Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer
With the increasing research interest in dialogue response generation, there is an emerging branch formulating this task as selecting next sentences, where given the partial dialogue contexts, the goal is to determine the most probable next sentence. Following the recent success of the Transformer model, this paper proposes (1) a new variant of attention mechanism based on multi-head attention, called highway attention, and (2) a recurrent model based on transformer and the proposed highway attention, so-called Highway Recurrent Transformer. Experiments on the response selection task in the seventh Dialog System Technology Challenge (DSTC7) show the capability of the proposed model of modeling both utterance-level and dialogue-level information; the effectiveness of each module is further analyzed as well.
Code (0)
등록된 구현이 없습니다.
Tasks
Response GenerationSentenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbots
Existing multi-turn context-response matching methods mainly concentrate on obtaining multi-level and multi-dimension representations and better interactions between context utterances and response. However, in real-plac…
Representation LearningRetrievalUser IdentificationKnowledge-aware response selection with semantics underlying multi-turn open-domain conversations
Response selection is a critical issue in the AI community, with important applications on the Web. The accuracy of the selected responses, however, tends to be insufficient due to the lack of contextual awareness, espec…
Conversational Response SelectionImproving Response Selection in Multi-Turn Dialogue Systems by Incorporating Domain Knowledge
Building systems that can communicate with humans is a core problem in Artificial Intelligence. This work proposes a novel neural network architecture for response selection in an end-to-end multi-turn conversational dia…
Dialogue Response Selection with Hierarchical Curriculum Learning
We study the learning of a matching model for dialogue response selection. Motivated by the recent finding that models trained with random negative samples are not ideal in real-world scenarios, we propose a hierarchical…
Conversational Response SelectionSEntNet: Source-aware Recurrent Entity Network for Dialogue Response Selection
Dialogue response selection is an important part of Task-oriented Dialogue Systems (TDSs); it aims to predict an appropriate response given a dialogue context. Obtaining key information from a complex, long dialogue cont…
Task-Oriented Dialogue Systems