D11-1054 challenges in adapting SMT to the response generation task . First , unlike bilingual
D08-1028 on a template-based approach to response generation . We focus on providing tools
D11-1054 straightforward data-driven approach to response generation is nearest neighbour , or information
D11-1054 various approaches to automated response generation , we used human evalu ators from
D11-1054 filter . We compare our approach to response generation against two Information Retrieval
D11-1054 translation as an approach for response generation . We are motivated by the following
E03-1060 to question analysis and to NL response generation . Our challenge is to integrate
D11-1054 one frequent type of response we response generation , we attempted to measure its
H89-1037 Computational Model of Cooperative Response Generation * </title> Brant A Cheikes Bonnie
A00-1014 strategies that guides MIMIC 's response generation process . This task is carried
D11-1054 than IR approaches on the task of response generation . Our system , MT-CHAT , produced
E03-1060 Cooperative response elaboration and response generation are presented in ( Benamara and
H89-1037 concerns the design of cooperative response generation ( CRG ) systems , NLQA systems
H01-1063 lower will not take effect in response generation ( i.e. prompting / clarification
A00-1014 adaptation to automatically adapt response generation strategies based on the cumulative
A00-1014 the dialogue acts employed for response generation in each system turn ( in boldface
D11-1054 accuracy . <title> Data-Driven Response Generation in Social Media </title> Alan
C02-1107 and " chikaku ( near ) " . 4 . Response generation : The system responds based on
D11-1054 the BLEU metric when applied to response generation , showing that though the metric
D11-1054 Because automatic evaluation of response generation is an open problem , we avoided
hide detail