Papers › Rethinking Attribute Representation and Injection for Sentiment Classification

Rethinking Attribute Representation and Injection for Sentiment Classification

26 Aug 2019IJCNLP 2019 11arXiv:1908.09590archive 2025-07-28

Reinald Kim Amplayo

Text attributes, such as user and product information in product reviews, have been used to improve the performance of sentiment classification models. The de facto standard method is to incorporate them as additional biases in the attention mechanism, and more performance gains are achieved by extending the model architecture. In this paper, we show that the above method is the least effective way to represent and inject attributes. To demonstrate this hypothesis, unlike previous models with complicated architectures, we limit our base model to a simple BiLSTM with attention classifier, and instead focus on how and where the attributes should be incorporated in the model. We propose to represent attributes as chunk-wise importance weight matrices and consider four locations in the model (i.e., embedding, encoding, attention, classifier) to inject attributes. Experiments show that our proposed method achieves significant improvements over the standard approach and that attention mechanism is the worst location to inject attributes, contradicting prior work. We also outperform the state-of-the-art despite our use of a simple base model. Finally, we show that these representations transfer well to other tasks. Model implementation and datasets are released here: https://github.com/rktamplayo/CHIM.

PaperPDFConference PDFCode

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

Code

rktamplayo/CHIM officialmentioned in paperpytorch 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

AttributeClassificationGeneral ClassificationSentiment AnalysisSentiment Analysis (Product + User)Sentiment Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sentiment Analysis User and product information BiLSTM+CHIM IMDB (Acc) 56.4 #2 of 10 Archive leaderboard report
Sentiment Analysis User and product information BiLSTM+CHIM Yelp 2013 (Acc) 67.8 #2 of 10 Archive leaderboard report
Sentiment Analysis User and product information BiLSTM+CHIM Yelp 2014 (Acc) 69.2 #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.

Methods

BiLSTMLSTMSigmoid 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