paper-with-me

홈 › Papers

Knowledge Enhanced Attention for Robust Natural Language Inference

2019-08-31 · Alexander Hanbo Li, Abhinav Sethy

Neural network models have been very successful at achieving high accuracy on natural language inference (NLI) tasks. However, as demonstrated in recent literature, when tested on some simple adversarial examples, most of the models suffer a significant drop in performance. This raises the concern about the robustness of NLI models. In this paper, we propose to make NLI models robust by incorporating external knowledge to the attention mechanism using a simple transformation. We apply the new attention to two popular types of NLI models: one is Transformer encoder, and the other is a decomposable model, and show that our method can significantly improve their robustness. Moreover, when combined with BERT pretraining, our method achieves the human-level performance on the adversarial SNLI data set.

📄 PDF Abstract BibTeX arXiv:1909.00102

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language Inference

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

ERNIE: Enhanced Representation through Knowledge Integration

2019-04-19 · Yu Sun, Shuohuan Wang, Yukun Li, Shikun Feng 외

We present a novel language representation model enhanced by knowledge called ERNIE (Enhanced Representation through kNowledge IntEgration). Inspired by the masking strategy of BERT, ERNIE is designed to learn language r…

Chinese Named Entity RecognitionChinese Sentence Pair ClassificationChinese Sentiment AnalysisCloze Test+7

Knowledge-Enhanced Natural Language Inference Based on Knowledge Graphs

2020-12-01 · COLING 2020 8 · Zikang Wang, Linjing Li, Daniel Zeng

Natural Language Inference (NLI) is a vital task in natural language processing. It aims to identify the logical relationship between two sentences. Most of the existing approaches make such inference based on semantic k…

Knowledge GraphsNatural Language InferenceRelation

Neural Natural Language Inference Models Enhanced with External Knowledge

2017-11-12 · ACL 2018 7 · Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Diana Inkpen 외

Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which …

Natural Language Inference

ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference

2021-08-03 · Amit Gajbhiye, Noura Al Moubayed, Steven Bradley

Neural language representation models such as BERT, pre-trained on large-scale unstructured corpora lack explicit grounding to real-world commonsense knowledge and are often unable to remember facts required for reasonin…

Knowledge GraphsNatural Language Inference

Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference

2019-04-27 · Tianda Li, Xiaodan Zhu, Quan Liu, Qian Chen 외

Natural language inference (NLI) is among the most challenging tasks in natural language understanding. Recent work on unsupervised pretraining that leverages unsupervised signals such as language-model and sentence pred…

Language ModelingLanguage ModellingNatural Language InferenceNatural Language Understanding+1