Filters








8,584 Hits in 3.5 sec

Temporal Reasoning on Implicit Events from Distant Supervision [article]

Ben Zhou and Kyle Richardson and Qiang Ning and Tushar Khot and Ashish Sabharwal and Dan Roth
2021 arXiv   pre-print
To address this, we propose a neuro-symbolic temporal reasoning model, SYMTIME, which exploits distant supervision signals from large-scale text and uses temporal rules to combine start times and durations  ...  This introduces a new challenge in temporal reasoning research, where prior work has focused on explicitly mentioned events.  ...  In summary, we make the following 3 contributions: (1) a temporal relation dataset TRACIE focusing on implicit events ( §3); (2) a distant supervision process for temporal understanding of implicit events  ... 
arXiv:2010.12753v2 fatcat:xyzyr2quljfolcs7gyvzeodnjy

Temporal Reasoning on Implicit Events from Distant Supervision

Ben Zhou, Kyle Richardson, Qiang Ning, Tushar Khot, Ashish Sabharwal, Dan Roth
2021 Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies   unpublished
To address this, we propose a neuro-symbolic temporal reasoning model, SYMTIME, which exploits distant supervision signals from largescale text and uses temporal rules to combine start times and durations  ...  This introduces a new challenge in temporal reasoning research, where prior work has focused on explicitly mentioned events.  ...  In summary, we make the following 3 contributions: (1) a temporal relation dataset TRACIE focusing on implicit events ( §3); (2) a distant supervision process for temporal understanding of implicit events  ... 
doi:10.18653/v1/2021.naacl-main.107 fatcat:y7qativf7zc5pdrvawtnbteuqa

CUNY BLENDER TAC-KBP2011 Temporal Slot Filling System Description

Javier Artiles, Qi Li, Taylor Cassidy, Suzanne Tamang, Heng Ji
2011 Text Analysis Conference  
In order to provide enough training data for these classifiers we used a distant supervision approach to automatically generate a large amount of training instances from the Web.  ...  We implemented a "structured" and a "flat" approach to the classification of temporal expressions.  ...  Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.  ... 
dblp:conf/tac/ArtilesLCTJ11 fatcat:enylabxqvbbhpagyq3jv7fl4vy

Effective Distant Supervision for Temporal Relation Extraction [article]

Xinyu Zhao, Shih-ting Lin, Greg Durrett
2021 arXiv   pre-print
We scrape and automatically label event pairs where the temporal relations are made explicit in text, then mask out those explicit cues, forcing a model trained on this data to learn other signals.  ...  We present a method of automatically collecting distantly-supervised examples of temporal relations.  ...  We present event-label tuples in Appendix D. MATRES Test Related Work There is little direct prior work on using this kind of distant supervision for temporal relation extraction.  ... 
arXiv:2010.12755v2 fatcat:omkd67k4kzgtpokljx2q6lki7y

Paragraph-level Commonsense Transformers with Recurrent Memory [article]

Saadia Gabriel, Chandra Bhagavatula, Vered Shwartz, Ronan Le Bras, Maxwell Forbes, Yejin Choi
2021 arXiv   pre-print
However, COMET was trained on commonsense inferences of short phrases, and is therefore discourse-agnostic.  ...  PARA-COMET captures both semantic knowledge pertaining to prior world knowledge, and episodic knowledge involving how current events relate to prior and future events in a narrative.  ...  distant supervision.  ... 
arXiv:2010.01486v2 fatcat:24db6xcsnffu7cnghfizyzxmce

UNED Slot Filling and Temporal Slot Filling systems at TAC KBP 2013: System description

Guillermo Garrido, Anselmo Peñas, Bernardo Cabaleiro
2013 Text Analysis Conference  
This is realized using distant supervision to match temporal information from a knowledge base and textual sources. Evidence is then aggregated into an imprecise temporal anchoring interval.  ...  For the Temporal Slot Filling task, our approach is based on learning the temporal link between relation mentions and previously identified contextual temporal expressions.  ...  scope of training examples to sentences, although co-reference allows to gather information from different parts of the documents; (4) in the Temporal Slot Filling task, we have integrated distant supervision  ... 
dblp:conf/tac/GarridoPC13 fatcat:2u4wwlunevha3p477q6rmgshgu

Extracting event and their relations from texts: A survey on recent research progress and challenges

Kang Liu, Yubo Chen, Jian Liu, Xinyu Zuo, Jun Zhao
2020 AI Open  
In event relation extraction, we focus on the extraction approaches for three typical event relation types, including coreference, causal and temporal relations, respectively.  ...  How to identify events from texts, extract their arguments, even analyze the relations between different events are important for many applications.  ...  Distant supervised data generation Works on distant supervised data generation aim to generate largescale labeled data by distant supervision automatically.  ... 
doi:10.1016/j.aiopen.2021.02.004 fatcat:qxbcmk55vzcb5nznhgfgwrbe4u

SemEval-2015 Task 5: QA TempEval - Evaluating Temporal Information Understanding with Question Answering

Hector Llorens, Nathanael Chambers, Naushad UzZaman, Nasrin Mostafazadeh, James Allen, James Pustejovsky
2015 Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)  
Features that helped achieve better results are event coreference and a time expression reasoner.  ...  Evaluation results show that the best automated TimeML annotations reach over 30% recall on questions with 'yes' answer and about 50% on easier questions with 'no' answers.  ...  Acknowledgments We want to thank participant Paramita Mirza for her collaboration on reviewing and correcting the test data, and also Marc Verhagen and Roser Sauri for their help on approximating the time-cost  ... 
doi:10.18653/v1/s15-2134 dblp:conf/semeval/LlorensCUMAP15 fatcat:udyco4aefbe5xbmd2eamzd5mmq

Which Semantics for Requirements Engineering: From Shallow to Deep

Roberto Garigliano, Dominic Perini, Luisa Mich
2018 Requirements Engineering: Foundation for Software Quality  
future generation of natural language processing systems needs a deep semantics, that is a representation of the content independent of the surface description, which represents hidden casual, spatial, temporal  ...  of system analysis improved by hand); use this with a suitable fitness function [Kra17] to improve large scale testing of the system; improve the system itself by deploying genetic algorithms based on  ...  More importantly from the point of view of discourse analysis, such basic units are also positioned with respect to one another, e.g. for space correlations (event A taking place 50 meters from Event B  ... 
dblp:conf/refsq/GariglianoPM18 fatcat:bqpj4kcj6vd4xotyprhyskv72e

Temporal data representation, normalization, extraction, and reasoning: A review from clinical domain

Mohcine Madkour, Driss Benhaddou, Cui Tao
2016 Computer Methods and Programs in Biomedicine  
However, temporal data representation, normalization, extraction and reasoning are very important in order to mine such massive data and therefore for constructing the clinical timeline.  ...  The review emphasis on the current existing gap between present methods and the semantic web technologies and catch up with the possible combinations.  ...  Many efforts have picked up from the latest works on reasoning about temporal relations.  ... 
doi:10.1016/j.cmpb.2016.02.007 pmid:27040831 pmcid:PMC4837648 fatcat:a75g25csqzdvlkfusbbgwmxigq

Literature survey of temporal data models

2017 International Journal of Latest Trends in Engineering and Technology  
going on from last two decades.  ...  Attribute values are functions from temporal elements onto attribute value domain, but not on the same temporal element. Hence, lack in temporal homogeneity.  ... 
doi:10.21172/1.841.47 fatcat:odbedlm2zrabrkqf3xnjroei5q

Recognizing Explicit and Implicit Hate Speech Using a Weakly Supervised Two-path Bootstrapping Approach [article]

Lei Gao, Alexis Kuppersmith, Ruihong Huang
2018 arXiv   pre-print
Applying this model on a large quantity of tweets collected before, after, and on election day reveals motivations and patterns of inflammatory language.  ...  To address various limitations of supervised hate speech classification methods including corpus bias and huge cost of annotation, we propose a weakly supervised two-path bootstrapping approach for an  ...  Tackling Semantic Drifts Semantic drift is the most challenging problem in distant supervision and bootstrapping.  ... 
arXiv:1710.07394v2 fatcat:te3sqzclpbbqpo67mmq4w247ni

Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences

Zhu Zhang, Zhou Zhao, Yang Zhao, Qi Wang, Huasheng Liu, Lianli Gao
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Thus, we then propose a novel Spatio-Temporal Graph Reasoning Network (STGRN) for this task.  ...  First, we build a spatiotemporal region graph to capture the region relationships with temporal object dynamics, which involves the implicit and explicit spatial subgraphs in each frame and the temporal  ...  Different from them, our spatio-temporal region graph not only involves the implicit and explicit spatial subgraphs in each frame, but also includes a temporal dynamic subgraph across frames.  ... 
doi:10.1109/cvpr42600.2020.01068 dblp:conf/cvpr/ZhangZZWLG20 fatcat:umcnf6qsajcezfx6k2sa2a6t5e

RPI-BLENDER TAC-KBP2013 Knowledge Base Population System

Dian Yu, Haibo Li, Taylor Cassidy, Qi Li, Hongzhao Huang, Zheng Chen, Heng Ji, Yongzhong Zhang, Dan Roth
2013 Text Analysis Conference  
This year the RPI-BLENDER team participated in the following four tasks: English Entity Linking, Regular Slot Filling, Temporal Slot Filling and Slot Filling Validation.  ...  In addition, we submitted two additional runs using temporal reasoning with event ordering constraints, based on collaboration with UIUC (Do et al., 2012) .  ...  the distant supervision assumption).  ... 
dblp:conf/tac/YuLCLHCJZR13 fatcat:prighf7bu5gd5gti5uz35hmh5m

Embedding Time Expressions for Deep Temporal Ordering Models

Tanya Goyal, Greg Durrett
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
on an automatically collected dataset with more frequent event-timex interactions. 1  ...  We evaluate the utility of these embeddings in the context of a strong neural model for event temporal ordering, and show a small increase in performance on the MATRES dataset and more substantial gains  ...  Additionally, to evaluate the full potential of the proposed approach, we construct another dataset with more frequent event-timex interactions using distant supervision.  ... 
doi:10.18653/v1/p19-1433 dblp:conf/acl/GoyalD19 fatcat:xlg4anjlsjboxiesyuitypw5ie
« Previous Showing results 1 — 15 out of 8,584 results