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

08/22/2018
by   Chongyang Tao, et al.
0

We consider matching with pre-trained contextualized word vectors for multi-turn response selection in retrieval-based chatbots. When directly applied to the task, state-of-the-art models, such as CoVe and ELMo, do not work as well as they do on other tasks, due to the hierarchical nature, casual language, and domain-specific word use of conversations. To tackle the challenges, we propose pre-training a sentence-level and a session-level contextualized word vectors by learning a dialogue generation model from large-scale human-human conversations with a hierarchical encoder-decoder architecture. The two levels of vectors are then integrated into the input layer and the output layer of a matching model respectively. Experimental results on two benchmark datasets indicate that the proposed contextualized word vectors can significantly and consistently improve the performance of existing matching models for response selection.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/07/2019

Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

In this paper, we propose an interactive matching network (IMN) to enhan...
research
05/16/2020

Sequential Sentence Matching Network for Multi-turn Response Selection in Retrieval-based Chatbots

Recently, open domain multi-turn chatbots have attracted much interest f...
research
01/25/2017

Hierarchical Recurrent Attention Network for Response Generation

We study multi-turn response generation in chatbots where a response is ...
research
09/10/2018

Improving Response Selection in Multi-turn Dialogue Systems

Building systems that can communicate with humans is a core problem in A...
research
04/30/2016

Response Selection with Topic Clues for Retrieval-based Chatbots

We consider incorporating topic information into message-response matchi...
research
03/14/2023

X-ReCoSa: Multi-Scale Context Aggregation For Multi-Turn Dialogue Generation

In multi-turn dialogue generation, responses are not only related to the...
research
06/11/2019

Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems

We study learning of a matching model for response selection in retrieva...

Please sign up or login with your details

Forgot password? Click here to reset