Modelling Interaction of Sentence Pair with Coupled-LSTMs

By Pengfei Liu, Xipeng Qiu, Yaqian Zhou, Jifan Chen, Xuanjing Huang. 2016

48 citations recorded by the source corpus.

Recently, there is rising interest in modelling the interactions of two sentences with deep neural networks. However, most of the existing methods encode two sequences with separate encoders, in which a sentence is encoded with little or no information from the other sentence. In this paper, we propose a deep architecture to model the strong interaction of sentence pair with two coupled-LSTMs. Specifically, we introduce two coupled ways to model the interdependences of two LSTMs, coupling the local contextualized interactions of two sentences. We then aggregate these interactions and use a dynamic pooling to select the most informative features. Experiments on two very large datasets demonstrate the efficacy of our proposed architecture and its superiority to state-of-the-art methods.

Subfields: Artificial Intelligence, Natural Language Processing, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mohit Bansal
2. Xiao-Dan Zhu
3. Zhenhua Ling
4. Qian Chen
5. Yejin Choi
6. Yoav Goldberg
7. Kyunghyun Cho
8. Jianfeng Gao

In Natural Language Processing

1. Mohit Bansal
2. Xiao-Dan Zhu
3. Qian Chen
4. Zhenhua Ling
5. Yejin Choi
6. Si Wei
7. Thomas Lukasiewicz
8. Oana-Maria Camburu

In Model Architectures

1. Qian Chen
2. Si Wei
3. Xiao-Dan Zhu
4. Zhenhua Ling
5. Phil Blunsom
6. Thomas Lukasiewicz
7. Sujian Li
8. Diana Inkpen

Citations in the corpus

• e-SNLI: Natural Language Inference with Natural Language Explanations (2018, background): “The SNLI dataset [3], containing 570 K data points of human-generated triples (premise, hypothesis, label), has driven the development of a large number of neural network models [25, 21, 22, 6, 19, 5, 7].”
• Performance Impact Caused by Hidden Bias of Training Data for Recognizing Textual Entailment (2018, methodology): “…important, because the SNLI corpus is widely used as training data by many NN models for RTE (Bowman et al., 2015; Rocktäschel et al., 2015; Yin et al., 2016; Mou et al., 2016a; Wang and Jiang, 2016; Liu et al., 2016a; Liu et al., 2016b; Cheng et al., 2016; Parikh et al., 2016; Sha et al., 2016).”
• Bilateral Multi-Perspective Matching for Natural Language Sentences (2017, neutral): “…cosine matching func-Models Accuracy [Bowman et al. , 2015] 77.6 [Vendrov et al. , 2015] 81.4 [Mou et al. , 2015] 82.1 [Rockt¨aschel et al. , 2015] 83.5 [Liu et al. , 2016b] 85.0 [Liu et al. , 2016a] 85.1 [Wang and Jiang, 2015] 86.1 [Cheng et al. , 2016] 86.3 [Parikh et al. , 2016] 86.8…”
• Deep Learning--based Text Classification (2020, unknown): “[121] model the interaction of a sentence pair with two coupled-LSTMs.”
• Reading and Thinking: Re-read LSTM Unit for Textual Entailment Recognition (2016, methodology): “Then, Yin et al. (2015) applied attention mechanic to convolution neural network, Liu et al. (2016a) proposed coupled-LSTM, Vendrov et al. (2015) proposed ordered embedding, Mou et al. (2016) applied Tree-based CNN, Wang and Jiang (2015) proposed matching LSTM, Liu et al. (2016b) applied…”
• Neural Natural Language Inference Models Enhanced with External Knowledge (2017, methodology): “…utilized for sentence encoding, such as LSTM (Bowman et al., 2015), GRU (Ven-drov et al., 2015), CNN (Mou et al., 2016), BiL-STM and its variants (Liu et al., 2016c; Lin et al., 2017; Chen et al., 2017b; Nie and Bansal, 2017), self-attention network (Shen et al., 2017, 2018), and more…”