Papers › Modeling Multi-turn Conversation with Deep Utterance Aggregation

Modeling Multi-turn Conversation with Deep Utterance Aggregation

24 Jun 2018COLING 2018 8arXiv:1806.09102archive 2025-07-28

Zhuosheng Zhang, Jiangtong Li, Pengfei Zhu, Hai Zhao, Gongshen Liu

Multi-turn conversation understanding is a major challenge for building intelligent dialogue systems. This work focuses on retrieval-based response matching for multi-turn conversation whose related work simply concatenates the conversation utterances, ignoring the interactions among previous utterances for context modeling. In this paper, we formulate previous utterances into context using a proposed deep utterance aggregation model to form a fine-grained context representation. In detail, a self-matching attention is first introduced to route the vital information in each utterance. Then the model matches a response with each refined utterance and the final matching score is obtained after attentive turns aggregation. Experimental results show our model outperforms the state-of-the-art methods on three multi-turn conversation benchmarks, including a newly introduced e-commerce dialogue corpus.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

cooelf/DeepUtteranceAggregation officialmentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Conversational Response SelectionRetrieval

Datasets

Introduced by this paper, per the archive.

E-commerce

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Conversational Response Selection Douban DUA MAP 0.551 #14 of 16 Archive leaderboard report
Conversational Response Selection Douban DUA MRR 0.599 #14 of 16 Archive leaderboard report
Conversational Response Selection Douban DUA P@1 0.421 #14 of 16 Archive leaderboard report
Conversational Response Selection Douban DUA R10@1 0.243 #14 of 16 Archive leaderboard report
Conversational Response Selection Douban DUA R10@2 0.421 #14 of 16 Archive leaderboard report
Conversational Response Selection Douban DUA R10@5 0.780 #14 of 16 Archive leaderboard report
Conversational Response Selection E-commerce DUA R10@1 0.501 #14 of 15 Archive leaderboard report
Conversational Response Selection E-commerce DUA R10@2 0.700 #14 of 15 Archive leaderboard report
Conversational Response Selection E-commerce DUA R10@5 0.921 #14 of 15 Archive leaderboard report
Conversational Response Selection Ubuntu Dialogue (v1, Ranking) DUA R10@1 0.752 #21 of 25 Archive leaderboard report
Conversational Response Selection Ubuntu Dialogue (v1, Ranking) DUA R10@2 0.868 #21 of 25 Archive leaderboard report
Conversational Response Selection Ubuntu Dialogue (v1, Ranking) DUA R10@5 0.962 #21 of 25 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections