Enhancing and Combining Sequential and Tree LSTM for Natural Language Inference

By Qian Chen, Xiao-Dan Zhu, Zhenhua Ling, Si Wei, Hui Jiang. 2016

130 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

Structured Attention Networks (2017, background): “3 Enhanced BiLSTM Inference Model (Chen et al., 2016) 87 .”
Learned in Translation: Contextualized Word Vectors (2017, neutral): “…87.3 bmLSTM [Radford et al., 2017] 92.9 re-read LSTM [Sha et al., 2016] 87.5 TRNN [Dieng et al., 2016] 93.8 btree-LSTM [Paria et al., 2016] 87.6 oh-LSTM [Johnson and Zhang, 2016] 94.1 600D ESIM [Chen et al., 2016] 88.0 Virtual [Miyato et al., 2017] 94.1 BCN+Char+CoVe (Ours) 88.1 Test Performance.”
SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation (2017, background): “matching n-grams, summarization and MT metrics (BLEU, WER, PER, ROUGE); a RNN and recurrent convolutional neural networks (RCNN) over word alignments; and a BiLSTM that is state-ofthe-art for textual entailment (Chen et al., 2016).”
Probing Neural Network Comprehension of Natural Language Arguments (2019, methodology): “…work on ARCT (Choi and Lee, 2018; Zhao et al., 2018; Niven and Kao, 2018) involved transfer learning from Natural Language Inference (NLI) datasets (Bowman et al., 2015; Williams et al., 2017), and utilized effective NLI models such as ESIM (Chen et al., 2016) and InferSent (Conneau et al., 2017).”
CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge (2019, methodology): “Average pre-trained embeddings and softmax are used to train the model. e ESIM We use ESIM, a strong NLI model (Chen et al., 2016).”
Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering (2020, background): “While neural models have proven effective at learning deep semantic matching between text pairs (Bowman et al., 2015; Parikh et al., 2016; Chen et al., 2016; Devlin et al., 2019), such matching usually requires ﬁne-grained token-level attention matching, suggesting that we need to store all the…”
e-SNLI: Natural Language Inference with Natural Language Explanations (2018, background): “Glockner et al. show that models achieving high accuracies on SNLI, such as [21, 22, 6], show dramatically reduced performance on this simpler dataset, while the model of Chen et al. [5] is more robust due to incorporating exter-nal knowledge.”
A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks (2016, methodology): “The parsers are used to improve higher-level tasks, such as natural language inference (Chen et al., 2016) and machine translation (Eriguchi et al., 2016).”
FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension (2017, methodology): “For this component, we follow the approach in (Chen et al., 2017a) First, a feature vector em i is created for each word in C to indicate whether the word occurs in the question Q .”
Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering (2017, methodology): “In this paper, we introduce syntactic information to encode questions with a speciﬁc form of recursive neural networks [Zhu et al., 2015, Tai et al., 2015, Chen et al., 2016, Socher et al., 2011].”
UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification (2018, methodology): “Originally developed for the SNLI task (Bowman et al., 2015) of determining entailment between two statements, the ESIM (Enhanced Sequential Inference Model) (Chen et al., 2016) creates a rich representation of statement-pairs.”
Bilateral Multi-Perspective Matching for Natural Language Sentences (2017, methodology): “…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 [Munkhdalai and Yu, 2016] 87.3 [Sha et al. , 2016] 87.5 [Chen et al. , 2016] tion (Eq.”
Trimming and Improving Skip-thought Vectors (2017, methodology): “While [8] proposed to concatenate the outputs from an average pooling function and a max pooling function, which both run over all time steps, to serve as a sentence representation, and showed a performance boost on the SNLI dataset.”
Dynamic Integration of Background Knowledge in Neural NLU Systems (2017, methodology): “We hypothesize that the attention mechanisms within ESIM jointly with powerful, pre-trained word representations allow for the recovery of some important lexical relations when trained on a large dataset.”
MITRE at SemEval-2017 Task 1: Simple Semantic Similarity (2017, methodology): “We recreated the neural model described in Chen et al. (2016) which reports state-of-the-art performance on the task of ﬁnding entailment in the SNLI corpus.”
A Review of Standard Text Classification Practices for Multi-label Toxicity Identification of Online Content (2018, background): “Both bi-LSTM (Chen et al., 2016) and bi-GRU (Chung et al., 2015) architectures are shown to perform well in sentence representation.”
Dynamic Task Prioritization for Multitask Learning (2018, methodology): “In the work by Søgaard and Goldberg [67], they developed a model with part-of-speech tags supervised at lower layers while higher-level language tasks such as language inference [68] and machine translation [69] were supervised at later layers.”