Concordance

Query N03-1004 17 >
Random sample 17 (544.3 per million)

tech,5-1-N03-1004,ak	Motivated by the success of <term> ensemble methods </term> in <term> machine learning </term> and other areas of <term> natural language processing </term> , we developed a multi-strategy and multi-source approach to <term> question answering </term> which is based on combining the results from different <term> answering agents </term> searching for <term> answers </term> in multiple <term> corpora </term> .	#2312 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.
tech,8-1-N03-1004,ak	Motivated by the success of <term> ensemble methods </term> in <term> machine learning </term> and other areas of <term> natural language processing </term> , we developed a multi-strategy and multi-source approach to <term> question answering </term> which is based on combining the results from different <term> answering agents </term> searching for <term> answers </term> in multiple <term> corpora </term> .	#2315 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.
tech,14-1-N03-1004,ak	Motivated by the success of <term> ensemble methods </term> in <term> machine learning </term> and other areas of <term> natural language processing </term> , we developed a multi-strategy and multi-source approach to <term> question answering </term> which is based on combining the results from different <term> answering agents </term> searching for <term> answers </term> in multiple <term> corpora </term> .	#2321 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,26-1-N03-1004,ak	Motivated by the success of <term> ensemble methods </term> in <term> machine learning </term> and other areas of <term> natural language processing </term> , we developed a multi-strategy and multi-source approach to <term> question answering </term> which is based on combining the results from different <term> answering agents </term> searching for <term> answers </term> in multiple <term> corpora </term> .	#2333 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 toquestion answering which is based on combining the results from different answering agents searching for answers in multiple corpora.
tech,37-1-N03-1004,ak	Motivated by the success of <term> ensemble methods </term> in <term> machine learning </term> and other areas of <term> natural language processing </term> , we developed a multi-strategy and multi-source approach to <term> question answering </term> which is based on combining the results from different <term> answering agents </term> searching for <term> answers </term> in multiple <term> corpora </term> .	#2344 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.
other,41-1-N03-1004,ak	Motivated by the success of <term> ensemble methods </term> in <term> machine learning </term> and other areas of <term> natural language processing </term> , we developed a multi-strategy and multi-source approach to <term> question answering </term> which is based on combining the results from different <term> answering agents </term> searching for <term> answers </term> in multiple <term> corpora </term> .	#2348 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.
lr,44-1-N03-1004,ak	Motivated by the success of <term> ensemble methods </term> in <term> machine learning </term> and other areas of <term> natural language processing </term> , we developed a multi-strategy and multi-source approach to <term> question answering </term> which is based on combining the results from different <term> answering agents </term> searching for <term> answers </term> in multiple <term> corpora </term> .	#2351 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,1-2-N03-1004,ak	The <term> answering agents </term> adopt fundamentally different strategies , one utilizing primarily knowledge-based mechanisms and the other adopting statistical techniques .	#2354 Theanswering agents adopt fundamentally different strategies, one utilizing primarily knowledge-based mechanisms and the other adopting statistical techniques.
tech,3-3-N03-1004,ak	We present our <term> multi-level answer resolution algorithm </term> that combines results from the <term> answering agents </term> at the <term> question , passage , and/or answer levels </term> .	#2376 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,ak	We present our <term> multi-level answer resolution algorithm </term> that combines results from the <term> answering agents </term> at the <term> question , passage , and/or answer levels </term> .	#2385 We present our multi-level answer resolution algorithm that combines results from theanswering agents at the question, passage, and/or answer levels.
other,16-3-N03-1004,ak	We present our <term> multi-level answer resolution algorithm </term> that combines results from the <term> answering agents </term> at the <term> question , passage , and/or answer levels </term> .	#2389 We present our multi-level answer resolution algorithm that combines results from the answering agents at thequestion , passage , and/or answer levels.
tech,6-4-N03-1004,ak	Experiments evaluating the effectiveness of our <term> answer resolution algorithm </term> show a 35.0 % <term> relative improvement </term> over our <term> baseline system </term> in the number of <term> questions </term> correctly answered , and a 32.8 % <term> improvement </term> according to the <term> average precision metric </term> .	#2403 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.
measure(ment),13-4-N03-1004,ak	Experiments evaluating the effectiveness of our <term> answer resolution algorithm </term> show a 35.0 % <term> relative improvement </term> over our <term> baseline system </term> in the number of <term> questions </term> correctly answered , and a 32.8 % <term> improvement </term> according to the <term> average precision metric </term> .	#2410 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 the average precision metric.
other,17-4-N03-1004,ak	Experiments evaluating the effectiveness of our <term> answer resolution algorithm </term> show a 35.0 % <term> relative improvement </term> over our <term> baseline system </term> in the number of <term> questions </term> correctly answered , and a 32.8 % <term> improvement </term> according to the <term> average precision metric </term> .	#2414 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.
other,23-4-N03-1004,ak	Experiments evaluating the effectiveness of our <term> answer resolution algorithm </term> show a 35.0 % <term> relative improvement </term> over our <term> baseline system </term> in the number of <term> questions </term> correctly answered , and a 32.8 % <term> improvement </term> according to the <term> average precision metric </term> .	#2420 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.
measure(ment),31-4-N03-1004,ak	Experiments evaluating the effectiveness of our <term> answer resolution algorithm </term> show a 35.0 % <term> relative improvement </term> over our <term> baseline system </term> in the number of <term> questions </term> correctly answered , and a 32.8 % <term> improvement </term> according to the <term> average precision metric </term> .	#2428 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 the average precision metric.
measure(ment),35-4-N03-1004,ak	Experiments evaluating the effectiveness of our <term> answer resolution algorithm </term> show a 35.0 % <term> relative improvement </term> over our <term> baseline system </term> in the number of <term> questions </term> correctly answered , and a 32.8 % <term> improvement </term> according to the <term> average precision metric </term> .	#2432 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.


	in Help