Papers › Disconnected Recurrent Neural Networks for Text Categorization
Disconnected Recurrent Neural Networks for Text Categorization
Baoxin Wang
Recurrent neural network (RNN) has achieved remarkable performance in text categorization. RNN can model the entire sequence and capture long-term dependencies, but it does not do well in extracting key patterns. In contrast, convolutional neural network (CNN) is good at extracting local and position-invariant features. In this paper, we present a novel model named disconnected recurrent neural network (DRNN), which incorporates position-invariance into RNN. By limiting the distance of information flow in RNN, the hidden state at each time step is restricted to represent words near the current position. The proposed model makes great improvements over RNN and CNN models and achieves the best performance on several benchmark datasets for text categorization.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Sentiment Analysis | Amazon Review Full | DRNN | Accuracy | 64.43 | #3 of 9 | Archive leaderboard | report |
| Sentiment Analysis | Amazon Review Polarity | DRNN | Accuracy | 96.49 | #4 of 9 | Archive leaderboard | report |
| Sentiment Analysis | Yelp Binary classification | DRNN | Error | 2.73 | #9 of 20 | Archive leaderboard | report |
| Sentiment Analysis | Yelp Fine-grained classification | DRNN | Error | 30.85 | #7 of 17 | Archive leaderboard | report |
| Text Classification | AG News | DRNN | Error | 5.53 | #5 of 24 | Archive leaderboard | report |
| Text Classification | DBpedia | DRNN | Error | 0.81 | #8 of 21 | Archive leaderboard | report |
| Text Classification | Yahoo! Answers | DRNN | Accuracy | 76.26 | #2 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.
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