Concordance

Query natural 45 (2,098.0 per million)

other,13-3-H01-1055,bq	has been extensively studied by the <term>	natural	language generation community </term> , though	#981 The issue of system response to users has been extensively studied by thenatural language generation community, though rarely in the context of dialog systems.
tech,6-1-P01-1008,bq	for <term> interpretation and generation of	natural	language </term> , current systems use manual	#1763 While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases.
tech,14-2-P01-1009,bq	<term> attention </term> , yet present <term>	natural	language search engines </term> perform poorly	#1860 These words appear frequently enough in dialog to warrant serious attention, yet presentnatural language search engines perform poorly on queries containing them.
tech,12-4-P01-1009,bq	<term> operational semantics </term> of <term>	natural	language applications </term> improve , even	#1915 The value of this approach is that as the operational semantics ofnatural language applications improve, even larger improvements are possible.
tech,7-1-P01-1056,bq	automatically training </term> modules of a <term>	natural	language generator </term> have recently	#2019 Techniques for automatically training modules of anatural language generator have recently been proposed, but a fundamental concern is whether the quality of utterances produced with trainable components can compete with hand-crafted template-based or rule-based approaches.
tech,14-1-N03-1004,bq	learning </term> and other areas of <term>	natural	language processing </term> , we developed	#2320 Motivated by the success of ensemble methods in machine learning and other areas ofnatural 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.
tech,11-1-N03-3010,bq	novel <term> Cooperative Model </term> for <term>	natural	language understanding </term> in a <term>	#3488 In this paper, we propose a novel Cooperative Model fornatural language understanding in a dialogue system.
other,13-1-P03-1005,bq	HDAG ) Kernel </term> for <term> structured	natural	language data </term> . The <term> HDAG Kernel	#3803 This paper proposes the Hierarchical Directed Acyclic Graph (HDAG) Kernel for structured natural language data.
other,11-5-C04-1147,bq	<term> terabyte corpus </term> to answer <term>	natural	language tests </term> , achieving encouraging	#6428 We apply it in combination with a terabyte corpus to answernatural language tests, achieving encouraging results.
other,14-1-I05-2048,bq	currently one of the hot spots in <term>	natural	language processing </term> . Over the last	#8001 Statistical machine translation (SMT) is currently one of the hot spots innatural language processing.
tech,8-12-J05-1003,bq	experiments in this article are on <term>	natural	language parsing ( NLP ) </term> , the <term>	#8944 Although the experiments in this article are onnatural 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.
tech,43-12-J05-1003,bq	<term> machine translation </term> , or <term>	natural	language generation </term> . We present	#8979 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, ornatural language generation.
other,9-1-P80-1004,bq	inescapable process in <term> human understanding of	natural	language </term> . This paper discusses a	#12452 Interpreting metaphors is an integral and inescapable process in human understanding of natural language.
tech,1-1-P80-1019,bq	</term> are also discussed . Current <term>	natural	language interfaces </term> have concentrated	#12528 Currentnatural language interfaces have concentrated largely on determining the literal meaning of input from their users.
tech,13-2-P80-1019,bq	underpinning , much recent work suggests that <term>	natural	language interfaces </term> will never appear	#12558 While such decoding is an essential underpinning, much recent work suggests thatnatural language interfaces will never appear cooperative or graceful unless they also incorporate numerous non-literal aspects of communication, such as robust communication procedures.
tech,20-4-P80-1019,bq	valuable methods of more traditional <term>	natural	language interfaces </term> . When people	#12662 The paper proposes interfaces based on a judicious mixture of these techniques and the still valuable methods of more traditionalnatural language interfaces.
other,3-1-P80-1026,bq	interfaces </term> . When people use <term>	natural	language </term> in natural settings , they	#12669 When people usenatural language in natural settings, they often use it ungrammatically, missing out or repeating words, breaking-off and restarting, speaking in fragments, etc..
	people use <term> natural language </term> in	natural	settings , they often use it ungrammatically	#12672 When people use natural language in natural settings, they often use it ungrammatically, missing out or repeating words, breaking-off and restarting, speaking in fragments, etc..
other,7-3-P80-1026,bq	computer system </term> wishes to accept <term>	natural	language input </term> from its <term> users	#12720 If a computer system wishes to acceptnatural language input from its users on a routine basis, it must display a similar indifference.
other,23-5-P80-1026,bq	these flexibilities for <term> restricted	natural	language </term> input to a limited-domain	#12780 We go, on to describe FlexP, a bottom-up pattern-matching parser that we have designed and implemented to provide these flexibilities for restricted natural language input to a limited-domain computer system.


	in Help