An Information Retrieval Approach to Short Text Conversation
arXiv:1408.6988
Abstract
Human computer conversation is regarded as one of the most difficult problems in artificial intelligence. In this paper, we address one of its key sub-problems, referred to as short text conversation, in which given a message from human, the computer returns a reasonable response to the message. We leverage the vast amount of short conversation data available on social media to study the issue. We propose formalizing short text conversation as a search problem at the first step, and employing state-of-the-art information retrieval (IR) techniques to carry out the task. We investigate the significance as well as the limitation of the IR approach. Our experiments demonstrate that the retrieval-based model can make the system behave rather "intelligently", when combined with a huge repository of conversation data from social media.
21 pages, 4 figures
Cited by in corpus (17)
- Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
- Training Neural Response Selection for Task-Oriented Dialogue Systems
- Multiresolution Graph Attention Networks for Relevance Matching
- Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion
- A Deep Look into Neural Ranking Models for Information Retrieval
- Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems
- DAL: Dual Adversarial Learning for Dialogue Generation
- Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems
- A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
- A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots
- IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems
- Towards Automatic Generation of Entertaining Dialogues in Chinese Crosstalks
- Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots
- Weakly-Supervised Neural Response Selection from an Ensemble of Task-Specialised Dialogue Agents
- Unsupervised Context Rewriting for Open Domain Conversation
- Automating App Review Response Generation
- Improving Multi-Turn Response Selection Models with Complementary Last-Utterance Selection by Instance Weighting