DeepAI AI Chat
Log In Sign Up

Improving Multi-Turn Response Selection Models with Complementary Last-Utterance Selection by Instance Weighting

by   Kun Zhou, et al.
Renmin University of China
Université de Montréal
Peking University

Open-domain retrieval-based dialogue systems require a considerable amount of training data to learn their parameters. However, in practice, the negative samples of training data are usually selected from an unannotated conversation data set at random. The generated training data is likely to contain noise and affect the performance of the response selection models. To address this difficulty, we consider utilizing the underlying correlation in the data resource itself to derive different kinds of supervision signals and reduce the influence of noisy data. More specially, we consider a main-complementary task pair. The main task ( our focus) selects the correct response given the last utterance and context, and the complementary task selects the last utterance given the response and context. The key point is that the output of the complementary task is used to set instance weights for the main task. We conduct extensive experiments in two public datasets and obtain significant improvement in both datasets. We also investigate the variant of our approach in multiple aspects, and the results have verified the effectiveness of our approach.


page 1

page 2

page 3

page 4


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

This paper proposes an utterance-to-utterance interactive matching netwo...

Utterance Pair Scoring for Noisy Dialogue Data Filtering

Filtering noisy training data is one of the key approaches to improving ...

Unsupervised Context Rewriting for Open Domain Conversation

Context modeling has a pivotal role in open domain conversation. Existin...

Grayscale Data Construction and Multi-Level Ranking Objective for Dialogue Response Selection

Response selection plays a vital role in building retrieval-based conver...

A Graph Reasoning Network for Multi-turn Response Selection via Customized Pre-training

We investigate response selection for multi-turn conversation in retriev...

Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding

To build a satisfying chatbot that has the ability of managing a goal-or...

Efficient Semi-Supervised Learning for Natural Language Understanding by Optimizing Diversity

Expanding new functionalities efficiently is an ongoing challenge for si...