42,175 Hits in 4.2 sec

Summarization as Indirect Supervision for Relation Extraction [article]

Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma, Muhao Chen
2022 arXiv   pre-print
We present SuRE, which converts RE into a summarization formulation. SuRE leads to more precise and resource-efficient RE based on indirect supervision from summarization tasks.  ...  Relation extraction (RE) models have been challenged by their reliance on training data with expensive annotations.  ...  We also perform comprehensive ablation studies to show the effectiveness of indirect supervision from summarization and best input conversion technique for SURE. Related Work Relation extraction.  ... 
arXiv:2205.09837v1 fatcat:oaix3dkdyraend4itjs5xzlm5a

Weakly Supervised Extractive Summarization with Attention

Yingying Zhuang, Yichao Lu, Simi Wang
2021 SIGDIAL Conferences  
In this paper, we develop a general framework that generates extractive summarization as a byproduct of supervised learning tasks for indirect signals via the help of attention mechanism.  ...  On the other hand, indirect signals for summarization are often available, such as agent actions for customer service dialogues, headlines for news articles, diagnosis for Electronic Health Records, etc  ...  Attention Based Extractive Summarization In this section, we propose a novel architecture that generates extractive summarization as a byproduct of the supervised learning tasks for indirect signals via  ... 
dblp:conf/sigdial/ZhuangLW21 fatcat:laian5c2tvai3j6upvrlyionoi

Life-iNet: A Structured Network-Based Knowledge Exploration and Analytics System for Life Sciences

Xiang Ren, Jiaming Shen, Meng Qu, Xuan Wang, Zeqiu Wu, Qi Zhu, Meng Jiang, Fangbo Tao, Saurabh Sinha, David Liem, Peipei Ping, Richard Weinshilboum (+1 others)
2017 Proceedings of ACL 2017, System Demonstrations  
These limitations are mainly due to the problems that factual information exists as an unstructured form in text, and also keyword and MeSH term-based queries cannot effectively imply semantic relations  ...  It also provides functionalities for finding distinctive entities for given entity types, and generating hypothetical facts to assist literaturebased knowledge discovery (e.g., drug target prediction).  ...  The views and conclusions contained in this paper are those of the authors and should not be interpreted as representing any funding agencies.  ... 
doi:10.18653/v1/p17-4010 dblp:conf/acl/RenSQWWZJTSLPWH17 fatcat:l4imv6rw6zeqzaxsroze3i4g4u

Improving Distantly Supervised Relation Extraction by Natural Language Inference [article]

Kang Zhou, Qiao Qiao, Yuepei Li, Qi Li
2022 arXiv   pre-print
To reduce human annotations for relation extraction (RE) tasks, distantly supervised approaches have been proposed, while struggling with low performance.  ...  The NLI-based indirect supervision acquires only one relation verbalization template from humans as a semantically general template for each relationship, and then the template set is enriched by high-quality  ...  Related Work Distantly Supervised Relation Extraction. Mintz et al. (2009) propose the DSRE task for the first time.  ... 
arXiv:2208.00346v1 fatcat:nzakmtb73vcdfhaxuxnmnannta

Multi-topical Discussion Summarization Using Structured Lexical Chains and Cue Words [chapter]

Jun Hatori, Akiko Murakami, Jun'ichi Tsujii
2011 Lecture Notes in Computer Science  
We propose a method to summarize threaded, multi-topical texts automatically, particularly online discussions and e-mail conversations.  ...  In experiments, we show the effectiveness of these features on the Innovation Jam 2008 Corpus and the BC3 Mailing List Corpus based on two task settings: key-sentence and keyword extraction.  ...  This work was partially supported by Grant-in-Aid for Specially Promoted Research (MEXT, Japan), and JSPS (Japan Society for the Promotion of Science) Research Fellowship.  ... 
doi:10.1007/978-3-642-19437-5_26 fatcat:3onxjgc6ivfmxi2lwbex4jfcce

Structured Output Learning with Indirect Supervision

Ming-Wei Chang, Vivek Srikumar, Dan Goldwasser, Dan Roth
2010 International Conference on Machine Learning  
While obtaining direct supervision for structures is difficult and expensive, it is often very easy to obtain indirect supervision from the companion binary decision problem.  ...  In this paper, we develop a large margin framework that jointly learns from both direct and indirect forms of supervision.  ...  Acknowledgment We thank Derek Hoiem and James Clarke for their insightful comments.  ... 
dblp:conf/icml/ChangSGR10 fatcat:77x2fm6dgrgjfnvsgjafcgz56a

Text Mining for Translational Bioinformatics

Hong-Jie Dai, Chih-Hsuan Wei, Hung-Yu Kao, Rey-Long Liu, Richard Tzong-Han Tsai, Zhiyong Lu
2015 BioMed Research International  
This approach is capable of finding both direct relations between diseases and genes as well as indirect obscure relationships among diseases and other biomedical entities.  ...  In the paper "Disease Related Knowledge Summarization Based on Deep Graph Search," X.  ...  Acknowledgments We would like to express our appreciation to all of the authors for their contributions and the reviewers for their support and constructive critiques in accomplishing this special issue  ... 
doi:10.1155/2015/368264 pmid:26380272 pmcid:PMC4563058 fatcat:mshc5klqsrb2vd7ik7jcauazey

Indirect Supervision for Relation Extraction using Question-Answer Pairs [article]

Zeqiu Wu, Xiang Ren, Frank F. Xu, Ji Li, Jiawei Han
2017 arXiv   pre-print
In this paper, we propose a novel framework, ReQuest, to leverage question-answer pairs as an indirect source of supervision for relation extraction, and study how to use such supervision to reduce noise  ...  Automatic relation extraction (RE) for types of interest is of great importance for interpreting massive text corpora in an efficient manner.  ...  The views and conclusions contained in this paper are those of the authors and should not be interpreted as representing any funding agencies.  ... 
arXiv:1710.11169v2 fatcat:hdvynvtiozecxgak2jeecx5x7e

An Unsupervised Text Mining Method for Relation Extraction from Biomedical Literature

Changqin Quan, Meng Wang, Fuji Ren, Gajendra P. S. Raghava
2014 PLoS ONE  
Dependency parsing and phrase structure parsing are combined for relation extraction.  ...  This paper presents an unsupervised method based on pattern clustering and sentence parsing to deal with biomedical relation extraction.  ...  Qiu defined two categories (direct and indirect dependency) to summarize all possible dependencies between two words in sentences [23] .  ... 
doi:10.1371/journal.pone.0102039 pmid:25036529 pmcid:PMC4103846 fatcat:nql5b24dbjho7emus6hcdavpdy

Characterizing classification datasets: a study of meta-features for meta-learning [article]

Adriano Rivolli, Luís P. F. Garcia, Carlos Soares, Joaquin Vanschoren, André C. P. L. F. de Carvalho
2019 arXiv   pre-print
Moreover, it presents MFE, a new tool for extracting meta-features from datasets and identifying more subtle reproducibility issues in the literature, proposing guidelines for data characterization that  ...  Such recommendations are made based on meta-data, consisting of performance evaluations of algorithms on prior datasets, as well as characterizations of these datasets.  ...  Supervised Indirect * P+T Both Yes [0, n] d No treeDepth Supervised Indirect * P+T Both Yes [1, n] n No treeImbalance Supervised Indirect * P+T Both Yes [0, 1] n No treeShape Supervised Indirect * P+T  ... 
arXiv:1808.10406v2 fatcat:2kqcwshj7rcfbbeo6qvz3ibkjq

Towards relation extraction from Arabic text: a review

Abeer AlArfaj
2019 International Robotics & Automation Journal  
In this paper, we present a review of the state of the art for relation extraction from texts, addressing the progress and difficulties in this field.  ...  Majority of relation extraction approaches implement a combination of statistical and linguistic techniques to extract semantic relations from text.  ...  AbdulMalik AlSalman for his valuable comments.  ... 
doi:10.15406/iratj.2019.05.00195 fatcat:2pep6mt7hbgxzmm55wcvxb5zre

Semantic role based sentence compression

Fatemeh Pourgholamali, Mohsen Kahani
2012 2012 2nd International eConference on Computer and Knowledge Engineering (ICCKE)  
The approach is applied in the context of multi-document summarization. Experiments showed better results than other state of the art approaches.  ...  As Filippova [3] noted, the average recall and precision for sentence compression are calculated as the amount of grammatical relations shared between standard grammatical relations and system output  ...  Our method is applied to the extracted sentences obtained from an extractive summarization method [15] .  ... 
doi:10.1109/iccke.2012.6395380 fatcat:o2ovzozpybbznh5zjdve27iyy4

Machine Learning with World Knowledge: The Position and Survey [article]

Yangqiu Song, Dan Roth
2017 arXiv   pre-print
knowledge linking and disambiguation, and learning with direct or indirect supervision.  ...  Machine learning has become pervasive in multiple domains, impacting a wide variety of applications, such as knowledge discovery and data mining, natural language processing, information retrieval, computer  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon.  ... 
arXiv:1705.02908v1 fatcat:t4fypa6h3vampcp64eosvppsfe

Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension [article]

Naoya Inoue, Harsh Trivedi, Steven Sinha, Niranjan Balasubramanian, Kentaro Inui
2021 arXiv   pre-print
The current strategies of identifying supporting sentences can be seen as an extractive question-focused summarization of the input text.  ...  However, these extractive explanations are not necessarily concise i.e. not minimally sufficient for answering a question.  ...  We thank the anonymous reviewers for the insightful feedback.  ... 
arXiv:2109.06853v1 fatcat:mdiqqhpitjesrap3ilgwld5rnu

Large-scale extraction of gene interactions from full-text literature using DeepDive

Emily K. Mallory, Ce Zhang, Christopher Ré, Russ B. Altman
2015 Bioinformatics  
For randomly curated extractions, the system achieved between 62% and 83% precision based on direct or indirect interactions, as well as sentence-level and document-level precision.  ...  For each candidate relation, DeepDive computed a probability that the relation was a correct interaction.  ...  Acknowledgements The authors would like to acknowledge Jaeho Shin, Matteo Riondato, Feiran Wang and Denny Britz for invaluable discussion and expertise with DeepDive.  ... 
doi:10.1093/bioinformatics/btv476 pmid:26338771 pmcid:PMC4681986 fatcat:oe33airyhvbxroebiwm2mnbon4
« Previous Showing results 1 — 15 out of 42,175 results