Concordance

Query new 52 >
Sort Left 52 (2,424.4 per million)

In our demonstration at <term> ACL </term> ,	new	<term> users </term> of our <term> tool </term>	#9909 In our demonstration at ACL, new users of our tool will drive a syntax-based decoder for themselves.
including <term> part of speech tagging </term> ,	new	<term> similarity measures </term> and expanded	#4112 Motivated by these arguments, we introduce a number of new performance enhancing techniques including part of speech tagging, new similarity measures and expanded stop lists.
Language Processing </term> . In this paper , a	new	mechanism , based on the concept of <term>	#18290 In this paper, a new mechanism, based on the concept of sublanguage, is proposed for identifying unknown words, especially personal names, in Chinese newspapers.
of the missing <term> fragments </term> . A	new	approach for <term> Interactive Machine Translation	#15639 A new approach for Interactive Machine Translation where the author interacts during the creation or the modification of the document is proposed.
</term> and <term> ambiguity handling </term> . A	new	, flexible <term> inference method </term>	#20879 A new, flexible inference method for Horn logic program is proposed.
</term> , a <term> sentence planner </term> , and a	new	methodology for automatically training <term>	#1349 In this paper, we present SPoT, a sentence planner, and a new methodology for automatically training SPoT on the basis of feedback provided by human judges.
technique for failed parses </term> , and a	new	technique called <term> terminal substring	#17481 We describe three techniques for making syntactic analysis more robust---an agenda-based scheduling parser, a recovery technique for failed parses, and a new technique called terminal substring parsing.
undisambiguated <term> corpus data </term> . We describe a	new	approach which involves clustering <term>	#3905 We describe a new approach which involves clustering subcategorization frame (SCF) distributions using the Information Bottleneck and nearest neighbour methods.
thesis statements </term> ) . We describe a	new	system that enhances <term> Criterion </term>	#6673 We describe a new system that enhances Criterion's capability, by evaluating multiple aspects of coherence in essays.
</term> occurs . In this paper we explore a	new	<term> theory of discourse structure </term>	#14086 In this paper we explore a new theory of discourse structure that stresses the role of purpose and processing in discourse.
predicate-argument structures </term> . We also introduce a	new	way of automatically identifying <term> predicate	#3733 We also introduce a new way of automatically identifying predicate argument structures, which is central to our IE paradigm.
relative performances . We also introduce a	new	strategy , called <term> Begin/After tagging	#10844 We also introduce a new strategy, called Begin/After tagging or BIA, and show that it is competitive to the best other strategies.
features </term> into account . We introduce a	new	<term> method </term> for the <term> reranking	#8762 We introduce a new method for the reranking task, based on the boosting approach to ranking problems described in Freund et al. (1998).
the best other strategies . We introduce a	new	<term> interactive corpus exploration tool	#10868 We introduce a new interactive corpus exploration tool called InfoMagnets.
to <term> learning </term> . We introduced a	new	<term> linguistic representation </term> ,	#15789 We introduced a new linguistic representation, the Dynamic Hierarchical Phrasal Lexicon (DHPL) [Zernik88], to facilitate language acquisition.
of 88.2 % . The article also introduces a	new	<term> algorithm </term> for the <term> boosting	#8866 The article also introduces a new algorithm for the boosting approach which takes advantage of the sparsity of the feature space in the parsing data.
Listen-Communicate-Show ( LCS ) </term> is a	new	paradigm for <term> human interaction with	#786 Listen-Communicate-Show (LCS) is a new paradigm for human interaction with data sources.
recognition </term> has brought to light a	new	problem : as <term> dialog systems </term>	#941 However, the improved speech recognition has brought to light a new problem: as dialog systems understand more of what the user tells them, they need to be more sophisticated at responding to the user.
constraint-based parser/generator </term> . We present a	new	<term> part-of-speech tagger </term> that demonstrates	#2912 We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of lexical features, including jointly conditioning on multiple consecutive words, (iii) effective use of priors in conditional loglinear models, and (iv) fine-grained modeling of unknown word features.
positive effect on both tasks . We present a	new	<term> HMM tagger </term> that exploits <term>	#5499 We present a new HMM tagger that exploits context on both sides of a word to be tagged, and evaluate it in both the unsupervised and supervised case.


	in Help