Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward
원문 초록
Controllable text generation is an appealing but challenging task, which allows users to specify particular attributes of the generated outputs. In this paper, we propose a controllable dialogue generation model to steer response generation under multi-attribute constraints. Specifically, we define and categorize the commonly used control attributes into global and local ones, which possess different granularities of effects on response generation. Then, we significantly extend the conventional seq2seq framework by introducing a novel two-stage decoder, which first uses a multi-grained style specification layer to impose the stylistic constraints and determine word-level control states of responses based on the attributes, and then employs a response generation layer to generate final responses maintaining both semantic relevancy to the contexts and fidelity to the attributes. Furthermore, we train our model with an attribute consistency reward to promote response control with explicit supervision signals. Extensive experiments and in-depth analyses on two datasets indicate that our model can significantly outperform competitive baselines in terms of response quality, content diversity and controllability.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sparse Regression Codes exploit Multi-User Diversity without CSI
DEU-Net: Dual-Encoder U-Net for Automated Skin Lesion Segmentation
Beyond the Attention: Distinguish the Discriminative and Confusable Features For Fine-grained Image Classification
Deep Encoder-Decoder Networks for Classification of Hyperspectral and LiDAR Data
Improving Diversity and Reducing Redundancy in Paragraph Captions
Making Language Model a Hierarchical Classifier and Generator
토론
이 논문과 연결된 포럼 글이 아직 없습니다.