| detect those automatically which is shown | on | a large database of TV shows . Emotions | #155 Several extensions of this basic idea are being discussed and/or evaluated: Similar to activities one can define subsets of larger database and detect those automatically which is shown on a large database of TV shows. | ||
| distribution of speakers might be available | on | the surface and could be used directly | #177 Emotions and other indices such as the dominance distribution of speakers might be available on the surface and could be used directly. | ||
| indicates further work needs to be done | on | the interface to make <term> users </term> | #370 We also report results of a preliminary, qualitative user evaluation of the system, which while broadly positive indicates further work needs to be done on the interface to make users aware of the increased potential of IE-enhanced text browsers. | ||
| of grammars </term> . Having been trained | on | <term> Korean newspaper articles </term> on | #518 Having been trained on Korean newspaper articles on missiles and chemical biological warfare, the system produces the translation output sufficient for content understanding of the original document. | ||
| on <term> Korean newspaper articles </term> | on | missiles and chemical biological warfare | #522 Having been trained on Korean newspaper articleson missiles and chemical biological warfare, the system produces the translation output sufficient for content understanding of the original document. | ||
| . Even more illuminating was the factors | on | which the <term> assessors </term> made their | #654 Even more illuminating was the factors on which the assessors made their decisions. | ||
| automatically training <term> SPoT </term> | on | the basis of <term> feedback </term> provided | #1355 In this paper, we present SPoT, a sentence planner, and a new methodology for automatically training SPoTon the basis of feedback provided by human judges. | ||
| sentence plan </term> whose <term> rating </term> | on | average is only 5 % worse than the <term> | #1447 We show that the trained SPR learns to select a sentence plan whose ratingon average is only 5% worse than the top human-ranked sentence plan. | ||
| </term> and <term> segment contiguity </term> | on | the <term> retrieval performance </term> of | #1478 In this paper, we compare the relative effects of segment order, segmentation and segment contiguityon the retrieval performance of a translation memory system. | ||
| of a practical evaluation of this method | on | a <term> wide coverage English grammar </term> | #1745 The results of a practical evaluation of this method on a wide coverage English grammar are given. | ||
| language search engines </term> perform poorly | on | <term> queries </term> containing them . I | #1867 These words appear frequently enough in dialog to warrant serious attention, yet present natural language search engines perform poorly on queries containing them. | ||
| </term> from <term> structured data </term> ( based | on | a <term> typing-algorithm </term> and <term> | #1985 Our logical definition leads to a neat relation to categorial grammar, (yielding a treatment of Montague semantics), a parsing-as-deduction in a resource sensitive logic, and a learning algorithm from structured data (based on a typing-algorithm and type-unification). | ||
| machine learning experiments </term> centering | on | the construction of <term> statistical models | #2135 We describe a set of supervised machine learning experiments centering on the construction of statistical models of WH-questions. | ||
| 's informational goals </term> . We report | on | different aspects of the <term> predictive | #2173 We report on different aspects of the predictive performance of our models, including the influence of various training and testing factors on predictive performance, and examine the relationships among the target variables. | ||
| of various training and testing factors | on | <term> predictive performance </term> , and | #2193 We report on different aspects of the predictive performance of our models, including the influence of various training and testing factors on predictive performance, and examine the relationships among the target variables. | ||
| accuracy </term> of the method is evaluated | on | three different <term> spoken language system | #2299 The classification accuracy of the method is evaluated on three different spoken language system domains. | ||
| <term> question answering </term> which is based | on | combining the results from different <term> | #2338 Motivated by the success of ensemble methods in machine learning and other areas of natural language processing, we developed a multi-strategy and multi-source approach to question answering which is based on combining the results from different answering agents searching for answers in multiple corpora. | ||
| for scoring sets of <term> concepts </term> | on | the basis of an <term> ontology </term> . We | #2450 In this paper we present ONTOSCORE, a system for scoring sets of conceptson the basis of an ontology. | ||
| models </term> does not have a strong impact | on | performance . Learning only <term> syntactically | #2653 Surprisingly, learning phrases longer than three words and learning phrases from high-accuracy word-level alignment models does not have a strong impact on performance. | ||
| <term> error correction </term> , with a focus | on | <term> post-processing </term> the <term> output | #2726 The model is designed for use in error correction, with a focus on post-processing the output of black-box OCR systems in order to make it more useful for NLP tasks. |
