Papers › Improved Sentence Modeling using Suffix Bidirectional LSTM

Improved Sentence Modeling using Suffix Bidirectional LSTM

18 May 2018arXiv:1805.07340archive 2025-07-28

Siddhartha Brahma

Recurrent neural networks have become ubiquitous in computing representations of sequential data, especially textual data in natural language processing. In particular, Bidirectional LSTMs are at the heart of several neural models achieving state-of-the-art performance in a wide variety of tasks in NLP. However, BiLSTMs are known to suffer from sequential bias - the contextual representation of a token is heavily influenced by tokens close to it in a sentence. We propose a general and effective improvement to the BiLSTM model which encodes each suffix and prefix of a sequence of tokens in both forward and reverse directions. We call our model Suffix Bidirectional LSTM or SuBiLSTM. This introduces an alternate bias that favors long range dependencies. We apply SuBiLSTMs to several tasks that require sentence modeling. We demonstrate that using SuBiLSTM instead of a BiLSTM in existing models leads to improvements in performance in learning general sentence representations, text classification, textual entailment and paraphrase detection. Using SuBiLSTM we achieve new state-of-the-art results for fine-grained sentiment classification and question classification.

Paper PDF

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

Classification General Classification Natural Language Inference Sentence Sentiment Analysis Sentiment Classification Text Classification text-classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Sentiment Analysis	CR	SuBiLSTM-Tied	Accuracy	86.5	#7 of 9	Archive leaderboard	report
Sentiment Analysis	MR	SuBiLSTM-Tied	Accuracy	81.6	#8 of 19	Archive leaderboard	report
Sentiment Analysis	SST-2 Binary classification	Suffix BiLSTM	Accuracy	91.2	#57 of 87	Archive leaderboard	report
Sentiment Analysis	SST-5 Fine-grained classification	BCN+Suffix BiLSTM-Tied+CoVe	Accuracy	56.2	#5 of 31	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

BiLSTM LSTM Sigmoid Activation Tanh 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