Papers › Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

7 Jan 2019arXiv:1901.01824archive 2025-07-28

Jia-Chen Gu, Zhen-Hua Ling, Quan Liu

In this paper, we propose an interactive matching network (IMN) for the multi-turn response selection task. First, IMN constructs word representations from three aspects to address the challenge of out-of-vocabulary (OOV) words. Second, an attentive hierarchical recurrent encoder (AHRE), which is capable of encoding sentences hierarchically and generating more descriptive representations by aggregating with an attention mechanism, is designed. Finally, the bidirectional interactions between whole multi-turn contexts and response candidates are calculated to derive the matching information between them. Experiments on four public datasets show that IMN outperforms the baseline models on all metrics, achieving a new state-of-the-art performance and demonstrating compatibility across domains for multi-turn response selection.

PaperPDFCode

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

Code

JasonForJoy/IMN officialmentioned in papermentioned on GitHubtf 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 SelectionDescriptiveRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Conversational Response Selection Douban IMN MAP 0.570 #13 of 16 Archive leaderboard report
Conversational Response Selection Douban IMN MRR 0.615 #13 of 16 Archive leaderboard report
Conversational Response Selection Douban IMN P@1 0.433 #13 of 16 Archive leaderboard report
Conversational Response Selection Douban IMN R10@1 0.262 #13 of 16 Archive leaderboard report
Conversational Response Selection Douban IMN R10@2 0.452 #13 of 16 Archive leaderboard report
Conversational Response Selection Douban IMN R10@5 0.789 #13 of 16 Archive leaderboard report
Conversational Response Selection E-commerce IMN R10@1 0.621 #9 of 15 Archive leaderboard report
Conversational Response Selection E-commerce IMN R10@2 0.797 #9 of 15 Archive leaderboard report
Conversational Response Selection E-commerce IMN R10@5 0.964 #9 of 15 Archive leaderboard report
Conversational Response Selection Ubuntu Dialogue (v1, Ranking) IMN R10@1 0.794 #16 of 25 Archive leaderboard report
Conversational Response Selection Ubuntu Dialogue (v1, Ranking) IMN R10@2 0.889 #16 of 25 Archive leaderboard report
Conversational Response Selection Ubuntu Dialogue (v1, Ranking) IMN R10@5 0.974 #16 of 25 Archive leaderboard report
Conversational Response Selection Ubuntu Dialogue (v1, Ranking) IMN R2@1 0.946 #16 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