Abstract

A neural conversation model is a promising approach to develop dialogue systems with the ability of chit-chat. It allows training a model in an end-to-end manner without complex rule design nor feature engineering. However, as a side effect, the neural model tends to generate safe but uninformative and insensitive responses like “OK” and “I don’t know.” Such replies are called generic responses and regarded as a critical problem for user-engagement of dialogue systems. For a more engaging chit-chat experience, we propose a neural conversation model that generates responsive and self-expressive replies. Specifically, our model generates domain-aware and sentiment-rich responses. Experiments empirically confirmed that our model outperformed the sequence-to-sequence model; 68.1% of our responses were domain-aware with sentiment polarities, which was only 2.7% for responses generated by the sequence-to-sequence model.

Highlights

  • Dialogue systems that conduct non-goal-oriented chat, i.e., chit-chat, is an active research area

  • To avoid error propagation from the pre-trained TWEET2VEC, gold domain labels are inputted into the multilayer perceptron (MLP) to learn correct representations of domain labels

  • This phenomenon may be because SEQ2SEQ tends to output generic responses that are less dependent on the utterances, making judgments difficult due to the limited clues to evaluate fluency

Read more

Summary

Introduction

Dialogue systems that conduct non-goal-oriented chat, i.e., chit-chat, is an active research area. The second is internal and external memories, which control the emotional state and the output of the decoder, respectively These previous studies propose methods to achieve either conversational responsiveness or self-expression. Different approaches have been proposed to generate diversified responses; by an objective function (Li et al, 2016a; Zhang et al, 2018b), segment-level reranking via a stochastic beam-search in a decoder (Shao et al, 2017), or by incorporating auto-encoders so that latent vectors are expressive enough for the utterance and response (Zou et al, 2018) In these approaches, balancing the diversity and coherency in a response is not trivial.

Proposed Architecture
Encoder
Decoder
Training Framework
Sentiment Annotation
Pre-Training on Sub-Models
Fine-Tuning on the Entire Model
Evaluation Design
Data Collection
Summary
Model Setting
Human Evaluation
Evaluation Results
Conclusion
A Construction of the Sentiment Lexicon
B Preprocessing
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call