Sequential Attention-based Network for Noetic End-to-End Response Selection

TL;DR

This paper introduces a sequential attention-based neural network for multi-turn response selection in dialog systems, outperforming hierarchy-based models and achieving state-of-the-art results on benchmark datasets.

Contribution

Proposes a novel sequential matching model that effectively captures multi-turn context without hierarchy, surpassing existing models in response selection tasks.

Findings

Outperforms hierarchy-based models on DSTC7 datasets

Achieves new state-of-the-art on large-scale benchmarks

Demonstrates the effectiveness of sequential matching in dialog response selection

Abstract

The noetic end-to-end response selection challenge as one track in Dialog System Technology Challenges 7 (DSTC7) aims to push the state of the art of utterance classification for real world goal-oriented dialog systems, for which participants need to select the correct next utterances from a set of candidates for the multi-turn context. This paper describes our systems that are ranked the top on both datasets under this challenge, one focused and small (Advising) and the other more diverse and large (Ubuntu). Previous state-of-the-art models use hierarchy-based (utterance-level and token-level) neural networks to explicitly model the interactions among different turns' utterances for context modeling. In this paper, we investigate a sequential matching model based only on chain sequence for multi-turn response selection. Our results demonstrate that the potentials of sequential matching approaches have not yet been fully exploited in the past for multi-turn response selection. In addition to ranking the top in the challenge, the proposed model outperforms all previous models, including state-of-the-art hierarchy-based models, and achieves new state-of-the-art performances on two large-scale public multi-turn response selection benchmark datasets.