Hierarchical Recurrent Attention Network for Response Generation

by   Chen Xing, et al.

We study multi-turn response generation in chatbots where a response is generated according to a conversation context. Existing work has modeled the hierarchy of the context, but does not pay enough attention to the fact that words and utterances in the context are differentially important. As a result, they may lose important information in context and generate irrelevant responses. We propose a hierarchical recurrent attention network (HRAN) to model both aspects in a unified framework. In HRAN, a hierarchical attention mechanism attends to important parts within and among utterances with word level attention and utterance level attention respectively. With the word level attention, hidden vectors of a word level encoder are synthesized as utterance vectors and fed to an utterance level encoder to construct hidden representations of the context. The hidden vectors of the context are then processed by the utterance level attention and formed as context vectors for decoding the response. Empirical studies on both automatic evaluation and human judgment show that HRAN can significantly outperform state-of-the-art models for multi-turn response generation.


page 1

page 2

page 3

page 4


A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots

We study the problem of response selection for multi-turn conversation i...

Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks

We study multi-turn response generation for open-domain dialogues. The e...

A non-hierarchical attention network with modality dropout for textual response generation in multimodal dialogue systems

Existing text- and image-based multimodal dialogue systems use the tradi...

TripleNet: Triple Attention Network for Multi-Turn Response Selection in Retrieval-based Chatbots

We consider the importance of different utterances in the context for se...

Improving Matching Models with Contextualized Word Representations for Multi-turn Response Selection in Retrieval-based Chatbots

We consider matching with pre-trained contextualized word vectors for mu...

Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances

Each utterance in multi-turn empathetic dialogues has features such as e...

Short Text Conversation Based on Deep Neural Network and Analysis on Evaluation Measures

With the development of Natural Language Processing, Automatic question-...

Please sign up or login with your details

Forgot password? Click here to reset