A Compare-Propagate Architecture with Alignment Factorization for Natural Language Inference

By Yi Tay, Anh Tuan Luu, Siu Cheung Hui. 2017

71 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

The Natural Language Decathlon: Multitask Learning as Question Answering (2018, methodology): “The most successful approaches make use of attentional models that match and align words in the premise to those in the hypothesis (Tay et al., 2017; Peters et al., 2018; Ghaeini et al., 2018; Chen et al., 2017; Wang et al., 2017b; McCann et al., 2017), but recent non-attentional models designed to ”
Enhancing Sentence Embedding with Generalized Pooling (2018, methodology): “0D BiLSTM gated-pooling (Chen et al., 2017b) 85.5 300D DiSAN (Shen et al., 2017) 85.6 300D Gumbel TreeLSTM (Choi et al., 2017) 85.6 600D Residual stacked BiLSTM (Nie and Bansal, 2017) 85.7 300D CAFE (Tay et al., 2018) 85.9 600D Gumbel TreeLSTM (Choi et al., 2017) 86.0 1200D Residual stacked BiLSTM (”
Interpreting Recurrent and Attention-Based Neural Models: a Case Study on Natural Language Inference (2018, methodology): “Many of the top performing NLI models (Ghaeini et al., 2018b; Tay et al., 2018; Peters et al., 2018; McCann et al., 2017; Gong et al., 2017; Wang et al., 2017; Chen et al., 2017), are variants of the ESIM model (Chen et al.”
Densely Connected Attention Propagation for Reading Comprehension (2018, methodology): “Finally, we note that the BAC module takes inspiration from the main body of our CAFE model [Tay et al., 2017] for entailment classiﬁcation.”
Multi-Pointer Co-Attention Networks for Recommendation (2018, unknown): “ly related to the problem domain of sequence pair modeling. A wide spectrum of models have been proposed for modeling relationships between two sequences, e.g., questionanswer [6], premise-hypothesis [22, 24, 28] which are very similar to the user-item modeling problem at hand. In these fields, lear”
Latent Relational Metric Learning via Memory-based Attention for Collaborative Ranking (2017, background): “ecifically,LRML uses a neural attention mechanism over an augmented memory module to generate latent vectors. Neural attention mechanisms are popular in the fields of computer vision [20, 39] and NLP [16, 23, 26, 31, 34] and are known to improve performance and interpretability of deep learning mode”
Neural Natural Language Inference Models Enhanced with External Knowledge (2017, unknown): “(Parikh et al., 2016) 86.8 NTI (Yu and Munkhdalai, 2017b) 87.3 Re-read LSTM (Sha et al., 2016) 87.5 BiMPM (Wang et al., 2017) 87.5 DIIN (Gong et al., 2017) 88.0 BCN + CoVe (McCann et al., 2017) 88.1 CAFE (Tay et al., 2018) 88.5 ESIM (Chen et al., 2017a) 88.0 KIM (This paper) 88.6 Table 2: Accuracies”
Improving Language Understanding by Generative Pre-Training (2018, background): “Although there has been a lot of recent interest [58, 35, 44], the task remains challenging due to the presence of a wide variety of phenomena like lexical entailment, coreference, and lexical and syntactic ambiguity.”