Don't Invite BERT to Drink a Bottle: Modeling the Interpretation of Metonymies Using BERT and Distributional Representations

机译：不要邀请BERT喝一瓶：使用BERT和分配表示建模转词的解释

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

In this work, we carry out two experiments in order to assess the ability of BERT to capture the meaning shift associated with metonymic expressions. We test the model on a new dataset that is representative of the most common types of metonymy. We compare BERT with the Structured Distributional Model (SDM), a model for the representation of words in context which is based on the notion of Generalized Event Knowledge. The results reveal that, while BERT ability to deal with metonymy is quite limited, SDM is good at predicting the meaning of metonymic expressions, providing support for an account of metonymy based on event knowledge.

机译：在这项工作中，我们执行两个实验，以评估BERT捕获与转喻表达相关的含义的含义。我们在代表最常见的转喻类型的新数据集中测试模型。我们将BERT与结构化分配模型（SDM）进行比较，这是基于广义事件知识的概念的语境中的语言表示的模型。结果表明，虽然伯特能力处理转喻的能力相当有限，但SDM擅长预测转喻表达式的含义，基于事件知识提供对转喻账户的支持。

著录项

来源
《International Conference on Computational Linguistics》|2020年|6831-6837|共7页
会议地点
作者
Paolo Pedinotti; Alessandro Lenci;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词

相似文献

外文文献
中文文献
专利

1. Fine-Tuning Bidirectional Encoder Representations From Transformers (BERT)–Based Models on Large-Scale Electronic Health Record Notes: An Empirical Study [J] . Fei Li, Yonghao Jin, Weisong Liu, JMIR Medical Informatics . 2019,第3期

机译：来自变压器（BERT）的微调双向编码器表示，基于大型电子健康记录的模型：实证研究
2. Zero‐anaphora resolution in Korean based on deep language representation model: BERT [J] . Youngtae Kim, Dongyul Ra, Soojong Lim ETRI journal . 2021,第2期

机译：基于深语陈述模型的韩国零安息日分辨率：伯特
3. Adapting Bidirectional Encoder Representations from Transformers (BERT) to Assess Clinical Semantic Textual Similarity: Algorithm Development and Validation Study [J] . Klaus Kades, Jan Sellner, Gregor Koehler, JMIR Medical Informatics . 2021,第2期

机译：使用变压器（BERT）的双向编码器表示来评估临床语义文本相似性：算法开发和验证研究
4. Vietnamese Question Answering System f rom Multilingual BERT Models to Monolingual BERT Model [C] . Nguyen Thi Mai Trang, Maxim Shcherbakov International Conference System Modeling and Advancement in Research Trends . 2020

机译：越南问题回答系统F ROM多语言BERT模型到单晶伯特模型
5. QMRA: Exposure model sensitivity to input parameters, critical review of dose-response models, and application in assessing risk of aging drinking water distribution systems [D] . Van Abel, Nicole A. 2014

机译：QMRA：暴露模型对输入参数的敏感性，剂量反应模型的严格审查，以及在评估饮用水分配系统老化的风险中的应用
6. Unified Medical Language System resources improve sieve-based generation and Bidirectional Encoder Representations from Transformers (BERT)–based ranking for concept normalization [O] . Dongfang Xu, Manoj Gopale, Jiacheng Zhang, 2020

机译：统一的医疗语言系统资源改善了从变压器（BERT）的基于筛的生成和双向编码器表示为概念标准化排名
7. Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering [O] . Zhiguo Wang, Patrick Ng, Xiaofei Ma, 2019

机译：多通道BERT：开放域问题应答的全球规范化的BERT模型

Don't Invite BERT to Drink a Bottle: Modeling the Interpretation of Metonymies Using BERT and Distributional Representations

摘要

著录项

相似文献

相关主题

期刊订阅