Author name cluster

Zekun Yang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

AAAI Conference 2020 Conference Paper

A Causal Inference Method for Reducing Gender Bias in Word Embedding Relations

Zekun Yang
Juan Feng

Word embedding has become essential for natural language processing as it boosts empirical performances of various tasks. However, recent research discovers that gender bias is incorporated in neural word embeddings, and downstream tasks that rely on these biased word vectors also produce gender-biased results. While some word-embedding genderdebiasing methods have been developed, these methods mainly focus on reducing gender bias associated with gender direction and fail to reduce the gender bias presented in word embedding relations. In this paper, we design a causal and simple approach for mitigating gender bias in word vector relation by utilizing the statistical dependency between genderdeﬁnition word embeddings and gender-biased word embeddings. Our method attains state-of-the-art results on genderdebiasing tasks, lexical- and sentence-level evaluation tasks, and downstream coreference resolution tasks. .

PDF Details

AAAI Conference 2020 Conference Paper

Causally Denoise Word Embeddings Using Half-Sibling Regression

Zekun Yang
Tianlin Liu

Distributional representations of words, also known as word vectors, have become crucial for modern natural language processing tasks due to their wide applications. Recently, a growing body of word vector postprocessing algorithm has emerged, aiming to render off-the-shelf word vectors even stronger. In line with these investigations, we introduce a novel word vector postprocessing scheme under a causal inference framework. Concretely, the postprocessing pipeline is realized by Half-Sibling Regression (HSR), which allows us to identify and remove confounding noise contained in word vectors. Compared to previous work, our proposed method has the advantages of interpretability and transparency due to its causal inference grounding. Evaluated on a battery of standard lexical-level evaluation tasks and downstream sentiment analysis tasks, our method reaches state-of-the-art performance.

PDF Details