发布求助
文献互助 智能选刊 最新文献

Proceedings of the First Workshop on Interactive Learning for Natural Language Processing最新文献

筛选
英文 中文
Dynamic Facet Selection by Maximizing Graded Relevance 动态面选择最大化分级相关性
Proceedings of the First Workshop on Interactive Learning for Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/2021.internlp-1.5
Michael R. Glass, Md. Faisal Mahbub Chowdhury, Yu Deng, R. Mahindru, Nicolas R. Fauceglia, A. Gliozzo, Nandana Mihindukulasooriya
{"title":"Dynamic Facet Selection by Maximizing Graded Relevance","authors":"Michael R. Glass, Md. Faisal Mahbub Chowdhury, Yu Deng, R. Mahindru, Nicolas R. Fauceglia, A. Gliozzo, Nandana Mihindukulasooriya","doi":"10.18653/v1/2021.internlp-1.5","DOIUrl":"https://doi.org/10.18653/v1/2021.internlp-1.5","url":null,"abstract":"Dynamic faceted search (DFS), an interactive query refinement technique, is a form of Human–computer information retrieval (HCIR) approach. It allows users to narrow down search results through facets, where the facets-documents mapping is determined at runtime based on the context of user query instead of pre-indexing the facets statically. In this paper, we propose a new unsupervised approach for dynamic facet generation, namely optimistic facets, which attempts to generate the best possible subset of facets, hence maximizing expected Discounted Cumulative Gain (DCG), a measure of ranking quality that uses a graded relevance scale. We also release code to generate a new evaluation dataset. Through empirical results on two datasets, we show that the proposed DFS approach considerably improves the document ranking in the search results.","PeriodicalId":262697,"journal":{"name":"Proceedings of the First Workshop on Interactive Learning for Natural Language Processing","volume":"83 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":"131984710","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
HILDIF: Interactive Debugging of NLI Models Using Influence Functions 使用影响函数的NLI模型交互式调试
Proceedings of the First Workshop on Interactive Learning for Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/2021.internlp-1.1
Hugo Zylberajch, Piyawat Lertvittayakumjorn, Francesca Toni
{"title":"HILDIF: Interactive Debugging of NLI Models Using Influence Functions","authors":"Hugo Zylberajch, Piyawat Lertvittayakumjorn, Francesca Toni","doi":"10.18653/v1/2021.internlp-1.1","DOIUrl":"https://doi.org/10.18653/v1/2021.internlp-1.1","url":null,"abstract":"Biases and artifacts in training data can cause unwelcome behavior in text classifiers (such as shallow pattern matching), leading to lack of generalizability. One solution to this problem is to include users in the loop and leverage their feedback to improve models. We propose a novel explanatory debugging pipeline called HILDIF, enabling humans to improve deep text classifiers using influence functions as an explanation method. We experiment on the Natural Language Inference (NLI) task, showing that HILDIF can effectively alleviate artifact problems in fine-tuned BERT models and result in increased model generalizability.","PeriodicalId":262697,"journal":{"name":"Proceedings of the First Workshop on Interactive Learning for Natural Language Processing","volume":"23 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":"115316163","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: 17
Active Curriculum Learning 主动课程学习
Proceedings of the First Workshop on Interactive Learning for Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/2021.internlp-1.6
B. Jafarpour, Dawn Sepehr, Nick Pogrebnyakov
{"title":"Active Curriculum Learning","authors":"B. Jafarpour, Dawn Sepehr, Nick Pogrebnyakov","doi":"10.18653/v1/2021.internlp-1.6","DOIUrl":"https://doi.org/10.18653/v1/2021.internlp-1.6","url":null,"abstract":"This paper investigates and reveals the relationship between two closely related machine learning disciplines, namely Active Learning (AL) and Curriculum Learning (CL), from the lens of several novel curricula. This paper also introduces Active Curriculum Learning (ACL) which improves AL by combining AL with CL to benefit from the dynamic nature of the AL informativeness concept as well as the human insights used in the design of the curriculum heuristics. Comparison of the performance of ACL and AL on two public datasets for the Named Entity Recognition (NER) task shows the effectiveness of combining AL and CL using our proposed framework.","PeriodicalId":262697,"journal":{"name":"Proceedings of the First Workshop on Interactive Learning for Natural Language Processing","volume":"54 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":"133833574","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: 9
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：481959085
Book学术官方微信