# Shortcut-Stacked Sentence Encoders for Multi-Domain Inference

arXiv: https://arxiv.org/abs/1708.02312 · HTML: https://mlsanity.com/paper/1708.02312/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2017.

## Built on by (most cited first, 7 of 7)

- [Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning](https://mlsanity.com/paper/2104.08676/) (2021)
- [Paraphrase Identification with Deep Learning: A Review of Datasets and Methods](https://mlsanity.com/paper/2212.06933/) (2022)
- [LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching](https://mlsanity.com/paper/2108.02915/) (2021)
- [Improving the Natural Language Inference robustness to hard dataset by data augmentation and preprocessing](https://mlsanity.com/paper/2412.07108/) (2024)
- [Contextualized Embeddings based Convolutional Neural Networks for Duplicate Question Identification](https://mlsanity.com/paper/2109.01560/) (2021)
- [Adaptable Text Matching via Meta-Weight Regulator](https://mlsanity.com/paper/2204.12668/) (2022)
- [R-DEIM Net: An Efficient Rationale-Augmented Dual-Expert Interaction Model for Paraphrase Detection](https://mlsanity.com/paper/2609.30100/) (2026)

## Abstract (arXiv)

We present a simple sequential sentence encoder for multi-domain natural language inference. Our encoder is based on stacked bidirectional LSTM-RNNs with shortcut connections and fine-tuning of word embeddings. The overall supervised model uses the above encoder to encode two input sentences into two vectors, and then uses a classifier over the vector combination to label the relationship between these two sentences as that of entailment, contradiction, or neural. Our Shortcut-Stacked sentence encoders achieve strong improvements over existing encoders on matched and mismatched multi-domain natural language inference (top non-ensemble single-model result in the EMNLP RepEval 2017 Shared Task (Nangia et al., 2017)). Moreover, they achieve the new state-of-the-art encoding result on the original SNLI dataset (Bowman et al., 2015).