paper-with-me

Papers

How effective is BERT without word ordering? Implications for language understanding and data privacy

2021-08-01 · ACL 2021 5 · Jack Hessel, Alexandra Schofield

Ordered word sequences contain the rich structures that define language. However, it{'}s often not clear if or how modern pretrained language models utilize these structures. We show that the token representations and self-attention activations within BERT are surprisingly resilient to shuffling the order of input tokens, and that for several GLUE language understanding tasks, shuffling only minimally degrades performance, e.g., by 4{\%} for QNLI. While bleak from the perspective of language understanding, our results have positive implications for cases where copyright or ethics necessitates the consideration of bag-of-words data (vs. full documents). We simulate such a scenario for three sensitive classification tasks, demonstrating minimal performance degradation vs. releasing full language sequences.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

EthicsQNLI

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Word Reordering for Zero-shot Cross-lingual Structured Prediction

2021-11-01 · EMNLP 2021 11 · Tao Ji, Yong Jiang, Tao Wang, Zhongqiang Huang 외

Adapting word order from one language to another is a key problem in cross-lingual structured prediction. Current sentence encoders (e.g., RNN, Transformer with position embeddings) are usually word order sensitive. Even…

Dependency ParsingMorphological TaggingPOSPosition+4

Word Ordering Without Syntax

2016-04-28 · EMNLP 2016 11 · Allen Schmaltz, Alexander M. Rush, Stuart M. Shieber

Recent work on word ordering has argued that syntactic structure is important, or even required, for effectively recovering the order of a sentence. We find that, in fact, an n-gram language model with a simple heuristic…

Language ModelingLanguage ModellingSentence

BERT-enhanced Relational Sentence Ordering Network

2020-11-01 · EMNLP 2020 11 · Baiyun Cui, Yingming Li, Zhongfei Zhang

In this paper, we introduce a novel BERT-enhanced Relational Sentence Ordering Network (referred to as BRSON) by leveraging BERT for capturing better dependency relationship among sentences to enhance the coherence model…

DecoderSentenceSentence Ordering

Word Alignment-Based Reordering of Source Chunks in PB-SMT

2014-05-01 · LREC 2014 5 · Santanu Pal, Sudip Kumar Naskar, B, Sivaji yopadhyay

Reordering poses a big challenge in statistical machine translation between distant language pairs. The paper presents how reordering between distant language pairs can be handled efficiently in phrase-based statistical …

Machine TranslationTranslationWord Alignment

Hilbert curves for efficient exploratory landscape analysis neighbourhood sampling

2024-08-01 · Johannes J. Pienaar, Anna S. Bosman, Katherine M. Malan

Landscape analysis aims to characterise optimisation problems based on their objective (or fitness) function landscape properties. The problem search space is typically sampled, and various landscape features are estimat…