Concordance

Query N03-1004 17 >
Shuffle 17 (792.6 per million)

tech,37-1-N03-1004,bq	combining the results from different <term>	answering agents	</term> searching for <term> answers </term>	#2343 Motivated by the success of ensemble methods in machine learning and other areas of natural language processing, we developed a multi-strategy and multi-source approach to question answering which is based on combining the results from differentanswering agents searching for answers in multiple corpora.
tech,3-3-N03-1004,bq	techniques </term> . We present our <term>	multi-level answer resolution algorithm	</term> that combines results from the <term>	#2375 We present ourmulti-level answer resolution algorithm that combines results from the answering agents at the question, passage, and/or answer levels.
tech,12-3-N03-1004,bq	</term> that combines results from the <term>	answering agents	</term> at the <term> question , passage ,	#2384 We present our multi-level answer resolution algorithm that combines results from theanswering agents at the question, passage, and/or answer levels.
measure(ment),23-4-N03-1004,bq	baseline system </term> in the number of <term>	questions correctly answered	</term> , and a 32.8 % improvement according	#2419 Experiments evaluating the effectiveness of our answer resolution algorithm show a 35.0% relative improvement over our baseline system in the number ofquestions correctly answered, and a 32.8% improvement according to the average precision metric.
other,17-4-N03-1004,bq	35.0 % relative improvement over our <term>	baseline system	</term> in the number of <term> questions correctly	#2413 Experiments evaluating the effectiveness of our answer resolution algorithm show a 35.0% relative improvement over ourbaseline system in the number of questions correctly answered, and a 32.8% improvement according to the average precision metric.
measure(ment),35-4-N03-1004,bq	32.8 % improvement according to the <term>	average precision metric	</term> . In this paper we present <term> ONTOSCORE	#2431 Experiments evaluating the effectiveness of our answer resolution algorithm show a 35.0% relative improvement over our baseline system in the number of questions correctly answered, and a 32.8% improvement according to theaverage precision metric.
tech,6-4-N03-1004,bq	evaluating the effectiveness of our <term>	answer resolution algorithm	</term> show a 35.0 % relative improvement	#2402 Experiments evaluating the effectiveness of ouranswer resolution algorithm show a 35.0% relative improvement over our baseline system in the number of questions correctly answered, and a 32.8% improvement according to the average precision metric.
tech,8-1-N03-1004,bq	of <term> ensemble methods </term> in <term>	machine learning	</term> and other areas of <term> natural language	#2314 Motivated by the success of ensemble methods inmachine learning and other areas of natural 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.
lr,44-1-N03-1004,bq	for <term> answers </term> in multiple <term>	corpora	</term> . The <term> answering agents </term>	#2350 Motivated by the success of ensemble methods in machine learning and other areas of natural 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 multiplecorpora.
tech,17-2-N03-1004,bq	mechanisms </term> and the other adopting <term>	statistical techniques	</term> . We present our <term> multi-level	#2369 The answering agents adopt fundamentally different strategies, one utilizing primarily knowledge-based mechanisms and the other adoptingstatistical techniques.
tech,21-1-N03-1004,bq	processing </term> , we developed a <term>	multi-strategy and multi-source approach to question answering	</term> which is based on combining the results	#2327 Motivated by the success of ensemble methods in machine learning and other areas of natural language processing, we developed amulti-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,1-2-N03-1004,bq	multiple <term> corpora </term> . The <term>	answering agents	</term> adopt fundamentally different strategies	#2353 Theanswering agents adopt fundamentally different strategies, one utilizing primarily knowledge-based mechanisms and the other adopting statistical techniques.
tech,11-2-N03-1004,bq	strategies , one utilizing primarily <term>	knowledge-based mechanisms	</term> and the other adopting <term> statistical	#2363 The answering agents adopt fundamentally different strategies, one utilizing primarilyknowledge-based mechanisms and the other adopting statistical techniques.
tech,14-1-N03-1004,bq	learning </term> and other areas of <term>	natural language processing	</term> , we developed a <term> multi-strategy	#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,5-1-N03-1004,bq	</term> . Motivated by the success of <term>	ensemble methods	</term> in <term> machine learning </term> and	#2311 Motivated by the success ofensemble methods in machine learning and other areas of natural 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.
other,16-3-N03-1004,bq	<term> answering agents </term> at the <term>	question , passage , and/or answer levels	</term> . Experiments evaluating the effectiveness	#2388 We present our multi-level answer resolution algorithm that combines results from the answering agents at thequestion , passage , and/or answer levels.
other,41-1-N03-1004,bq	answering agents </term> searching for <term>	answers	</term> in multiple <term> corpora </term> .	#2347 Motivated by the success of ensemble methods in machine learning and other areas of natural 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 foranswers in multiple corpora.


	in Help