Papers › Sequential Matching Network: A New Architecture for Multi-turn Response Selection in...

Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots

6 Dec 2016ACL 2017 7arXiv:1612.01627archive 2025-07-28

Yu Wu, Wei Wu, Chen Xing, Ming Zhou, Zhoujun Li

We study response selection for multi-turn conversation in retrieval-based chatbots. Existing work either concatenates utterances in context or matches a response with a highly abstract context vector finally, which may lose relationships among utterances or important contextual information. We propose a sequential matching network (SMN) to address both problems. SMN first matches a response with each utterance in the context on multiple levels of granularity, and distills important matching information from each pair as a vector with convolution and pooling operations. The vectors are then accumulated in a chronological order through a recurrent neural network (RNN) which models relationships among utterances. The final matching score is calculated with the hidden states of the RNN. An empirical study on two public data sets shows that SMN can significantly outperform state-of-the-art methods for response selection in multi-turn conversation.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (MarkWuNLP/MultiTurnResponseSelection) was not harvested; the 3 samples below come from 1 community repository.

Syntology 3 code samples harvested from 1 repository linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 3 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

MarkWuNLP/MultiTurnResponseSelection officialmentioned in papertfSyntology: not harvested report
xiaobaicxy/SMN_Multi_Turn_Response_Selection_Pytorch mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
yangliuy/NeuralResponseRanking mentioned on GitHubtfMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified 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

3 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran

Licence: 0 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from yangliuy/NeuralResponseRanking. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

yangliuy/NeuralResponseRanking community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
rank_crossentropy_loss matchzoo/losses/rank_losses.py ran MIT (permissive) · bcfc9e8b905d3ef1 · report fixture: signature kwargs:dict/0/? · returned function · level recorded 2026-09-26
rank_hinge_loss matchzoo/losses/rank_losses.py ran MIT (permissive) · ddc9d8a2cabd27e1 · report fixture: signature kwargs:dict/0/? · returned function · level recorded 2026-09-26
serialize in 19 papers matchzoo/losses/rank_losses.py ran MIT (permissive) · 3d063b0c90233541 · report fixture: signature rank_loss:callable/0/? · returned str · level recorded 2026-09-26

Tasks

Conversational Response SelectionRetrieval

Datasets

Introduced by this paper, per the archive.

DoubanDouban Conversation Corpus

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Conversational Response Selection Douban SMN MAP 0.529 #16 of 16 Archive leaderboard report
Conversational Response Selection Douban SMN MRR 0.569 #16 of 16 Archive leaderboard report
Conversational Response Selection Douban SMN P@1 0.397 #16 of 16 Archive leaderboard report
Conversational Response Selection Douban SMN R10@1 0.233 #16 of 16 Archive leaderboard report
Conversational Response Selection Douban SMN R10@2 0.396 #16 of 16 Archive leaderboard report
Conversational Response Selection Douban SMN R10@5 0.724 #16 of 16 Archive leaderboard report
Conversational Response Selection E-commerce SMN R10@1 0.453 #15 of 15 Archive leaderboard report
Conversational Response Selection E-commerce SMN R10@2 0.654 #15 of 15 Archive leaderboard report
Conversational Response Selection E-commerce SMN R10@5 0.886 #15 of 15 Archive leaderboard report
Conversational Response Selection RRS SMN MAP 0.487 #7 of 7 Archive leaderboard report
Conversational Response Selection RRS SMN MRR 0.501 #7 of 7 Archive leaderboard report
Conversational Response Selection RRS SMN P@1 0.309 #7 of 7 Archive leaderboard report
Conversational Response Selection RRS SMN R10@1 0.281 #7 of 7 Archive leaderboard report
Conversational Response Selection RRS SMN R10@2 0.442 #7 of 7 Archive leaderboard report
Conversational Response Selection RRS SMN R10@5 0.723 #7 of 7 Archive leaderboard report
Conversational Response Selection Ubuntu Dialogue (v1, Ranking) SMN R10@1 0.726 #22 of 25 Archive leaderboard report
Conversational Response Selection Ubuntu Dialogue (v1, Ranking) SMN R10@2 0.822 #22 of 25 Archive leaderboard report
Conversational Response Selection Ubuntu Dialogue (v1, Ranking) SMN R10@5 0.960 #22 of 25 Archive leaderboard report
Conversational Response Selection Ubuntu Dialogue (v1, Ranking) SMN R2@1 0.926 #22 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.

Methods

Convolution

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