Filters








27,816 Hits in 5.5 sec

Using active learning to expand training data for implicit discourse relation recognition

Yang Xu, Yu Hong, Huibin Ruan, Jianmin Yao, Min Zhang, Guodong Zhou
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
Implicit relation recognition is challenging due to the lack of explicit relational clues.  ...  On the basis, we carry out an experiment of sampling, in which a simple active learning approach is used, so as to take the informative instances for data expansion.  ...  We focus on the implicit relation recognition in this paper, and follow Rutherford and Xue (2015) to strengthen the current neural discourse-level relation classification by expanding the training data  ... 
doi:10.18653/v1/d18-1079 dblp:conf/emnlp/XuHRYZZ18 fatcat:jr2fqlw7mjguvodgdq4bzbi6am

Self-organizing incremental and graph convolution neural network for English implicit discourse relation recognition

Yubo Geng
2021 EAI Endorsed Transactions on Scalable Information Systems  
Implicit discourse relation recognition is a sub-task of discourse relation recognition, which is challenging because it is difficult to learn the argument representation with rich semantic information  ...  To solve this problem, this paper proposes a self-organizing incremental and graph convolution neural network for English implicit discourse relation recognition.  ...  [27] used explicit discourse relational corpus to construct pseudo-implicit style examples, and selected samples with high information content based on active learning method to expand implicit discourse  ... 
doi:10.4108/eai.22-11-2021.172215 fatcat:dx4swsvbtnbw3bww3cxz6ohs7q

A Survey of Implicit Discourse Relation Recognition [article]

Wei Xiang, Bang Wang
2022 arXiv   pre-print
The task of implicit discourse relation recognition (IDRR) is to detect implicit relation and classify its sense between two text segments without a connective.  ...  This article provides a comprehensive and up-to-date survey for the IDRR task. We first summarize the task definition and data sources widely used in the field.  ...  Illustration of using a recurrent neural network for implicit discourse relation recognition.  ... 
arXiv:2203.02982v1 fatcat:ubublxw2fnfdpexgw4jslj76tm

A Recurrent Neural Model with Attention for the Recognition of Chinese Implicit Discourse Relations

Samuel Rönnqvist, Niko Schenk, Christian Chiarcos
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
We introduce an attention-based Bi-LSTM for Chinese implicit discourse relations and demonstrate that modeling argument pairs as a joint sequence can outperform word order-agnostic approaches.  ...  We also visualize its attention activity to illustrate the model's ability to selectively focus on the relevant parts of an input sequence.  ...  We are grateful to Farrokh Mehryary for technical support with the attention layer implementation.  ... 
doi:10.18653/v1/p17-2040 dblp:conf/acl/RonnqvistSC17 fatcat:v6epjjxqdrgcfegx7vdp7ucyt4

Adapting Event Embedding for Implicit Discourse Relation Recognition

Maria Leonor Pacheco, I-Ta Lee, Xiao Zhang, Abdullah Khan Zehady, Pranjal Daga, Di Jin, Ayush Parolia, Dan Goldwasser
2016 Proceedings of the CoNLL-16 shared task  
We model discourse arguments as a combination of word and event vectors. Event information is aggregated with word vectors and a Multi-Layer Neural Network is used to classify discourse senses.  ...  Predicting the sense of a discourse relation is particularly challenging when connective markers are missing.  ...  Implicit Discourse Relations Sense classification for implicit discourse relations is notoriously hard.  ... 
doi:10.18653/v1/k16-2019 dblp:conf/conll/PachecoLZZDJPG16 fatcat:6hopiufz3zfnxoyqpptt6rjmvy

Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation

Jinglin Liu, Yi Ren, Xu Tan, Chen Zhang, Tao Qin, Zhou Zhao, Tie-Yan Liu
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
We called our method as task-level curriculum learning for NAT (TCL-NAT).  ...  To smooth the shift from AT training to NAT training, in this paper, we introduce semi-autoregressive translation (SAT) as intermediate tasks.  ...  ., 2018] used active learning to sample explicitly-related arguments and expanded informative and reliable instances.  ... 
doi:10.24963/ijcai.2020/530 dblp:conf/ijcai/LiuOSJ20 fatcat:srxploensnb5jkftojqjpgdfjq

On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification [article]

Xin Liu, Jiefu Ou, Yangqiu Song, Xin Jiang
2020 arXiv   pre-print
We also analyze the effectiveness of different modules in the implicit discourse relation classification task and demonstrate how different levels of representation learning can affect the results.  ...  Implicit discourse relation classification is one of the most difficult parts in shallow discourse parsing as the relation prediction without explicit connectives requires the language understanding at  ...  ., 2018] used active learning to sample explicitly-related arguments and expanded informative and reliable instances.  ... 
arXiv:2004.12617v2 fatcat:msw4i3es5rcjfo5m5jqbtj36me

Application prospects for vector time maps of cognitive images links

E A Pustovoy, O A Pustovaya
2019 IOP Conference Series: Materials Science and Engineering  
Neural networks have a great advantage in the analysis of implicit dependencies, big data analysis, image recognition and other recognition systems.  ...  They are quite difficult to edit or create new structures based on existing trained models. They do not have the necessary flexibility and scalability in the process of learning and in use.  ...  Introduction Modern convolutional neural networks (CNN) have shown to good advantage in implicit dependencies analysis, Big Data analysis (BD), image recognition and other multiple classification systems  ... 
doi:10.1088/1757-899x/643/1/012108 fatcat:3ijpveeka5egffybdaqt3756ne

Automatic discourse connective detection in biomedical text

Balaji Polepalli Ramesh, Rashmi Prasad, Tim Miller, Brian Harrington, Hong Yu
2012 JAMIA Journal of the American Medical Informatics Association  
A first step in identifying discourse relations involves the detection of discourse connectives: words or phrases used in text to express discourse relations.  ...  In-domain supervised machine-learning classifiers were trained on the Biomedical Discourse Relation Bank, an annotated corpus of discourse relations over 24 full-text biomedical articles (w112 000 word  ...  The classifier was then trained using this weighted training dataset. Instance pruning actively removes misleading training instances.  ... 
doi:10.1136/amiajnl-2011-000775 pmid:22744958 pmcid:PMC3422833 fatcat:cg6viavcbjh2haokisj5ctd5xe

How to Make or Break Implicit Bias Instruction

Cristina M. Gonzalez, Ramya J. Garba, Alyssa Liguori, Paul R. Marantz, M. Diane McKee, Monica L. Lypson
2018 Academic Medicine  
related to implicit bias and the Implicit Association Test.  ...  Grounded theory methodology was used to analyze interview transcripts.  ...  Natalia Rodriguez for their generous assistance; and Dr. Paula Ross for her invaluable contributions to the revision.  ... 
doi:10.1097/acm.0000000000002386 pmid:30365433 pmcid:PMC6211195 fatcat:yrrbkby4wbhrvctpz4guub6zii

My pronouns are they/them: Talking about pronouns changes how pronouns are understood

Jennifer E. Arnold, Heather C. Mayo, Lisa Dong
2021 Psychonomic Bulletin & Review  
learn this fact through observation.  ...  Critically, the singular interpretation was stronger when participants heard explicit instructions that Alex uses they/them pronouns, even though participants in all conditions had ample opportunity to  ...  Acknowledgements We are grateful to Darith Klibanow for drawing the pictures of the characters in our survey.  ... 
doi:10.3758/s13423-021-01905-0 pmid:33945124 pmcid:PMC8094985 fatcat:nqo35ywzm5gelfy5ib2ek7ygrm

The biomedical discourse relation bank

Rashmi Prasad, Susan McRoy, Nadya Frid, Aravind Joshi, Hong Yu
2011 BMC Bioinformatics  
A biomedical text corpus annotated with discourse relations would be very useful for developing and evaluating methods for biomedical discourse processing.  ...  Results: We have developed the Biomedical Discourse Relation Bank (BioDRB), in which we have annotated explicit and implicit discourse relations in 24 open-access full-text biomedical articles from the  ...  We thank Geraud Campion for tool support. We are grateful to the anonymous reviewers for their helpful and insightful comments.  ... 
doi:10.1186/1471-2105-12-188 pmid:21605399 pmcid:PMC3130691 fatcat:sqdd6nz3qrbllb5haszd3kfsi4

Acronyms as an Integral Part of Multi-Word Term Recognition – A Token of Appreciation

Irena Spasic
2018 IEEE Access  
In terms of generality, heuristic approaches are preferred to machine learning ones as they are readily portable between domains and require no training.  ...  Our own algorithm for implicit acronym recognition was deliberately strict in order to achieve high precision.  ... 
doi:10.1109/access.2018.2807122 fatcat:f54bq3vuu5bdpp56pfkodulzka

Learning oral presentation skills

Richard J. Haber, Lorelei A. Lingard
2001 Journal of general internal medicine  
Discourse-based interviews of 8 students and 10 teachers. Data were quanlitatively analyzed to uncover recurrent patterns of communication.  ...  It has not previously been applied to medical discourse.  ...  those activities and the relations between research subjects.  ... 
doi:10.1046/j.1525-1497.2001.00233.x pmid:11359549 pmcid:PMC1495213 fatcat:2wot5b2mpvb6laqgfkxzbwxcie

Foreign Language Tutoring in Oral Conversations Using Spoken Dialog Systems

Sungjin LEE, Hyungjong NOH, Jonghoon LEE, Kyusong LEE, Gary Geunbae LEE
2012 IEICE transactions on information and systems  
The results showed that our CALL approaches can be enjoyable and fruitful activities for students.  ...  Although the results of this study bring us a step closer to understanding computer-based education, more studies are needed to consolidate the findings. key words: intelligent computer-assisted language  ...  They implemented the simulated user to produce example dialogs to expose language learners to language use and to expand the training corpus for the system.  ... 
doi:10.1587/transinf.e95.d.1216 fatcat:7ewddkfn45g3plz7wrwnyfnozi
« Previous Showing results 1 — 15 out of 27,816 results