Papers › Abstractive Text Classification Using Sequence-to-convolution Neural Networks

Abstractive Text Classification Using Sequence-to-convolution Neural Networks

20 May 2018arXiv:1805.07745archive 2025-07-28

Taehoon Kim, Jihoon Yang

We propose a new deep neural network model and its training scheme for text classification. Our model Sequence-to-convolution Neural Networks(Seq2CNN) consists of two blocks: Sequential Block that summarizes input texts and Convolution Block that receives summary of input and classifies it to a label. Seq2CNN is trained end-to-end to classify various-length texts without preprocessing inputs into fixed length. We also present Gradual Weight Shift(GWS) method that stabilizes training. GWS is applied to our model's loss function. We compared our model with word-based TextCNN trained with different data preprocessing methods. We obtained significant improvement in classification accuracy over word-based TextCNN without any ensemble or data augmentation.

PaperPDFCode

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

Code

tgisaturday/Seq2CNN 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

ClassificationData AugmentationGeneral ClassificationText Classificationtext-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Classification AG News Seq2CNN with GWS(50) Error 9.64 #20 of 24 Archive leaderboard report
Text Classification DBpedia Seq2CNN(50) Error 2.77 #21 of 21 Archive leaderboard report
Text Classification Yahoo! Answers Seq2CNN(50) Accuracy 55.39 #10 of 10 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