CLAug 2, 2017

Domain Aware Neural Dialog System

arXiv:1708.00897v123 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the challenge of maintaining context in multi-domain conversations for chatbots, though it appears incremental by extending existing sequence-to-sequence methods.

The paper tackles the problem of building a domain-aware chat system that generates intelligent responses across different conversation topics, achieving improved performance compared to a baseline Seq2Seq model as evaluated on automatic metrics.

We investigate the task of building a domain aware chat system which generates intelligent responses in a conversation comprising of different domains. The domain, in this case, is the topic or theme of the conversation. To achieve this, we present DOM-Seq2Seq, a domain aware neural network model based on the novel technique of using domain-targeted sequence-to-sequence models (Sutskever et al., 2014) and a domain classifier. The model captures features from current utterance and domains of the previous utterances to facilitate the formation of relevant responses. We evaluate our model on automatic metrics and compare our performance with the Seq2Seq model.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes