paper-with-me

Papers

Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks?

2020-12-30 · Findings (ACL) 2021 8 · Thang M. Pham, Trung Bui, Long Mai, Anh Nguyen

Do state-of-the-art natural language understanding models care about word order - one of the most important characteristics of a sequence? Not always! We found 75% to 90% of the correct predictions of BERT-based classifiers, trained on many GLUE tasks, remain constant after input words are randomly shuffled. Despite BERT embeddings are famously contextual, the contribution of each individual word to downstream tasks is almost unchanged even after the word's context is shuffled. BERT-based models are able to exploit superficial cues (e.g. the sentiment of keywords in sentiment analysis; or the word-wise similarity between sequence-pair inputs in natural language inference) to make correct decisions when tokens are arranged in random orders. Encouraging classifiers to capture word order information improves the performance on most GLUE tasks, SQuAD 2.0 and out-of-samples. Our work suggests that many GLUE tasks are not challenging machines to understand the meaning of a sentence.

📄 PDF Abstract BibTeX arXiv:2012.15180

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language InferenceNatural Language UnderstandingSentenceSentiment Analysis

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
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.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study

2021-06-01 · NAACL 2021 4 · Chongyang Tao, Shen Gao, Juntao Li, Yansong Feng 외

Sequential information, a.k.a., orders, is assumed to be essential for processing a sequence with recurrent neural network or convolutional neural network based encoders. However, is it possible to encode natural languag…

Sentence

Detecting Media Bias in News Articles using Gaussian Bias Distributions

2020-10-20 · Findings of the Association for Computational Linguistics 2020 · Wei-Fan Chen, Khalid Al-Khatib, Benno Stein, Henning Wachsmuth

Media plays an important role in shaping public opinion. Biased media can influence people in undesirable directions and hence should be unmasked as such. We observe that featurebased and neural text classification appro…

ArticlesBias DetectionSentencetext-classification+1

Depth-Adaptive Graph Recurrent Network for Text Classification

2020-02-29 · Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu 외

The Sentence-State LSTM (S-LSTM) is a powerful and high efficient graph recurrent network, which views words as nodes and performs layer-wise recurrent steps between them simultaneously. Despite its successes on text rep…

ClassificationGeneral ClassificationSentencetext-classification+1

Generalized Optimal Linear Orders

2021-08-13 · Rishi Bommasani

The sequential structure of language, and the order of words in a sentence specifically, plays a central role in human language processing. Consequently, in designing computational models of language, the de facto approa…

Sentence

Sentence Level Recurrent Topic Model: Letting Topics Speak for Themselves

2016-04-07 · Fei Tian, Bin Gao, Di He, Tie-Yan Liu

We propose Sentence Level Recurrent Topic Model (SLRTM), a new topic model that assumes the generation of each word within a sentence to depend on both the topic of the sentence and the whole history of its preceding wor…

SentenceShort-Text ConversationTopic Models