Papers › Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings

Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings

7 Feb 2016arXiv:1602.02373archive 2025-07-28

Rie Johnson, Tong Zhang

One-hot CNN (convolutional neural network) has been shown to be effective for text categorization (Johnson & Zhang, 2015). We view it as a special case of a general framework which jointly trains a linear model with a non-linear feature generator consisting of `text region embedding + pooling'. Under this framework, we explore a more sophisticated region embedding method using Long Short-Term Memory (LSTM). LSTM can embed text regions of variable (and possibly large) sizes, whereas the region size needs to be fixed in a CNN. We seek effective and efficient use of LSTM for this purpose in the supervised and semi-supervised settings. The best results were obtained by combining region embeddings in the form of LSTM and convolution layers trained on unlabeled data. The results indicate that on this task, embeddings of text regions, which can convey complex concepts, are more useful than embeddings of single words in isolation. We report performances exceeding the previous best results on four benchmark datasets.

PaperPDF

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

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

Sentiment AnalysisText CategorizationText Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sentiment Analysis IMDb oh-LSTM Accuracy 94.1 #23 of 49 Archive leaderboard report
Sentiment Analysis Yelp Binary classification CNN Error 2.9 #10 of 20 Archive leaderboard report
Sentiment Analysis Yelp Fine-grained classification CNN Error 32.39 #9 of 17 Archive leaderboard report
Text Classification AG News CNN Error 6.57 #8 of 24 Archive leaderboard report
Text Classification DBpedia CNN Error 0.84 #9 of 21 Archive leaderboard report
Text Classification RCV1 oh-CNN + two LSTM tv-embed. Accuracy 92.85 #1 of 4 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

ConvolutionLSTMSigmoid ActivationTanh Activation

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