| </term> is a set of inter-related but distinct | tasks | , one of which is <term> sentence scoping | #1302 Sentence planning is a set of inter-related but distinct tasks, one of which is sentence scoping, i.e. the choice of syntactic structure for elementary speech acts and the decision of how to combine them into one or more sentences. | ||
| human judges </term> . We reconceptualize the | task | into two distinct phases . First , a very | #1368 We reconceptualize the task into two distinct phases. | ||
| </term> . We apply our <term> system </term> to the | task | of scoring alternative <term> speech recognition | #2463 We apply our system to the task of scoring alternative speech recognition hypotheses (SRH) in terms of their semantic coherence. | ||
| tech,29-2-N03-1018,ak | order to make it more useful for <term> NLP | tasks | </term> . We present an implementation of | #2743 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. | |
| tech,26-2-N03-2003,ak | topic </term> of the <term> target recognition | task | </term> , but also that it is possible to | #3057 In this paper, we show how training data can be supplemented with text from the web filtered to match the style and/or topic of the target recognition task, but also that it is possible to get bigger performance gains from the data by using class-dependent interpolation of N-grams. | |
| time finding more data relevant to their | task | , and gives them translingual reach into | #3620 It gives users the ability to spend their time finding more data relevant to their task, and gives them translingual reach into other languages by leveraging human language technology. | ||
| tech,9-3-P03-1005,ak | classification </term> and <term> sentence alignment | tasks | </term> to evaluate its performance as a <term> | #3851 We applied the proposed method to question classification and sentence alignment tasks to evaluate its performance as a similarity measure and a kernel function. | |
| tech,11-1-P03-1030,ak | for the <term> Topic Detection and Tracking | tasks | </term> of <term> new event detection </term> | #4058 Link detection has been regarded as a core technology for the Topic Detection and Tracking tasks of new event detection. | |
| tech,13-2-P03-1030,ak | detection </term> as <term> information retrieval | task | </term> and hypothesize on the impact of <term> | #4079 In this paper we formulate story link detection and new event detection as information retrieval task and hypothesize on the impact of precision and recall on both systems. | |
| other,29-2-P03-1058,ak | the <term> SENSEVAL-2 English lexical sample | task | </term> . Our investigation reveals that | #4856 In this paper, we evaluate an approach to automatically acquire sense-tagged training data from English-Chinese parallel corpora, which are then used for disambiguating the nouns in the SENSEVAL-2 English lexical sample task. | |
| </term> in the context of a direction-giving | task | . The distribution of <term> nonverbal behaviors | #5058 We analyzed eye gaze, head nods and attentional focus in the context of a direction-giving task. | ||
| errors </term> are analyzed in detail . Other | tasks | using the method developed for <term> ILIMP | #6196 Other tasks using the method developed for ILIMP are described briefly, as well as the use of ILIMP in a modular syntactic analysis system. | ||
| other,37-1-I05-2021,ak | the <term> Senseval-3 Chinese lexical sample | task | </term> . Much effort has been put in designing | #6370 We present the first known empirical test of an increasingly common speculative claim, by evaluating a representative Chinese-to-English SMT model directly on word sense disambiguation performance, using standard WSD evaluation methodology and datasets from the Senseval-3 Chinese lexical sample task. | |
| </term> in a larger volume from the Web . The | task | of <term> machine translation ( MT ) evaluation | #7367 The task of machine translation (MT) evaluation is closely related to the task of sentence-level semantic equivalence classification. | ||
| evaluation </term> is closely related to the | task | of <term> sentence-level semantic equivalence | #7380 The task of machine translation (MT) evaluation is closely related to the task of sentence-level semantic equivalence classification. | ||
| Annotating <term> honorifics </term> is a complex | task | that involves identifying a <term> predicate | #7986 Annotating honorifics is a complex task that involves identifying a predicate with honorifics, assigning ranks to referents of the predicate, calibrating the ranks, and connecting referents with their predicates. | ||
| other,7-5-J05-1003,ak | introduce a new method for the <term> reranking | task | </term> , based on the <term> boosting approach | #8132 We introduce a new method for the reranking task, based on the boosting approach to ranking problems described in Freund et al. (1998). | |
| other,30-12-J05-1003,ak | which are naturally framed as <term> ranking | tasks | </term> , for example , <term> speech recognition | #8332 Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example, speech recognition, machine translation, or natural language generation. | |
| for certain field structured extraction | tasks | , such as classified advertisements and | #9043 We demonstrate that for certain field structured extraction tasks, such as classified advertisements and bibliographic citations, small amounts of prior knowledge can be used to learn effective models in a primarily unsupervised fashion. | ||
| conditional random field ( CRF ) </term> for this | task | and relate results with this <term> model | #9498 In this paper, we evaluate the use of a conditional random field (CRF) for this task and relate results with this model to our prior work. |
