发布求助
文献互助 智能选刊 最新文献

Proceedings of the conference. Association for Computational Linguistics. Meeting最新文献

筛选
英文 中文
Training Classifiers with Natural Language Explanations 用自然语言解释训练分类器
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2018-05-10 DOI: 10.18653/v1/P18-1175
Braden Hancock, P. Varma, Stephanie Wang, Martin Bringmann, Percy Liang, C. Ré
{"title":"Training Classifiers with Natural Language Explanations","authors":"Braden Hancock, P. Varma, Stephanie Wang, Martin Bringmann, Percy Liang, C. Ré","doi":"10.18653/v1/P18-1175","DOIUrl":"https://doi.org/10.18653/v1/P18-1175","url":null,"abstract":"Training accurate classifiers requires many labels, but each label provides only limited information (one bit for binary classification). In this work, we propose BabbleLabble, a framework for training classifiers in which an annotator provides a natural language explanation for each labeling decision. A semantic parser converts these explanations into programmatic labeling functions that generate noisy labels for an arbitrary amount of unlabeled data, which is used to train a classifier. On three relation extraction tasks, we find that users are able to train classifiers with comparable F1 scores from 5-100 faster by providing explanations instead of just labels. Furthermore, given the inherent imperfection of labeling functions, we find that a simple rule-based semantic parser suffices.","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"2 1","pages":"1884-1895"},"PeriodicalIF":0.0,"publicationDate":"2018-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83375273","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: 140
Automating Biomedical Evidence Synthesis: RobotReviewer. 自动化生物医学证据合成:RobotReviewer。
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2017-07-01 DOI: 10.18653/v1/P17-4002
Iain J Marshall, Joël Kuiper, Edward Banner, Byron C Wallace
{"title":"Automating Biomedical Evidence Synthesis: RobotReviewer.","authors":"Iain J Marshall, Joël Kuiper, Edward Banner, Byron C Wallace","doi":"10.18653/v1/P17-4002","DOIUrl":"10.18653/v1/P17-4002","url":null,"abstract":"<p><p>We present <i>RobotReviewer</i>, an open-source web-based system that uses machine learning and NLP to semi-automate biomedical evidence synthesis, to aid the practice of Evidence-Based Medicine. RobotReviewer processes full-text journal articles (PDFs) describing randomized controlled trials (RCTs). It appraises the reliability of RCTs and extracts text describing key trial characteristics (e.g., descriptions of the population) using novel NLP methods. RobotReviewer then automatically generates a report synthesising this information. Our goal is for RobotReviewer to automatically extract and synthesise the full-range of structured data needed to inform evidence-based practice.</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"2017 ","pages":"7-12"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5662138/pdf/nihms880383.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35568129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Neural Semantic Encoders. 神经语义编码器。
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2017-04-01
Tsendsuren Munkhdalai, Hong Yu
{"title":"Neural Semantic Encoders.","authors":"Tsendsuren Munkhdalai,&nbsp;Hong Yu","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through <i>read</i>, <i>compose</i> and <i>write</i> operations. NSE can also access multiple and shared memories. In this paper, we demonstrated the effectiveness and the flexibility of NSE on five different natural language tasks: natural language inference, question answering, sentence classification, document sentiment analysis and machine translation where NSE achieved state-of-the-art performance when evaluated on publically available benchmarks. For example, our shared-memory model showed an encouraging result on neural machine translation, improving an attention-based baseline by approximately 1.0 BLEU.</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"1 ","pages":"397-407"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5657452/pdf/nihms912000.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35553901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Neural Tree Indexers for Text Understanding. 文本理解的神经树索引器。
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2017-04-01
Tsendsuren Munkhdalai, Hong Yu
{"title":"Neural Tree Indexers for Text Understanding.","authors":"Tsendsuren Munkhdalai,&nbsp;Hong Yu","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Recurrent neural networks (RNNs) process input text sequentially and model the conditional transition between word tokens. In contrast, the advantages of recursive networks include that they explicitly model the compositionality and the recursive structure of natural language. However, the current recursive architecture is limited by its dependence on syntactic tree. In this paper, we introduce a robust syntactic parsing-independent tree structured model, Neural Tree Indexers (NTI) that provides a middle ground between the sequential RNNs and the syntactic tree-based recursive models. NTI constructs a <i>full n-ary tree</i> by processing the input text with its node function in a bottom-up fashion. Attention mechanism can then be applied to both structure and node function. We implemented and evaluated a binary-tree model of NTI, showing the model achieved the state-of-the-art performance on three different NLP tasks: natural language inference, answer sentence selection, and sentence classification, outperforming state-of-the-art recurrent and recursive neural networks .</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"1 ","pages":"11-21"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5657441/pdf/nihms912010.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35552522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Aggregating and Predicting Sequence Labels from Crowd Annotations. 从人群注释中聚合和预测序列标签。
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2017-01-01 DOI: 10.18653/v1/P17-1028
An T Nguyen, Byron C Wallace, Junyi Jessy Li, Ani Nenkova, Matthew Lease
{"title":"Aggregating and Predicting Sequence Labels from Crowd Annotations.","authors":"An T Nguyen,&nbsp;Byron C Wallace,&nbsp;Junyi Jessy Li,&nbsp;Ani Nenkova,&nbsp;Matthew Lease","doi":"10.18653/v1/P17-1028","DOIUrl":"https://doi.org/10.18653/v1/P17-1028","url":null,"abstract":"<p><p>Despite sequences being core to NLP, scant work has considered how to handle noisy sequence labels from multiple annotators for the same text. Given such annotations, we consider two complementary tasks: (1) aggregating sequential crowd labels to infer a best single set of consensus annotations; and (2) using crowd annotations as training data for a model that can predict sequences in unannotated text. For aggregation, we propose a novel Hidden Markov Model variant. To predict sequences in unannotated text, we propose a neural approach using Long Short Term Memory. We evaluate a suite of methods across two different applications and text genres: Named-Entity Recognition in news articles and Information Extraction from biomedical abstracts. Results show improvement over strong baselines. Our source code and data are available online.</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"2017 ","pages":"299-309"},"PeriodicalIF":0.0,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.18653/v1/P17-1028","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35568131","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 75
Understanding Discourse on Work and Job-Related Well-Being in Public Social Media 理解公共社交媒体中关于工作和工作相关幸福感的话语
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2016-08-01 DOI: 10.18653/v1/P16-1099
Tong Liu, Christopher Homan, Cecilia Ovesdotter Alm, Megan C. Lytle-Flint, Ann Marie White, Henry A. Kautz
{"title":"Understanding Discourse on Work and Job-Related Well-Being in Public Social Media","authors":"Tong Liu, Christopher Homan, Cecilia Ovesdotter Alm, Megan C. Lytle-Flint, Ann Marie White, Henry A. Kautz","doi":"10.18653/v1/P16-1099","DOIUrl":"https://doi.org/10.18653/v1/P16-1099","url":null,"abstract":"We construct a humans-in-the-loop supervised learning framework that integrates crowdsourcing feedback and local knowledge to detect job-related tweets from individual and business accounts. Using data-driven ethnography, we examine discourse about work by fusing language-based analysis with temporal, geospational, and labor statistics information.","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"251 1","pages":"1044-1053"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75760239","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
Nonparametric Spherical Topic Modeling with Word Embeddings. 基于词嵌入的非参数球形主题建模。
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2016-08-01 DOI: 10.18653/v1/P16-2087
Kayhan Batmanghelich, Ardavan Saeedi, Karthik Narasimhan, Sam Gershman
{"title":"Nonparametric Spherical Topic Modeling with Word Embeddings.","authors":"Kayhan Batmanghelich,&nbsp;Ardavan Saeedi,&nbsp;Karthik Narasimhan,&nbsp;Sam Gershman","doi":"10.18653/v1/P16-2087","DOIUrl":"https://doi.org/10.18653/v1/P16-2087","url":null,"abstract":"<p><p>Traditional topic models do not account for semantic regularities in language. Recent distributional representations of words exhibit semantic consistency over directional metrics such as cosine similarity. However, neither categorical nor Gaussian observational distributions used in existing topic models are appropriate to leverage such correlations. In this paper, we propose to use the von Mises-Fisher distribution to model the density of words over a unit sphere. Such a representation is well-suited for directional data. We use a Hierarchical Dirichlet Process for our base topic model and propose an efficient inference algorithm based on Stochastic Variational Inference. This model enables us to naturally exploit the semantic structures of word embeddings while flexibly discovering the number of topics. Experiments demonstrate that our method outperforms competitive approaches in terms of topic coherence on two different text corpora while offering efficient inference.</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"2016 ","pages":"537-542"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6327958/pdf/nihms-999400.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"36858644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 78
Neural Tree Indexers for Text Understanding 文本理解的神经树索引器
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2016-07-15 DOI: 10.18653/V1/E17-1002
Tsendsuren Munkhdalai, Hong Yu
{"title":"Neural Tree Indexers for Text Understanding","authors":"Tsendsuren Munkhdalai, Hong Yu","doi":"10.18653/V1/E17-1002","DOIUrl":"https://doi.org/10.18653/V1/E17-1002","url":null,"abstract":"Recurrent neural networks (RNNs) process input text sequentially and model the conditional transition between word tokens. In contrast, the advantages of recursive networks include that they explicitly model the compositionality and the recursive structure of natural language. However, the current recursive architecture is limited by its dependence on syntactic tree. In this paper, we introduce a robust syntactic parsing-independent tree structured model, Neural Tree Indexers (NTI) that provides a middle ground between the sequential RNNs and the syntactic treebased recursive models. NTI constructs a full n-ary tree by processing the input text with its node function in a bottom-up fashion. Attention mechanism can then be applied to both structure and node function. We implemented and evaluated a binary tree model of NTI, showing the model achieved the state-of-the-art performance on three different NLP tasks: natural language inference, answer sentence selection, and sentence classification, outperforming state-of-the-art recurrent and recursive neural networks.","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"1 1","pages":"11-21"},"PeriodicalIF":0.0,"publicationDate":"2016-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78981638","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: 103
Neural Semantic Encoders 神经语义编码器
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2016-07-14 DOI: 10.18653/V1/E17-1038
Tsendsuren Munkhdalai, Hong Yu
{"title":"Neural Semantic Encoders","authors":"Tsendsuren Munkhdalai, Hong Yu","doi":"10.18653/V1/E17-1038","DOIUrl":"https://doi.org/10.18653/V1/E17-1038","url":null,"abstract":"We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through read, compose and write operations. NSE can also access 1 multiple and shared memories. In this paper, we demonstrated the effectiveness and the flexibility of NSE on five different natural language tasks: natural language inference, question answering, sentence classification, document sentiment analysis and machine translation where NSE achieved state-of-the-art performance when evaluated on publically available benchmarks. For example, our shared-memory model showed an encouraging result on neural machine translation, improving an attention-based baseline by approximately 1.0 BLEU.","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"91 1","pages":"397-407"},"PeriodicalIF":0.0,"publicationDate":"2016-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73677189","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: 133
Exploring Autism Spectrum Disorders Using HLT. 使用 HLT 探索自闭症谱系障碍。
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2016-06-01 DOI: 10.18653/v1/w16-0308
Julia Parish-Morris, Mark Liberman, Neville Ryant, Christopher Cieri, Leila Bateman, Emily Ferguson, Robert T Schultz
{"title":"Exploring Autism Spectrum Disorders Using HLT.","authors":"Julia Parish-Morris, Mark Liberman, Neville Ryant, Christopher Cieri, Leila Bateman, Emily Ferguson, Robert T Schultz","doi":"10.18653/v1/w16-0308","DOIUrl":"10.18653/v1/w16-0308","url":null,"abstract":"<p><p>The phenotypic complexity of Autism Spectrum Disorder motivates the application of modern computational methods to large collections of observational data, both for improved clinical diagnosis and for better scientific understanding. We have begun to create a corpus of annotated language samples relevant to this research, and we plan to join with other researchers in pooling and publishing such resources on a large scale. The goal of this paper is to present some initial explorations to illustrate the opportunities that such datasets will afford.</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"2016 ","pages":"74-84"},"PeriodicalIF":0.0,"publicationDate":"2016-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7558465/pdf/nihms-985179.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38604333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
首页 上一页 下一页 尾页
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