# Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention

arXiv: https://arxiv.org/abs/1605.09090 · HTML: https://mlsanity.com/paper/1605.09090/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2016.

## Built on by (most cited first, 23 of 23)

- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks](https://mlsanity.com/paper/2101.10642/) (2021)
- [Pushing the Limits of ChatGPT on NLP Tasks](https://mlsanity.com/paper/2306.09719/) (2023)
- [Lifelong Learning of Hate Speech Classification on Social Media](https://mlsanity.com/paper/2106.02821/) (2021)
- [Type-aware Embeddings for Multi-Hop Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2205.00782/) (2022)
- [Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction](https://mlsanity.com/paper/2109.02403/) (2021)
- [Comateformer: Combined Attention Transformer for Semantic Sentence Matching](https://mlsanity.com/paper/2412.07220/) (2024)
- [AlignVE: Visual Entailment Recognition Based on Alignment Relations](https://mlsanity.com/paper/2211.08736/) (2022)
- [MIPO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning](https://mlsanity.com/paper/2107.09288/) (2021)
- [Machine Learning in Access Control: A Taxonomy and Survey](https://mlsanity.com/paper/2207.01739/) (2022)
- [LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching](https://mlsanity.com/paper/2108.02915/) (2021)
- [Review of deep learning models for crypto price prediction: implementation and evaluation](https://mlsanity.com/paper/2405.11431/) (2024)
- [Hyperbolic sentence representations for solving Textual Entailment](https://mlsanity.com/paper/2406.15472/) (2024)
- [Domain-guided Machine Learning for Remotely Sensed In-Season Crop Growth Estimation](https://mlsanity.com/paper/2106.13323/) (2021)
- [Compliance Checking with NLI: Privacy Policies vs. Regulations](https://mlsanity.com/paper/2204.01845/) (2022)
- [Bitformer: An efficient Transformer with bitwise operation-based attention for Big Data Analytics at low-cost low-precision devices](https://mlsanity.com/paper/2311.13502/) (2023)
- [Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence Generation](https://mlsanity.com/paper/2503.09094/) (2025)
- [DGA-Net Dynamic Gaussian Attention Network for Sentence Semantic Matching](https://mlsanity.com/paper/2106.04905/) (2021)
- [Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision](https://mlsanity.com/paper/2109.09036/) (2021)
- [Integrating Dependency Tree Into Self-attention for Sentence Representation](https://mlsanity.com/paper/2203.05918/) (2022)
- [CRL+: A Novel Semi-Supervised Deep Active Contrastive Representation Learning-Based Text Classification Model for Insurance Data](https://mlsanity.com/paper/2302.04343/) (2023)
- [Using External knowledge to Enhanced PLM for Semantic Matching](https://mlsanity.com/paper/2505.06605/) (2025)
- [Boosting Neural Language Inference via Cascaded Interactive Reasoning](https://mlsanity.com/paper/2505.06607/) (2025)

## Abstract (arXiv)

In this paper, we proposed a sentence encoding-based model for recognizing text entailment. In our approach, the encoding of sentence is a two-stage process. Firstly, average pooling was used over word-level bidirectional LSTM (biLSTM) to generate a first-stage sentence representation. Secondly, attention mechanism was employed to replace average pooling on the same sentence for better representations. Instead of using target sentence to attend words in source sentence, we utilized the sentence's first-stage representation to attend words appeared in itself, which is called "Inner-Attention" in our paper . Experiments conducted on Stanford Natural Language Inference (SNLI) Corpus has proved the effectiveness of "Inner-Attention" mechanism. With less number of parameters, our model outperformed the existing best sentence encoding-based approach by a large margin.