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
Two-stage Federated Phenotyping and Patient Representation Learning. 两阶段联合表型和患者表征学习。
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2019-08-01 DOI: 10.18653/v1/W19-5030
Dianbo Liu, Dmitriy Dligach, Timothy Miller
{"title":"Two-stage Federated Phenotyping and Patient Representation Learning.","authors":"Dianbo Liu, Dmitriy Dligach, Timothy Miller","doi":"10.18653/v1/W19-5030","DOIUrl":"10.18653/v1/W19-5030","url":null,"abstract":"<p><p>A large percentage of medical information is in unstructured text format in electronic medical record systems. Manual extraction of information from clinical notes is extremely time consuming. Natural language processing has been widely used in recent years for automatic information extraction from medical texts. However, algorithms trained on data from a single healthcare provider are not generalizable and error-prone due to the heterogeneity and uniqueness of medical documents. We develop a two-stage federated natural language processing method that enables utilization of clinical notes from different hospitals or clinics without moving the data, and demonstrate its performance using obesity and comorbities phenotyping as medical task. This approach not only improves the quality of a specific clinical task but also facilitates knowledge progression in the whole healthcare system, which is an essential part of learning health system. To the best of our knowledge, this is the first application of federated machine learning in clinical NLP.</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":" ","pages":"283-291"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8072229/pdf/nihms-1063931.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38915276","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: 58
We need to talk about standard splits. 我们需要讨论标准分割。
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2019-07-01 DOI: 10.18653/v1/p19-1267
Kyle Gorman, Steven Bedrick
{"title":"We need to talk about standard splits.","authors":"Kyle Gorman,&nbsp;Steven Bedrick","doi":"10.18653/v1/p19-1267","DOIUrl":"https://doi.org/10.18653/v1/p19-1267","url":null,"abstract":"<p><p>It is standard practice in speech & language technology to rank systems according to performance on a test set held out for evaluation. However, few researchers apply statistical tests to determine whether differences in performance are likely to arise by chance, and few examine the stability of system ranking across multiple training-testing splits. We conduct replication and reproduction experiments with nine part-of-speech taggers published between 2000 and 2018, each of which reports state-of-the-art performance on a widely-used \"standard split\". We fail to reliably reproduce some rankings using <i>randomly generated</i> splits. We suggest that randomly generated splits should be used in system comparison.</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"2019 ","pages":"2786-2791"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10287171/pdf/nihms-1908534.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9715654","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: 103
Multimodal Transformer for Unaligned Multimodal Language Sequences. 未对齐多模态语言序列的多模态变换器
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2019-07-01 DOI: 10.18653/v1/p19-1656
Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J Zico Kolter, Louis-Philippe Morency, Ruslan Salakhutdinov
{"title":"Multimodal Transformer for Unaligned Multimodal Language Sequences.","authors":"Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J Zico Kolter, Louis-Philippe Morency, Ruslan Salakhutdinov","doi":"10.18653/v1/p19-1656","DOIUrl":"10.18653/v1/p19-1656","url":null,"abstract":"<p><p>Human language is often multimodal, which comprehends a mixture of natural language, facial gestures, and acoustic behaviors. However, two major challenges in modeling such multimodal human language time-series data exist: 1) inherent data non-alignment due to variable sampling rates for the sequences from each modality; and 2) long-range dependencies between elements across modalities. In this paper, we introduce the Multimodal Transformer (MulT) to generically address the above issues in an end-to-end manner without explicitly aligning the data. At the heart of our model is the directional pairwise cross-modal attention, which attends to interactions between multimodal sequences across distinct time steps and latently adapt streams from one modality to another. Comprehensive experiments on both aligned and non-aligned multimodal time-series show that our model outperforms state-of-the-art methods by a large margin. In addition, empirical analysis suggests that correlated crossmodal signals are able to be captured by the proposed crossmodal attention mechanism in MulT.</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":" ","pages":"6558-6569"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7195022/pdf/nihms-1570579.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"37896067","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
Hybrid Attention based Multimodal Network for Spoken Language Classification. 用于口语分类的基于注意力的多模式混合网络。
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2018-08-01
Yue Gu, Kangning Yang, Shiyu Fu, Shuhong Chen, Xinyu Li, Ivan Marsic
{"title":"Hybrid Attention based Multimodal Network for Spoken Language Classification.","authors":"Yue Gu,&nbsp;Kangning Yang,&nbsp;Shiyu Fu,&nbsp;Shuhong Chen,&nbsp;Xinyu Li,&nbsp;Ivan Marsic","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>We examine the utility of linguistic content and vocal characteristics for multimodal deep learning in human spoken language understanding. We present a deep multimodal network with both feature attention and modality attention to classify utterance-level speech data. The proposed hybrid attention architecture helps the system focus on learning informative representations for both modality-specific feature extraction and model fusion. The experimental results show that our system achieves state-of-the-art or competitive results on three published multimodal datasets. We also demonstrated the effectiveness and generalization of our system on a medical speech dataset from an actual trauma scenario. Furthermore, we provided a detailed comparison and analysis of traditional approaches and deep learning methods on both feature extraction and fusion.</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"2018 ","pages":"2379-2390"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6217979/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41156853","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
Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment. 使用词级对齐的层次注意策略进行多模式情感分析。
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2018-07-01
Yue Gu, Kangning Yang, Shiyu Fu, Shuhong Chen, Xinyu Li, Ivan Marsic
{"title":"Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment.","authors":"Yue Gu,&nbsp;Kangning Yang,&nbsp;Shiyu Fu,&nbsp;Shuhong Chen,&nbsp;Xinyu Li,&nbsp;Ivan Marsic","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Multimodal affective computing, learning to recognize and interpret human affect and subjective information from multiple data sources, is still challenging because:(i) it is hard to extract informative features to represent human affects from heterogeneous inputs; (ii) current fusion strategies only fuse different modalities at abstract levels, ignoring time-dependent interactions between modalities. Addressing such issues, we introduce a hierarchical multimodal architecture with attention and word-level fusion to classify utterance-level sentiment and emotion from text and audio data. Our introduced model outperforms state-of-the-art approaches on published datasets, and we demonstrate that our model's synchronized attention over modalities offers visual interpretability.</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"2018 ","pages":"2225-2235"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6261375/pdf/nihms-993286.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41174352","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
Compositional Language Modeling for Icon-Based Augmentative and Alternative Communication. 基于图标的组合语言建模的辅助和替代交流。
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2018-07-01 DOI: 10.18653/v1/w18-3404
Shiran Dudy, Steven Bedrick
{"title":"Compositional Language Modeling for Icon-Based Augmentative and Alternative Communication.","authors":"Shiran Dudy,&nbsp;Steven Bedrick","doi":"10.18653/v1/w18-3404","DOIUrl":"https://doi.org/10.18653/v1/w18-3404","url":null,"abstract":"<p><p>Icon-based communication systems are widely used in the field of Augmentative and Alternative Communication. Typically, icon-based systems have lagged behind word- and character-based systems in terms of predictive typing functionality, due to the challenges inherent to training icon-based language models. We propose a method for synthesizing training data for use in icon-based language models, and explore two different modeling strategies.</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"2018 ","pages":"25-32"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8087438/pdf/nihms-1001619.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38939330","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: 12
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 : 2018-07-01
Braden Hancock, Martin Bringmann, Paroma Varma, Percy Liang, Stephanie Wang, Christopher Ré
{"title":"Training Classifiers with Natural Language Explanations.","authors":"Braden Hancock, Martin Bringmann, Paroma Varma, Percy Liang, Stephanie Wang, Christopher Ré","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"2018 ","pages":"1884-1895"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6534135/pdf/nihms-993798.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"37013648","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
A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature. 一个包含患者、干预措施和结果的多层次注释的语料库，以支持医学文献的语言处理。
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2018-07-01
Benjamin Nye, Junyi Jessy Li, Roma Patel, Yinfei Yang, Iain J Marshall, Ani Nenkova, Byron C Wallace
{"title":"A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature.","authors":"Benjamin Nye, Junyi Jessy Li, Roma Patel, Yinfei Yang, Iain J Marshall, Ani Nenkova, Byron C Wallace","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>We present a corpus of 5,000 richly annotated abstracts of medical articles describing clinical randomized controlled trials. Annotations include demarcations of text spans that describe the Patient population enrolled, the Interventions studied and to what they were Compared, and the Outcomes measured (the 'PICO' elements). These spans are further annotated at a more granular level, e.g., individual interventions within them are marked and mapped onto a structured medical vocabulary. We acquired annotations from a diverse set of workers with varying levels of expertise and cost. We describe our data collection process and the corpus itself in detail. We then outline a set of challenging NLP tasks that would aid searching of the medical literature and the practice of evidence-based medicine.</p>","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"2018 ","pages":"197-207"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6174533/pdf/nihms-988059.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41158894","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
A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature 支持医学文献语言处理的病人、干预和结果多层次注释语料库
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2018-06-11 DOI: 10.18653/v1/P18-1019
Benjamin E. Nye, Junyi Jessy Li, Roma Patel, Yinfei Yang, I. Marshall, A. Nenkova, Byron C. Wallace
{"title":"A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature","authors":"Benjamin E. Nye, Junyi Jessy Li, Roma Patel, Yinfei Yang, I. Marshall, A. Nenkova, Byron C. Wallace","doi":"10.18653/v1/P18-1019","DOIUrl":"https://doi.org/10.18653/v1/P18-1019","url":null,"abstract":"We present a corpus of 5,000 richly annotated abstracts of medical articles describing clinical randomized controlled trials. Annotations include demarcations of text spans that describe the Patient population enrolled, the Interventions studied and to what they were Compared, and the Outcomes measured (the ‘PICO’ elements). These spans are further annotated at a more granular level, e.g., individual interventions within them are marked and mapped onto a structured medical vocabulary. We acquired annotations from a diverse set of workers with varying levels of expertise and cost. We describe our data collection process and the corpus itself in detail. We then outline a set of challenging NLP tasks that would aid searching of the medical literature and the practice of evidence-based medicine.","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"120 1","pages":"197-207"},"PeriodicalIF":0.0,"publicationDate":"2018-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76655771","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: 162
Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment 基于层次注意策略的多模态情感分析
Proceedings of the conference. Association for Computational Linguistics. Meeting Pub Date : 2018-05-22 DOI: 10.18653/v1/P18-1207
Yue Gu, Kangning Yang, Shiyu Fu, Shuhong Chen, Xinyu Li, I. Marsic
{"title":"Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment","authors":"Yue Gu, Kangning Yang, Shiyu Fu, Shuhong Chen, Xinyu Li, I. Marsic","doi":"10.18653/v1/P18-1207","DOIUrl":"https://doi.org/10.18653/v1/P18-1207","url":null,"abstract":"Multimodal affective computing, learning to recognize and interpret human affect and subjective information from multiple data sources, is still a challenge because: (i) it is hard to extract informative features to represent human affects from heterogeneous inputs; (ii) current fusion strategies only fuse different modalities at abstract levels, ignoring time-dependent interactions between modalities. Addressing such issues, we introduce a hierarchical multimodal architecture with attention and word-level fusion to classify utterance-level sentiment and emotion from text and audio data. Our introduced model outperforms state-of-the-art approaches on published datasets, and we demonstrate that our model is able to visualize and interpret synchronized attention over modalities.","PeriodicalId":74541,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"68 1","pages":"2225-2235"},"PeriodicalIF":0.0,"publicationDate":"2018-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79113531","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: 100
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