Filters








518 Hits in 3.7 sec

Event Coreference Resolution: A Survey of Two Decades of Research

Jing Lu, Vincent Ng
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Being a core event-based task, event coreference resolution is less studied but arguably more challenging than entity coreference resolution.  ...  Recent years have seen a gradual shift of focus from entity-based tasks to event-based tasks in information extraction research.  ...  ACE 2005, the most widely used version of the ACE corpora for within-document event coreference evaluations, includes both English and Chinese documents.  ... 
doi:10.24963/ijcai.2018/773 dblp:conf/ijcai/LuN18 fatcat:x4d7nnuhgzbhhfcu6e2dlwln5a

Bootstrapped Training of Event Extraction Classifiers

Ruihong Huang, Ellen Riloff
2012 Conference of the European Chapter of the Association for Computational Linguistics  
Most event extraction systems are trained with supervised learning and rely on a collection of annotated documents.  ...  We aim to rapidly train a state-of-the-art event extraction system using a small set of "seed nouns" for each event role, a collection of relevant (in-domain) and irrelevant (outof-domain) texts, and a  ...  Propagating Labels with Coreference To enrich the automatically labeled training instances, we also propagate the event role labels across coreferent noun phrases within a document.  ... 
dblp:conf/eacl/HuangR12 fatcat:dovkkihaofalfgrvjobtawzjw4

A Hierarchical Distance-dependent Bayesian Model for Event Coreference Resolution [article]

Bishan Yang and Claire Cardie and Peter Frazier
2015 arXiv   pre-print
widely used in supervised coreference models to guide the generative clustering processing for better event clustering both within and across documents.  ...  Experiments on the ECB+ corpus show that our model outperforms state-of-the-art methods for both within- and cross-document event coreference resolution.  ...  It is usually considered a strong baseline for event coreference resolution. • AGGLOMERATIVE: a supervised clustering method for within-document event coreference (Chen et al., 2009) .  ... 
arXiv:1504.05929v2 fatcat:svbkjzmi65fptnnmr7shh36smi

A Hierarchical Distance-dependent Bayesian Model for Event Coreference Resolution

Bishan Yang, Claire Cardie, Peter Frazier
2015 Transactions of the Association for Computational Linguistics  
widely used in supervised coreference models to guide the generative clustering processing for better event clustering both within and across documents.  ...  Experiments on the ECB+ corpus show that our model outperforms state-of-the-art methods for both within- and cross-document event coreference resolution.  ...  It is usually considered a strong baseline for event coreference resolution. • AGGLOMERATIVE: a supervised clustering method for within-document event coreference (Chen et al., 2009) .  ... 
doi:10.1162/tacl_a_00155 fatcat:ylirhc6b25b4tdm2e2d36tizrq

Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events

Prafulla Kumar Choubey, Ruihong Huang
2017 Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing  
Among event mentions in the same chain, we distinguish within-and cross-document event coreference links by using two distinct pairwise classifiers, trained separately to capture differences in feature  ...  We introduce a novel iterative approach for event coreference resolution that gradually builds event clusters by exploiting inter-dependencies among event mentions within the same chain as well as across  ...  The neural net classifiers were trained using all coreferent event mention pairs including both within-document and cross-document ones.  ... 
doi:10.18653/v1/d17-1226 dblp:conf/emnlp/ChoubeyH17a fatcat:vf35lweuuncujevt5horgxbi54

Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events [article]

Prafulla Kumar Choubey, Ruihong Huang
2017 arXiv   pre-print
Among event mentions in the same chain, we distinguish within- and cross-document event coreference links by using two distinct pairwise classifiers, trained separately to capture differences in feature  ...  distributions of within- and cross-document event clusters.  ...  The neural net classifiers were trained using all coreferent event mention pairs including both within-document and cross-document ones.  ... 
arXiv:1707.07344v1 fatcat:m6ndz6wsqrelja2dqep6z6egze

Event Coreference Resolution Using Neural Network Classifiers [article]

Arun Pandian, Lamana Mulaffer, Kemal Oflazer, Amna AlZeyara
2018 arXiv   pre-print
This paper presents a neural network classifier approach to detecting both within- and cross- document event coreference effectively using only event mention based features.  ...  cross-document event coreference resolution.  ...  There are two types of event coreference resolution, within-document (WD) and cross-document (CD) event resolution.  ... 
arXiv:1810.04216v1 fatcat:lppm76h45rezrf4wvj5jxjnwl4

Entity, Relation, and Event Extraction with Contextualized Span Representations

David Wadden, Ulme Wennberg, Yi Luan, Hannaneh Hajishirzi
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
For instance, propagating span representations via predicted coreference links can enable the model to disambiguate challenging entity mentions.  ...  We examine the capabilities of a unified, multitask framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction.  ...  In coreference propagation, a span's neighbors in the graph are its likely coreference antecedents. In relation propagation, neighbors are related entities within a sentence.  ... 
doi:10.18653/v1/d19-1585 dblp:conf/emnlp/WaddenWLH19 fatcat:jsscal7pajayhlwbidqqeakun4

Revisiting the Evaluation for Cross Document Event Coreference

Shyam Upadhyay, Nitish Gupta, Christos Christodoulopoulos, Dan Roth
2016 International Conference on Computational Linguistics  
Our new evaluation setting better reflects the corpus-wide information aggregation ability of CDEC systems by separating event-coreference decisions made across documents from those made within a document  ...  Cross document event coreference (CDEC) is an important task that aims at aggregating eventrelated information across multiple documents.  ...  This work was supported by Contract HR0011-15-2-0025 with the US Defense Advanced Research Projects Agency (DARPA). Approved for Public Release, Distribution Unlimited.  ... 
dblp:conf/coling/UpadhyayGCR16 fatcat:q66qolut2jdk3a55wounkwwrka

Entity, Relation, and Event Extraction with Contextualized Span Representations [article]

David Wadden, Ulme Wennberg, Yi Luan, Hannaneh Hajishirzi
2019 arXiv   pre-print
For instance, propagating span representations via predicted coreference links can enable the model to disambiguate challenging entity mentions.  ...  We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction.  ...  In coreference propagation, a span's neighbors in the graph are its likely coreference antecedents. In relation propagation, neighbors are related entities within a sentence.  ... 
arXiv:1909.03546v2 fatcat:e6s2mtk2tne5jhzmkcan4oo2tu

A general framework for information extraction using dynamic span graphs

Yi Luan, Dave Wadden, Luheng He, Amy Shah, Mari Ostendorf, Hannaneh Hajishirzi
2019 Proceedings of the 2019 Conference of the North  
The dynamic span graph allows coreference and relation type confidences to propagate through the graph to iteratively refine the span representations.  ...  We introduce a general framework for several information extraction tasks that share span representations using dynamically constructed span graphs.  ...  information from relations and coreferences.  ... 
doi:10.18653/v1/n19-1308 dblp:conf/naacl/LuanWHSOH19 fatcat:fwvmu7ifz5d6fb36xcy5ho6igu

Identity and Granularity of Events in Text [article]

Piek Vossen, Agata Cybulska
2017 arXiv   pre-print
We compare these descriptions to solve a cross-document event coreference task. Our com- ponent approach to event semantics defines identity and granularity of events at different levels.  ...  It performs close to state-of-the-art approaches on the cross-document event coreference task, while outperforming other works when assuming similar quality of event detection.  ...  ", challenge 4.4 -Area Intelligent Information Management.  ... 
arXiv:1704.04259v1 fatcat:cot23g3ma5bhvopszwy4py3z3u

A General Framework for Information Extraction using Dynamic Span Graphs [article]

Yi Luan, Dave Wadden, Luheng He, Amy Shah, Mari Ostendorf, Hannaneh Hajishirzi
2019 arXiv   pre-print
The dynamic span graph allows coreference and relation type confidences to propagate through the graph to iteratively refine the span representations.  ...  We introduce a general framework for several information extraction tasks that share span representations using dynamically constructed span graphs.  ...  information from relations and coreferences.  ... 
arXiv:1904.03296v1 fatcat:mq6dvql3qfhfnmfqgu5kqcjhsq

Graph-Based Decoding for Event Sequencing and Coreference Resolution [article]

Zhengzhong Liu, Teruko Mitamura, Eduard Hovy
2018 arXiv   pre-print
Events in text documents are interrelated in complex ways. In this paper, we study two types of relation: Event Coreference and Event Sequencing.  ...  Empirically, our event coreference system has achieved state-of-the-art performance on the TAC-KBP 2015 event coreference task and our event sequencing system beats a strong temporal-based, oracle-informed  ...  ., 2012; Cybulska and Vossen, 2014) focuses on both within-document and cross-document coreference.  ... 
arXiv:1806.05099v1 fatcat:xkdzw3keeze3vglf6bfsuleh2m

End-to-End Neural Event Coreference Resolution [article]

Yaojie Lu and Hongyu Lin and Jialong Tang and Xianpei Han and Le Sun
2020 arXiv   pre-print
Traditional event coreference systems usually rely on pipeline framework and hand-crafted features, which often face error propagation problem and have poor generalization ability.  ...  In this paper, we propose an End-to-End Event Coreference approach -- E3C neural network, which can jointly model event detection and event coreference resolution tasks, and learn to extract features from  ...  Joint inference over a lightly supervised information extraction pipeline: Towards event coreference resolution for resource-scarce languages.  ... 
arXiv:2009.08153v1 fatcat:adytwu7sp5duzmvsifej6mqwt4
« Previous Showing results 1 — 15 out of 518 results