Concordance

Query task 31 >
Sort Right 31 (1,445.3 per million)

	time finding more data relevant to their	task	, and gives them translingual reach into	#3619 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,7-5-J05-1003,bq	<term> method </term> for the <term> reranking	task	</term> , based on the <term> boosting approach	#8767 We introduce a new method for the reranking task, based on the boosting approach to ranking problems described in Freund et al. (1998).
tech,27-2-N03-2003,bq	topic </term> of the target <term> recognition	task	</term> , but also that it is possible to	#3056 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.
tech,10-1-N06-2038,bq	extraction </term> as a <term> token classification	task	</term> , using various <term> tagging strategies	#10811 There are several approaches that model information extraction as a token classification task, using various tagging strategies to combine multiple tokens.
	topic signatures </term> on a <term> WSD </term>	task	, where we trained a <term> second-order	#7002 We evaluated the topic signatures on a WSDtask, where we trained a second-order vector co-occurrence algorithm on standard WSD datasets, with promising results.
other,9-5-P05-1067,bq	model </term> for the <term> machine translation	task	</term> , which can also be viewed as a <term>	#9485 Second, we describe the graphical model for the machine translation task, which can also be viewed as a stochastic tree-to-tree transducer.
tech,14-4-P80-1004,bq	reconstruction </term> to a <term> recognition	task	</term> . Implications towards automating	#12513 It is argued that the method reduces metaphor interpretation from a reconstruction to a recognition task.
other,37-1-I05-2021,bq	the <term> Senseval-3 Chinese lexical sample	task	</term> . Much effort has been put in designing	#7827 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.
other,29-2-P03-1058,bq	the <term> SENSEVAL-2 English lexical sample	task	</term> . Our investigation reveals that	#4854 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.
other,10-4-N04-1022,bq	on a <term> Chinese-to-English translation	task	</term> . Our results show that <term> MBR	#6624 We report the performance of the MBR decoders on a Chinese-to-English translation task.
tech,14-5-P05-1069,bq	standard <term> Arabic-English translation	task	</term> . Previous work has used <term> monolingual	#9652 The best system obtains a 18.6% improvement over the baseline on a standard Arabic-English translation task.
other,15-2-P03-1070,bq	in the context of a <term> direction-giving	task	</term> . The distribution of <term> nonverbal	#5056 We analyzed eye gaze, head nods and attentional focus in the context of a direction-giving task.
	the <term> text </term> is irrelevant to the	task	. The <term> parser </term> gains algorithmic	#17585 We present an efficient algorithm for chart-based phrase structure parsing of natural language that is tailored to the problem of extracting specific information from unrestricted texts where many of the words are unknown and much of the text is irrelevant to the task.
	indicators for the top-level prediction	task	. We also find that the <term> transcription	#10606 Examination of the effect of features shows that predicting top-level and predicting subtopic boundaries are two distinct tasks: (1) for predicting subtopic boundaries, the lexical cohesion-based approach alone can achieve competitive results, (2) for predicting top-level boundaries, the machine learning approach that combines lexical-cohesion and conversational features performs best, and (3) conversational cues, such as cue phrases and overlapping speech, are better indicators for the top-level prediction task.
	for such a <term> need </term> is a valuable	task	. We investigate that claim by adopting	#10760 Finding the preferred language for such a need is a valuable task.
tech,13-2-P03-1030,bq	detection </term> as <term> information retrieval	task	</term> and hypothesize on the impact of <term>	#4078 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.
	forming an <term> utterance </term> about a	task	and in determining the conversational vehicle	#14558 We want to illustrate a framework less restrictive than earlier ones by allowing a speaker leeway in forming an utterance about a task and in determining the conversational vehicle to deliver it.
	<term> paraphrases </term> . We show that this	task	can be done using <term> bilingual parallel	#9671 We show that this task can be done using bilingual parallel corpora, a much more commonly available resource.
other,21-1-C88-2130,bq	or house , a much-studied <term> discourse	task	</term> first characterized linguistically	#15456 We have developed a computational model of the process of describing the layout of an apartment or house, a much-studied discourse task first characterized linguistically by Linde (1974).
	linguistic databases </term> . Our most important	task	in building the <term> editor </term> was to	#17296 Our most important task in building the editor was to define a set of coherence rules that could be computationally applied to ensure the validity of lexical entries.


	in Help