compare commercial systemsoutputting unsegmented texts with, for instance, statistical MT systems which usually segment their outputs. | |
| other,21-3-N03-1001,bq | particular <term> domain </term> ; the <term> | output | </term> of <term> recognition </term> with this | #2276 In our method, unsupervised training is first used to train a phone n-gram model for a particular domain; theoutput of recognition with this model is then passed to a phone-string classifier. |
| </term> are in <term> Arabic </term> , and the | output | <term> summary </term> is in <term> English </term> | #7170 We consider the case of multi-document summarization, where the input documents are in Arabic, and the output summary is in English. | |
| tech,3-7-P05-1067,bq | <term> model </term> . We evaluate the <term> | outputs | </term> of our <term> MT system </term> using | #9512 We evaluate theoutputs of our MT system using the NIST and Bleu automatic MT evaluation software. |
| by gathering <term> statistics </term> on the | output | of other <term> linguistic tools </term> . | #16664 The scheme was implemented by gathering statistics on the output of other linguistic tools. | |
| other,16-2-N03-1018,bq | on <term> post-processing </term> the <term> | output | </term> of black-box <term> OCR systems </term> | #2728 The model is designed for use in error correction, with a focus on post-processing theoutput of black-box OCR systems in order to make it more useful for NLP tasks. |
