Conversational Word Embedding for Retrieval-Based Dialog System

04/28/2020

∙

by Wentao Ma, et al.

∙

Harbin Institute of Technology

∙

Anhui USTC iFLYTEK Co

∙

Human conversations contain many types of information, e.g., knowledge, common sense, and language habits. In this paper, we propose a conversational word embedding method named PR-Embedding, which utilizes the conversation pairs 〈post, reply〉 to learn word embedding. Different from previous works, PR-Embedding uses the vectors from two different semantic spaces to represent the words in post and reply. To catch the information among the pair, we first introduce the word alignment model from statistical machine translation to generate the cross-sentence window, then train the embedding on word-level and sentence-level. We evaluate the method on single-turn and multi-turn response selection tasks for retrieval-based dialog systems. The experiment results show that PR-Embedding can improve the quality of the selected response. PR-Embedding source code is available at https://github.com/wtma/PR-Embedding

READ FULL TEXT

Conversational Word Embedding for Retrieval-Based Dialog System

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

NoPPA: Non-Parametric Pairwise Attention Random Walk Model for Sentence Representation

Introduction of a novel word embedding approach based on technology labels extracted from patent data

Show, Price and Negotiate: A Hierarchical Attention Recurrent Visual Negotiator

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

Aligning Vector-spaces with Noisy Supervised Lexicons

SuperChat: Dialogue Generation by Transfer Learning from Vision to Language using Two-dimensional Word Embedding and Pretrained ImageNet CNN Models

Code Repositories

PR-Embedding

Conversational Word Embedding for Retrieval-Based Dialog System

Related Research

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

NoPPA: Non-Parametric Pairwise Attention Random Walk Model for Sentence Representation

Introduction of a novel word embedding approach based on technology labels extracted from patent data

Show, Price and Negotiate: A Hierarchical Attention Recurrent Visual Negotiator

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

Aligning Vector-spaces with Noisy Supervised Lexicons

SuperChat: Dialogue Generation by Transfer Learning from Vision to Language using Two-dimensional Word Embedding and Pretrained ImageNet CNN Models

Code Repositories

PR-Embedding