paper-with-me

홈 › Papers

Learning Bias-reduced Word Embeddings Using Dictionary Definitions

2022-05-01 · Findings (ACL) 2022 5 · Haozhe An, Xiaojiang Liu, Donald Zhang

Pre-trained word embeddings, such as GloVe, have shown undesirable gender, racial, and religious biases. To address this problem, we propose DD-GloVe, a train-time debiasing algorithm to learn word embeddings by leveraging \underline{d}ictionary \underline{d}efinitions. We introduce dictionary-guided loss functions that encourage word embeddings to be similar to their relatively neutral dictionary definition representations. Existing debiasing algorithms typically need a pre-compiled list of seed words to represent the bias direction, along which biased information gets removed. Producing this list involves subjective decisions and it might be difficult to obtain for some types of biases. We automate the process of finding seed words: our algorithm starts from a single pair of initial seed words and automatically finds more words whose definitions display similar attributes traits. We demonstrate the effectiveness of our approach with benchmark evaluations and empirical analyses. Our code is available at https://github.com/haozhe-an/DD-GloVe.

📄 PDF Abstract BibTeX

Code (1)

haozhe-an/dd-glove 공식 구현 pytorch

Tasks

Word Embeddings

Similar Papers 제목 키워드 기반

Def2Vec: Extensible Word Embeddings from Dictionary Definitions

2023-12-16 · ICNLSP 2023 12 · Irene Morazzoni, Vincenzo Scotti, Roberto Tedesco

Def2Vec introduces a novel paradigm for word embeddings, leveraging dictionary definitions to learn semantic representations. By constructing term-document matrices from definitions and applying Latent Semantic Analysis …

Chunkingnamed-entity-recognitionNamed Entity RecognitionNER+5

Dictionary-based Debiasing of Pre-trained Word Embeddings

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

Word embeddings trained on large corpora have shown to encode high levels of unfair discriminatory gender, racial, religious and ethnic biases. In contrast, human-written dictionaries describe the meanings of words in a …

Word Embeddings

Bridging the Defined and the Defining: Exploiting Implicit Lexical Semantic Relations in Definition Modeling

2019-11-01 · IJCNLP 2019 11 · Koki Washio, Satoshi Sekine, Tsuneaki Kato

Definition modeling includes acquiring word embeddings from dictionary definitions and generating definitions of words. While the meanings of defining words are important in dictionary definitions, it is crucial to captu…

Word Embeddings

Auto-Encoding Dictionary Definitions into Consistent Word Embeddings

2018-10-01 · EMNLP 2018 10 · Tom Bosc, Pascal Vincent

Monolingual dictionaries are widespread and semantically rich resources. This paper presents a simple model that learns to compute word embeddings by processing dictionary definitions and trying to reconstruct them. It e…

Document ClassificationMachine TranslationSemantic SimilaritySemantic Textual Similarity+1

Word Definitions from Large Language Models

2023-11-10 · Bach Pham, JuiHsuan Wong, Samuel Kim, Yunting Yin 외

Dictionary definitions are historically the arbitrator of what words mean, but this primacy has come under threat by recent progress in NLP, including word embeddings and generative models like ChatGPT. We present an exp…

Word Embeddings