Generating Stylistically Consistent Dialog Responses with Transfer Learning
We propose a novel, data-driven, and stylistically consistent dialog response generation system. To create a user-friendly system, it is crucial to make generated responses not only appropriate but also stylistically consistent. For leaning both the properties effectively, our proposed framework has two training stages inspired by transfer learning. First, we train the model to generate appropriate responses, and then we ensure that the responses have a specific style. Experimental results demonstrate that the proposed method produces stylistically consistent responses while maintaining the appropriateness of the responses learned in a general domain.
Code (0)
등록된 구현이 없습니다.
Tasks
Response GenerationTransfer LearningSimilar Papers 제목 키워드 기반
Consistent Dialogue Generation with Self-supervised Feature Learning
Generating responses that are consistent with the dialogue context is one of the central challenges in building engaging conversational agents. We demonstrate that neural conversation models can be geared towards generat…
Dialogue GenerationResponse GenerationGenerating Persona Consistent Dialogues by Exploiting Natural Language Inference
Consistency is one of the major challenges faced by dialogue agents. A human-like dialogue agent should not only respond naturally, but also maintain a consistent persona. In this paper, we exploit the advantages of natu…
DecoderDialogue GenerationNatural Language InferenceReinforcement LearningLearning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training
In this paper, we propose Inverse Adversarial Training (IAT) algorithm for training neural dialogue systems to avoid generic responses and model dialogue history better. In contrast to standard adversarial training algor…
Dialogue GenerationDiversityResponse GenerationAutomatically Exposing Problems with Neural Dialog Models
Neural dialog models are known to suffer from problems such as generating unsafe and inconsistent responses. Even though these problems are crucial and prevalent, they are mostly manually identified by model designers th…
reinforcement-learningReinforcement Learning (RL)GFDC: Graph Function Dependence for Logically Consistent Dialogue Response Beyond Persona Data
The rigorous logical consistency between current and historical responses during dialogue is the basis of an excellent human speaker, and it is also essential for dialogue agents. Although maintaining consistent personas…
Dialogue GenerationGeneral Knowledge