Concordance

Query to 432 >
Sort Right 432 >
Sort Node 432 >
Positive filter TO 432 >
Sort Left 432 (20,140.8 per million)

statistical machine translation ( MT ) </term> ,	to	understand the <term> model </term> 's strengths	#9866 The method allows a user to explore a model of syntax-based statistical machine translation (MT), to understand the model's strengths and weaknesses, and to compare it to other MT systems.
Phrasal Lexicon ( DHPL ) </term> [ Zernik88 ] ,	to	facilitate <term> language acquisition </term>	#15805 We introduced a new linguistic representation, the Dynamic Hierarchical Phrasal Lexicon (DHPL) [Zernik88], to facilitate language acquisition.
confines of <term> syntax </term> , for instance ,	to	the task of <term> semantic interpretation	#16452 The unique properties of tree-adjoining grammars (TAG) present a challenge for the application of TAGs beyond the limited confines of syntax, for instance, to the task of semantic interpretation or automatic translation of natural language.
<term> machine translation </term> , that is ,	to	make decisions on the basis of <term> translation	#18095 Currently some attempts are being made to use case-based reasoning in machine translation, that is, to make decisions on the basis of translation examples at appropriate pints in MT.
of <term> human language learners </term> ,	to	the <term> output </term> of <term> machine translation	#570 The purpose of this research is to test the efficacy of applying automated evaluation techniques, originally devised for the evaluation of human language learners, to the output of machine translation (MT) systems.
able , after attending this workshop ,	to	set out building an <term> SMT system </term>	#8086 Participants should be able, after attending this workshop, to set out building an SMT system themselves and achieving good baseline results in a short time.
noted I walked : to walk : : I laughed :	to	laugh ) . But <term> computational linguists	#5880 The reality of analogies between words is refuted by noone (e.g., I walked is to to walk as I laughed is to to laugh, noted I walked : to walk :: I laughed : to laugh).
laughed is to to laugh , noted I walked :	to	walk : : I laughed : to laugh ) . But <term>	#5873 The reality of analogies between words is refuted by noone (e.g., I walked is to to walk as I laughed is to to laugh, noted I walked : to walk :: I laughed : to laugh).
patterns </term> in a large <term> corpus </term> .	To	a large extent , these <term> statistics </term>	#16633 This paper presents an automatic scheme for collecting statistics on co-occurrence patterns in a large corpus. To a large extent, these statistics reflect semantic constraints and thus are used to disambiguate anaphora references and syntactic ambiguities.
the <term> accuracy rate </term> directly .	To	make the proposed algorithm robust , the	#17880 The proposed method remedies these problems by adjusting the parameters to maximize the accuracy rate directly. To make the proposed algorithm robust, the possible variations between the training corpus and the real tasks are also taken into consideration by enlarging the separation margin between the correct candidate and its competing members.
their <term> translation equivalents </term> .	To	help this task we have developed an <term>	#20776 This paper describes the enhancements made, within a unification framework, based on typed feature structures, in order to support linking of lexical entries to their translation equivalents. To help this task we have developed an interactive environment: TGE.
detected <term> homophone errors </term> .	To	align <term> bilingual texts </term> becomes	#20532 Also, the method successfully indicates the correct candidates for the detected homophone errors. To align bilingual texts becomes a crucial issue recently.
<term> N-Best sentence hypotheses </term> .	To	avoid <term> grammar coverage problems </term>	#16903 We describe algorithms that greatly reduce the computation needed to compute the N-Best sentence hypotheses. To avoid grammar coverage problems we use a fully-connected first-order statistical class grammar.
values </term> is <term> NP-complete </term> .	To	deal with this <term> complexity </term> ,	#14833 We have shown that the consistency problem for formulas with disjunctive values is NP-complete. To deal with this complexity, we describe how disjunctive values can be specified in a way which delays expansion to disjunctive normal form.
attribute </term> among <term> objects </term> .	To	overcome this limitation , this paper proposes	#5649 However, such an approach does not work well when there is no distinctive attribute among objects. To overcome this limitation, this paper proposes a method utilizing the perceptual groups of objects and n-ary relations among them.
these <term> indices </term> can be obtained .	To	support engaging human users in robust	#206 Despite the small size of the databases used some results about the effectiveness of these indices can be obtained. To support engaging human users in robust, mixed-initiative speech dialogue interactions which reach beyond current capabilities in dialogue systems, the DARPA Communicator program [1] is funding the development of a distributed message-passing infrastructure for dialogue systems which all Communicator participants are using.
</term> of about 110,000 <term> words </term> .	To	improve the <term> segmentation </term><term>	#4706 The language model is initially estimated from a small manually segmented corpus of about 110,000 words. To improve the segmentation accuracy, we use an unsupervised algorithm for automatically acquiring new stems from a 155 million word unsegmented corpus, and re-estimate the model parameters with the expanded vocabulary and training corpus.
</term> of the described <term> world </term> .	To	reconstruct the <term> model </term> , the	#18454 It is done by an experimental computer program SPRINT, which takes natural language texts and produces a model of the described world. To reconstruct the model, the authors extract the qualitative spatial constraints from the text, and represent them as the numerical constraints on the spatial attributes of the entities.
Lexical-Functional Grammars ( LFG ) </term>	to	the domain of <term> sentence condensation	#2801 We present an application of ambiguity packing and stochastic disambiguation techniques for Lexical-Functional Grammars (LFG) to the domain of sentence condensation.
methods ( BLEU , NIST , WER and PER ) </term>	to	building <term> classifiers </term> to predict	#8357 This paper investigates the utility of applying standard MT evaluation methods (BLEU, NIST, WER and PER) to building classifiers to predict semantic equivalence and entailment.


	in Help