首页/论文/1908.00308

arXiv 1908.003082019-08-01cs.CLcs.LG

MSnet: A BERT-based Network for Gendered Pronoun Resolution

CEIEC（中国电子进出口总公司）

Zili Wang

备注：: 7 pages; 1 figures; accepted by 1st ACL Workshop on Gender Bias for NLP at ACL 2019

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

The pre-trained BERT model achieves a remarkable state of the art across a wide range of tasks in natural language processing. For solving the gender bias in gendered pronoun resolution task, I propose a novel neural network model based on the pre-trained BERT. This model is a type of mention score classifier and uses an attention mechanism with no parameters to compute the contextual representation of entity span, and a vector to represent the triple-wise semantic similarity among the pronoun and the entities. In stage 1 of the gendered pronoun resolution task, a variant of this model, trained in the fine-tuning approach, reduced the multi-class logarithmic loss to 0.3033 in the 5-fold cross-validation of training set and 0.2795 in testing set. Besides, this variant won the 2nd place with a score at 0.17289 in stage 2 of the task. The code in this paper is available at: https://github.com/ziliwang/MSnet-for-Gendered-PronounResolution

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Gendered Ambiguous Pronouns Shared Task: Boosting Model Confidence by Evidence Pooling

This paper presents a strong set of results for resolving gendered ambiguous pronouns on the Gendered Ambiguous Pronouns shared task. The model presented here draws upon the strengths of state-of-the-art language and coreference resolution models, and introduces a novel evidence-based deep learning architecture. Injecting evidence from the coreference models compliments the base architecture, and analysis shows that the model is not hindered by their weaknesses, specifically gender bias. The modularity and simplicity of the architecture make it very easy to extend for further improvement and a…

2019-06-03cs.CL

Gendered Pronoun Resolution using BERT and an extractive question answering formulation

The resolution of ambiguous pronouns is a longstanding challenge in Natural Language Understanding. Recent studies have suggested gender bias among state-of-the-art coreference resolution systems. As an example, Google AI Language team recently released a gender-balanced dataset and showed that performance of these coreference resolvers is significantly limited on the dataset. In this paper, we propose an extractive question answering (QA) formulation of pronoun resolution task that overcomes this limitation and shows much lower gender bias (0.99) on their dataset. This system uses fine-tuned …

2019-06-09cs.CLcs.LG

Anonymized BERT: An Augmentation Approach to the Gendered Pronoun Resolution Challenge

S&P Global（标普全球）

We present our 7th place solution to the Gendered Pronoun Resolution challenge, which uses BERT without fine-tuning and a novel augmentation strategy designed for contextual embedding token-level tasks. Our method anonymizes the referent by replacing candidate names with a set of common placeholder names. Besides the usual benefits of effectively increasing training data size, this approach diversifies idiosyncratic information embedded in names. Using same set of common first names can also help the model recognize names better, shorten token length, and remove gender and regional biases asso…

2019-06-11cs.AIcs.CLcs.LG

Mind the GAP: A Balanced Corpus of Gendered Ambiguous Pronouns

Google AI Language（谷歌人工智能语言部门）

Coreference resolution is an important task for natural language understanding, and the resolution of ambiguous pronouns a longstanding challenge. Nonetheless, existing corpora do not capture ambiguous pronouns in sufficient volume or diversity to accurately indicate the practical utility of models. Furthermore, we find gender bias in existing corpora and systems favoring masculine entities. To address this, we present and release GAP, a gender-balanced labeled corpus of 8,908 ambiguous pronoun-name pairs sampled to provide diverse coverage of challenges posed by real-world text. We explore a …

2018-10-11cs.CL

Resolving Gendered Ambiguous Pronouns with BERT

University of Pennsylvania（宾夕法尼亚大学）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；Kitsong；PJSC Sberbank（俄罗斯联邦储蓄银行）；Jet Infosystems；Sofia University（索非亚大学）

Pronoun resolution is part of coreference resolution, the task of pairing an expression to its referring entity. This is an important task for natural language understanding and a necessary component of machine translation systems, chat bots and assistants. Neural machine learning systems perform far from ideally in this task, reaching as low as 73% F1 scores on modern benchmark datasets. Moreover, they tend to perform better for masculine pronouns than for feminine ones. Thus, the problem is both challenging and important for NLP researchers and practitioners. In this project, we describe our…

2019-06-13cs.CLcs.LGstat.ML

Look Again at the Syntax: Relational Graph Convolutional Network for Gendered Ambiguous Pronoun Resolution

University of Pennsylvania（宾夕法尼亚大学）；Yale University（耶鲁大学）

Gender bias has been found in existing coreference resolvers. In order to eliminate gender bias, a gender-balanced dataset Gendered Ambiguous Pronouns (GAP) has been released and the best baseline model achieves only 66.9% F1. Bidirectional Encoder Representations from Transformers (BERT) has broken several NLP task records and can be used on GAP dataset. However, fine-tune BERT on a specific task is computationally expensive. In this paper, we propose an end-to-end resolver by combining pre-trained BERT with Relational Graph Convolutional Network (R-GCN). R-GCN is used for digesting structura…

2019-05-31cs.CL

更多相关论文收起更多论文

Is Japanese gendered language used on Twitter ? A large scale study

University of Milan（米兰大学）

This study analyzes the usage of Japanese gendered language on Twitter. Starting from a collection of 408 million Japanese tweets from 2015 till 2019 and an additional sample of 2355 manually classified Twitter accounts timelines into gender and categories (politicians, musicians, etc). A large scale textual analysis is performed on this corpus to identify and examine sentence-final particles (SFPs) and first-person pronouns appearing in the texts. It turns out that gendered language is in fact used also on Twitter, in about 6% of the tweets, and that the prescriptive classification into "male…

2020-07-09cs.CLstat.AP

语言建模任务中的欠规范化：一项基于因果信息的性别代词消解研究

Underspecification in Language Modeling Tasks: A Causality-Informed Study of Gendered Pronoun Resolution

本文提出一种因果机制解释语言建模任务中的欠规范化如何导致虚假相关，并据此开发两种轻量级黑盒评估方法，在多种规模、预训练目标和训练阶段的大语言模型上检测性别代词消解中的推理时欠规范化及此前未报告的虚假相关。

2024-02-22cs.AIcs.CL

Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns

University of Oxford（牛津大学）；TU Wien（维也纳工业大学）；University College London（伦敦大学学院）

Bias-measuring datasets play a critical role in detecting biased behavior of language models and in evaluating progress of bias mitigation methods. In this work, we focus on evaluating gender bias through coreference resolution, where previous datasets are either hand-crafted or fail to reliably measure an explicitly defined bias. To overcome these shortcomings, we propose a novel method to collect diverse, natural, and minimally distant text pairs via counterfactual generation, and construct Counter-GAP, an annotated dataset consisting of 4008 instances grouped into 1002 quadruples. We furthe…

2023-02-11cs.AIcs.CL

探究中文大语言模型中的社会身份偏见：基于性别代词与社会群体

Probing Social Identity Bias in Chinese LLMs with Gendered Pronouns and Social Groups

Department of Electronics, Information and Bioengineering, Politecnico di Milano（电子、信息与生物工程系，米兰理工大学）；University of Science and Technology of China（中国科学技术大学）

通过设计考虑中文语言特性的提示，评估十种代表性中文大语言模型在240个社会群体上的内群体与外群体框架下的情感和毒性偏见，发现系统性不对称且指令调优减少情感偏见但毒性差距更持久，女性标记代词与更高毒性相关。

2026-05-26cs.CL

ChatGPT在机器翻译中延续性别偏见并忽视非性别代词：孟加拉语及其他五种低资源语言的调查结果

ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages

University of Washington（华盛顿大学）

研究评估ChatGPT在孟加拉语等六种低资源语言互译中的性别中立代词处理，发现其延续职业性别刻板印象且误译“they”，并提出以人为本的改进建议。

2023-05-17cs.AIcs.CLcs.CY

代词逻辑

Pronoun Logic

Worcester Polytechnic Institute（伍斯特理工学院）

本文提出用形式逻辑表达个人代词及性别期望，比较线性逻辑、时序逻辑和带确定描述的自由逻辑三种基础，旨在以趣味性方式让TGNB群体在逻辑领域获得归属感并推动相关工具应用。

2024-09-13cs.CL

缓解大型语言模型中酷儿表征的偏见：一种协作式智能体方法

Mitigating Bias in Queer Representation within Large Language Models: A Collaborative Agent Approach

App-In Club（App-In俱乐部）

针对 LLM 在性别代词使用中排斥酷儿身份的问题，本文提出含偏见检测与纠正专用智能体的协作流水线，并在 Tango 上证明其相较 GPT-4o 显著提升包容性代词判断。

2024-12-02cs.CLcs.MA

Scalable Cross Lingual Pivots to Model Pronoun Gender for Translation

Google Research（谷歌研究院）

Machine translation systems with inadequate document understanding can make errors when translating dropped or neutral pronouns into languages with gendered pronouns (e.g., English). Predicting the underlying gender of these pronouns is difficult since it is not marked textually and must instead be inferred from coreferent mentions in the context. We propose a novel cross-lingual pivoting technique for automatically producing high-quality gender labels, and show that this data can be used to fine-tune a BERT classifier with 92% F1 for Spanish dropped feminine pronouns, compared with 30-51% for…

2020-06-16cs.CL

转变荷兰语：为荷兰语共指消解系统去偏以支持非二元代词

Transforming Dutch: Debiasing Dutch Coreference Resolution Systems for Non-binary Pronouns

Utrecht University（乌得勒支大学）

本文研究荷兰语共指消解系统对非二元代词 hen 和 die 的处理性能，比较 CDA 与去词汇化两种去偏方法，并提出代词得分指标，证明 CDA 在低资源下也能有效缩小性别中立代词与有性别代词之间的性能差距。

2024-04-30cs.AIcs.CL

用于医疗应用的性别中立大型语言模型：减少PubMed摘要中的偏见

Gender-Neutral Large Language Models for Medical Applications: Reducing Bias in PubMed Abstracts

Yale University Department of Computer Science（耶鲁大学计算机科学系）；UTHealth Houston McWilliams School of Biomedical Informatics（德克萨斯大学健康科学中心休斯顿生物医学信息学学院）

本文提出一种通过中和职业代词缓解医疗文献LLM性别偏见的流水线，开发了MOBERT模型，其包容性替换率达70%，远超基线1965BERT的4%，促进了医疗应用的公平语言建模。

2025-05-28cs.AIcs.CLcs.IR

使用人口普查数据测量语言模型中的规范性与描述性偏见

Measuring Normative and Descriptive Biases in Language Models Using Census Data

University of Bergen（卑尔根大学）；University of Oslo（奥斯陆大学）

本文利用四国官方人口普查数据构建性别—职业分布基准，通过模板句探测十种语言模型，提出一种语言无关的评分方法，以测量模型在职业性别分布上与规范性和描述性分布的一致程度。

2023-04-12cs.CL

RGAT：深入探究用于共指消解的句法依存信息

RGAT: A Deeper Look into Syntactic Dependency Information for Coreference Resolution

Shanghai University of International Business and Economics（上海对外经贸大学）

本文提出结合BERT与RGAT的端到端解析器，通过学习句法依存图生成融合表示，在GAP和OntoNotes 5.0数据集上有效提升了共指消解性能。

2023-09-10cs.AIcs.CL