# Enhanced LSTM for Natural Language Inference

arXiv: https://arxiv.org/abs/1609.06038 · HTML: https://mlsanity.com/paper/1609.06038/

## Key facts

- Cited by 200 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2016.

## Built on by (most cited first, 30 of 200)

- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations](https://mlsanity.com/paper/2106.01093/) (2021)
- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [A Survey on Stance Detection for Mis- and Disinformation Identification](https://mlsanity.com/paper/2103.00242/) (2021)
- [CoSQA: 20,000+ Web Queries for Code Search and Question Answering](https://mlsanity.com/paper/2105.13239/) (2021)
- [DocNLI: A Large-scale Dataset for Document-level Natural Language Inference](https://mlsanity.com/paper/2106.09449/) (2021)
- [Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics](https://mlsanity.com/paper/2110.01518/) (2021)
- [ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning](https://mlsanity.com/paper/2104.04697/) (2021)
- [Coreference Resolution without Span Representations](https://mlsanity.com/paper/2101.00434/) (2021)
- [Tracing Text Provenance via Context-Aware Lexical Substitution](https://mlsanity.com/paper/2112.07873/) (2021)
- [BERT & Family Eat Word Salad: Experiments with Text Understanding](https://mlsanity.com/paper/2101.03453/) (2021)
- [Paradigm Shift in Natural Language Processing](https://mlsanity.com/paper/2109.12575/) (2021)
- [Automatic Text Evaluation through the Lens of Wasserstein Barycenters](https://mlsanity.com/paper/2108.12463/) (2021)
- [Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information](https://mlsanity.com/paper/2104.09580/) (2021)
- [A Survey on Out-of-Distribution Detection in NLP](https://mlsanity.com/paper/2305.03236/) (2023)
- [Revisiting Large Language Models as Zero-shot Relation Extractors](https://mlsanity.com/paper/2310.05028/) (2023)
- [Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods](https://mlsanity.com/paper/2203.05227/) (2022)
- [Pushing the Limits of ChatGPT on NLP Tasks](https://mlsanity.com/paper/2306.09719/) (2023)
- [NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning](https://mlsanity.com/paper/2105.14167/) (2021)
- [Bayesian Attention Belief Networks](https://mlsanity.com/paper/2106.05251/) (2021)
- [Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks](https://mlsanity.com/paper/2102.10934/) (2021)
- [QuantumFed: A Federated Learning Framework for Collaborative Quantum Training](https://mlsanity.com/paper/2106.09109/) (2021)
- [DABERT: Dual Attention Enhanced BERT for Semantic Matching](https://mlsanity.com/paper/2210.03454/) (2022)
- [Dual Path Modeling for Semantic Matching by Perceiving Subtle Conflicts](https://mlsanity.com/paper/2302.12530/) (2023)
- [SPECTRA: Sparse Structured Text Rationalization](https://mlsanity.com/paper/2109.04552/) (2021)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [On the Calibration of Massively Multilingual Language Models](https://mlsanity.com/paper/2210.12265/) (2022)
- [Natural Language Decompositions of Implicit Content Enable Better Text Representations](https://mlsanity.com/paper/2305.14583/) (2023)
- [Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System](https://mlsanity.com/paper/2109.11292/) (2021)
- [Hierarchical Cross-Modality Semantic Correlation Learning Model for Multimodal Summarization](https://mlsanity.com/paper/2112.12072/) (2021)

## Abstract (arXiv)

Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is very challenging. With the availability of large annotated data (Bowman et al., 2015), it has recently become feasible to train neural network based inference models, which have shown to be very effective. In this paper, we present a new state-of-the-art result, achieving the accuracy of 88.6% on the Stanford Natural Language Inference Dataset. Unlike the previous top models that use very complicated network architectures, we first demonstrate that carefully designing sequential inference models based on chain LSTMs can outperform all previous models. Based on this, we further show that by explicitly considering recursive architectures in both local inference modeling and inference composition, we achieve additional improvement. Particularly, incorporating syntactic parsing information contributes to our best result---it further improves the performance even when added to the already very strong model.