发布求助
文献互助 智能选刊 最新文献

Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)最新文献

筛选
英文 中文
Transfer Learning Parallel Metaphor using Bilingual Embeddings 基于双语嵌入的平行隐喻迁移学习
Proceedings of the 3rd Workshop on Figurative Language Processing (FLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.flp-1.3
Maria Berger
{"title":"Transfer Learning Parallel Metaphor using Bilingual Embeddings","authors":"Maria Berger","doi":"10.18653/v1/2022.flp-1.3","DOIUrl":"https://doi.org/10.18653/v1/2022.flp-1.3","url":null,"abstract":"Automated metaphor detection in languages other than English is highly restricted as training corpora are comparably rare. One way to overcome this problem is transfer learning. This paper gives an overview on transfer learning techniques applied to NLP. We first introduce types of transfer learning, then we present work focusing on: i) transfer learning with cross-lingual embeddings; ii) transfer learning in machine translation; and iii) transfer learning using pre-trained transformer models. The paper is complemented by first experiments that make use of bilingual embeddings generated from different sources of parallel data: We i) present the preparation of a parallel Gold corpus; ii) examine the embeddings spaces to search for metaphoric words cross-lingually; iii) run first experiments in transfer learning German metaphor from English labeled data only. Results show that finding data sources for bilingual embeddings training and the vocabulary covered by these embeddings is critical for learning metaphor cross-lingually.","PeriodicalId":332745,"journal":{"name":"Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)","volume":" 393","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113946762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Bayes at FigLang 2022 Euphemism Detection shared task: Cost-Sensitive Bayesian Fine-tuning and Venn-Abers Predictors for Robust Training under Class Skewed Distributions 委婉语检测共享任务:类偏斜分布下鲁棒训练的成本敏感贝叶斯微调和Venn-Abers预测
Proceedings of the 3rd Workshop on Figurative Language Processing (FLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.flp-1.13
Paul Trust, Kadusabe Provia, Kizito Omala
{"title":"Bayes at FigLang 2022 Euphemism Detection shared task: Cost-Sensitive Bayesian Fine-tuning and Venn-Abers Predictors for Robust Training under Class Skewed Distributions","authors":"Paul Trust, Kadusabe Provia, Kizito Omala","doi":"10.18653/v1/2022.flp-1.13","DOIUrl":"https://doi.org/10.18653/v1/2022.flp-1.13","url":null,"abstract":"Transformers have achieved a state of the art performance across most natural language processing tasks. However the performance of these models degrade when being trained on skewed class distributions (class imbalance) because training tends to be biased towards head classes with most of the data points . Classical methods that have been proposed to handle this problem (re-sampling and re-weighting) often suffer from unstable performance, poor applicability and poor calibration. In this paper, we propose to use Bayesian methods and Venn-Abers predictors for well calibrated and robust training against class imbalance. Our proposed approach improves f1-score of the baseline RoBERTa (A Robustly Optimized Bidirectional Embedding from Transformers Pretraining Approach) model by about 6 points (79.0% against 72.6%) when training with class imbalanced data.","PeriodicalId":332745,"journal":{"name":"Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126565357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
NLP@UIT at FigLang-EMNLP 2022: A Divide-and-Conquer System For Shared Task On Understanding Figurative Language NLP@UIT在FigLang-EMNLP 2022:一个用于理解比喻语言的共享任务的分而治之系统
Proceedings of the 3rd Workshop on Figurative Language Processing (FLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.flp-1.21
Khoa Thi-Kim Phan, Duc-Vu Nguyen, N. Nguyen
{"title":"NLP@UIT at FigLang-EMNLP 2022: A Divide-and-Conquer System For Shared Task On Understanding Figurative Language","authors":"Khoa Thi-Kim Phan, Duc-Vu Nguyen, N. Nguyen","doi":"10.18653/v1/2022.flp-1.21","DOIUrl":"https://doi.org/10.18653/v1/2022.flp-1.21","url":null,"abstract":"This paper describes our submissions to the EMNLP 2022 shared task on Understanding Figurative Language as part of the Figurative Language Workshop (FigLang 2022). Our systems based on pre-trained language model T5 are divide-and-conquer models which can address both two requirements of the task: 1) classification, and 2) generation. In this paper, we introduce different approaches in which each approach we employ a processing strategy on input model. We also emphasize the influence of the types of figurative language on our systems.","PeriodicalId":332745,"journal":{"name":"Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134487656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
FigurativeQA: A Test Benchmark for Figurativeness Comprehension for Question Answering 比喻性问答:回答问题的比喻性理解的测试基准
Proceedings of the 3rd Workshop on Figurative Language Processing (FLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.flp-1.23
Geetanjali Rakshit, Jeffrey Flanigan
{"title":"FigurativeQA: A Test Benchmark for Figurativeness Comprehension for Question Answering","authors":"Geetanjali Rakshit, Jeffrey Flanigan","doi":"10.18653/v1/2022.flp-1.23","DOIUrl":"https://doi.org/10.18653/v1/2022.flp-1.23","url":null,"abstract":"Figurative language is widespread in human language (Lakoff and Johnson, 2008) posing potential challenges in NLP applications. In this paper, we investigate the effect of figurative language on the task of question answering (QA). We construct FigQA, a test set of 400 yes-no questions with figurative and non-figurative contexts, extracted from product reviews and restaurant reviews. We demonstrate that a state-of-the-art RoBERTa QA model has considerably lower performance in question answering when the contexts are figurative rather than literal, indicating a gap in current models. We propose a general method for improving the performance of QA models by converting the figurative contexts into non-figurative by prompting GPT-3, and demonstrate its effectiveness. Our results indicate a need for building QA models infused with figurative language understanding capabilities.","PeriodicalId":332745,"journal":{"name":"Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131156462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Can Yes-No Question-Answering Models be Useful for Few-Shot Metaphor Detection? 是非问答模型对少量隐喻检测有用吗?
Proceedings of the 3rd Workshop on Figurative Language Processing (FLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.flp-1.17
Lena Dankin, Kfir Bar, N. Dershowitz
{"title":"Can Yes-No Question-Answering Models be Useful for Few-Shot Metaphor Detection?","authors":"Lena Dankin, Kfir Bar, N. Dershowitz","doi":"10.18653/v1/2022.flp-1.17","DOIUrl":"https://doi.org/10.18653/v1/2022.flp-1.17","url":null,"abstract":"Metaphor detection has been a challenging task in the NLP domain both before and after the emergence of transformer-based language models. The difficulty lies in subtle semantic nuances that are required to detect metaphor and in the scarcity of labeled data. We explore few-shot setups for metaphor detection, and also introduce new question answering data that can enhance classifiers that are trained on a small amount of data. We formulate the classification task as a question-answering one, and train a question-answering model. We perform extensive experiments for few shot on several architectures and report the results of several strong baselines. Thus, the answer to the question posed in the title is a definite “Yes!”","PeriodicalId":332745,"journal":{"name":"Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125156064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信