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

By Qian Chen, Wen Wang. 2019

41 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Dialogue & Conversational AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Dialogue & Conversational AI

Citations in the corpus

Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring (2019, neutral): “E.g., the Bi-encoder reaches 81.7% R@1 on ConvAI2 and 66.8% R@1 on DSTC7, while the Cross-encoder achieves higher scores of 84.8% R@1 on ConvAI2 and 67.4% R@1 on DSTC7.”
Real-time Inference in Multi-sentence Tasks with Deep Pretrained Transformers (2019, methodology): “The Cross-encoder scores 84.9% R@1 on ConvAI2 and 67.7% R@1 on DSTC7.”
Domain Adaptive Training BERT for Response Selection (2019, methodology): “The response selection task is similar to natural language inference problem; therefore, the most recent works are based on Enhanced Sequential Inference Model (ESIM) (Dong and Huang, 2018; Gu et al., 2019; Chen and Wang, 2019).”