Papers › Information Aggregation via Dynamic Routing for Sequence Encoding

Information Aggregation via Dynamic Routing for Sequence Encoding

5 Jun 2018COLING 2018 8arXiv:1806.01501archive 2025-07-28

Jingjing Gong, Xipeng Qiu, Shaojing Wang, Xuanjing Huang

While much progress has been made in how to encode a text sequence into a sequence of vectors, less attention has been paid to how to aggregate these preceding vectors (outputs of RNN/CNN) into fixed-size encoding vector. Usually, a simple max or average pooling is used, which is a bottom-up and passive way of aggregation and lack of guidance by task information. In this paper, we propose an aggregation mechanism to obtain a fixed-size encoding with a dynamic routing policy. The dynamic routing policy is dynamically deciding that what and how much information need be transferred from each word to the final encoding of the text sequence. Following the work of Capsule Network, we design two dynamic routing policies to aggregate the outputs of RNN/CNN encoding layer into a final encoding vector. Compared to the other aggregation methods, dynamic routing can refine the messages according to the state of final encoding vector. Experimental results on five text classification tasks show that our method outperforms other aggregating models by a significant margin. Related source code is released on our github page.

PaperPDFConference PDFCode

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

Code

FudanNLP/Capsule4TextClassification officialmentioned in papermentioned on GitHubtf report
michael-wzhu/dynamic_routing_pytorch mentioned on GitHubpytorch 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

Sentiment AnalysisText Classificationtext-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sentiment Analysis IMDb Standard DR-AGG Accuracy 45.1 #48 of 49 Archive leaderboard report
Sentiment Analysis IMDb Reverse DR-AGG Accuracy 44.5 #49 of 49 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification Standard DR-AGG Accuracy 87.6 #71 of 87 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification Reverse DR-AGG Accuracy 87.2 #73 of 87 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

Average PoolingCapsule Network

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