paper-with-me

홈 › Papers

Towards Debiasing Sentence Representations

2020-07-16 · ACL 2020 6 · Paul Pu Liang, Irene Mengze Li, Emily Zheng, Yao Chong Lim, Ruslan Salakhutdinov, Louis-Philippe Morency

As natural language processing methods are increasingly deployed in real-world scenarios such as healthcare, legal systems, and social science, it becomes necessary to recognize the role they potentially play in shaping social biases and stereotypes. Previous work has revealed the presence of social biases in widely used word embeddings involving gender, race, religion, and other social constructs. While some methods were proposed to debias these word-level embeddings, there is a need to perform debiasing at the sentence-level given the recent shift towards new contextualized sentence representations such as ELMo and BERT. In this paper, we investigate the presence of social biases in sentence-level representations and propose a new method, Sent-Debias, to reduce these biases. We show that Sent-Debias is effective in removing biases, and at the same time, preserves performance on sentence-level downstream tasks such as sentiment analysis, linguistic acceptability, and natural language understanding. We hope that our work will inspire future research on characterizing and removing social biases from widely adopted sentence representations for fairer NLP.

📄 PDF Abstract BibTeX arXiv:2007.08100

Code (1)

pliang279/sent_debias 공식 구현 pytorch

Tasks

Linguistic AcceptabilityNatural Language UnderstandingSentenceSentiment AnalysisWord Embeddings

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Tanh Activation 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Adam 설명 없음
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…
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.

Similar Papers 제목 키워드 기반

FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders

2021-03-11 · ICLR 2021 1 · Pengyu Cheng, Weituo Hao, Siyang Yuan, Shijing Si 외

Pretrained text encoders, such as BERT, have been applied increasingly in various natural language processing (NLP) tasks, and have recently demonstrated significant performance gains. However, recent studies have demons…

Contrastive LearningFairnessSentence

A Simple yet Effective Self-Debiasing Framework for Transformer Models

2023-06-02 · Xiaoyue Wang, Lijie Wang, Xin Liu, Suhang Wu 외

Current Transformer-based natural language understanding (NLU) models heavily rely on dataset biases, while failing to handle real-world out-of-distribution (OOD) instances. Many methods have been proposed to deal with t…

Natural Language UnderstandingSentence

Towards Debiasing Temporal Sentence Grounding in Video

2021-11-08 · Hao Zhang, Aixin Sun, Wei Jing, Joey Tianyi Zhou

The temporal sentence grounding in video (TSGV) task is to locate a temporal moment from an untrimmed video, to match a language query, i.e., a sentence. Without considering bias in moment annotations (e.g., start and en…

SentenceTemporal Sentence Grounding

Projective Methods for Mitigating Gender Bias in Pre-trained Language Models

2024-03-27 · Hillary Dawkins, Isar Nejadgholi, Daniel Gillis, Judi McCuaig

Mitigation of gender bias in NLP has a long history tied to debiasing static word embeddings. More recently, attention has shifted to debiasing pre-trained language models. We study to what extent the simplest projective…

Language ModelingLanguage ModellingSentenceWord Embeddings

Debiasing Pre-trained Contextualised Embeddings

2021-01-23 · EACL 2021 2 · Masahiro Kaneko, Danushka Bollegala

In comparison to the numerous debiasing methods proposed for the static non-contextualised word embeddings, the discriminative biases in contextualised embeddings have received relatively little attention. We propose a f…

SentenceWord Embeddings