277 Hits in 5.0 sec

Natural Language Processing for Information Extraction [article]

Sonit Singh
2018 arXiv   pre-print
Various sub-tasks of IE such as Named Entity Recognition, Coreference Resolution, Named Entity Linking, Relation Extraction, Knowledge Base reasoning forms the building blocks of various high end Natural  ...  This paper introduces Information Extraction technology, its various sub-tasks, highlights state-of-the-art research in various IE subtasks, current challenges and future research directions.  ...  Moreover, Cross-document coreference resolution (Gao et al., 2010) is at the research forefront in research community.  ... 
arXiv:1807.02383v1 fatcat:3bdyidbjp5hn7c2w4iqve4ajvi

HeidelToul: A Baseline Approach for Cross-document Event Ordering

Bilel Moulahi, Jannik Strötgen, Michael Gertz, Lynda Tamine
2015 Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)  
In this paper, we give an overview of our participation in the timeline generation task of SemEval-2015 (task 4, TimeLine: Cross-Document Event Ordering).  ...  For this, we developed an ad-hoc approach based on a temporal tagger and a coreference resolution tool for entities.  ...  Acknowledgments We thank the task organizers for their guidance and prompt support in all organizational matters.  ... 
doi:10.18653/v1/s15-2139 dblp:conf/semeval/MoulahiSGT15 fatcat:puoqcui4ujegxit4cjlk2veqb4

Type Prediction for Efficient Coreference Resolution in Heterogeneous Semantic Graphs

Jennifer Sleeman, Tim Finin
2013 2013 IEEE Seventh International Conference on Semantic Computing  
In the absence of known ontologies, performing coreference resolution can be challenging.  ...  We describe an approach for performing entity type recognition in heterogeneous semantic graphs in order to reduce the computational cost of performing coreference resolution.  ...  The term is also used for the more difficult task of linking expressions in multiple, independent documents, often described as cross-document coreference resolution [1] .  ... 
doi:10.1109/icsc.2013.22 dblp:conf/semco/SleemanF13 fatcat:zna7amykpzasdkqg5koq6cvyii

Big Data and Cross-Document Coreference Resolution: Current State and Future Opportunities [article]

Seyed-Mehdi-Reza Beheshti and Srikumar Venugopal and Seung Hwan Ryu and Boualem Benatallah and Wei Wang
2013 arXiv   pre-print
Among various IE tasks, extracting actionable intelligence from ever-increasing amount of data depends critically upon Cross-Document Coreference Resolution (CDCR) - the task of identifying entity mentions  ...  Recently, document datasets of the order of peta-/tera-bytes has raised many challenges for performing effective CDCR such as scaling to large numbers of mentions and limited representational power.  ...  The evaluation shows the viability and efficiency of using MapReduce in cross-document coreference resolution process.  ... 
arXiv:1311.3987v1 fatcat:qhpa2u4kavd5jjsjvepwrqweue

CIS at TAC Cold Start 2015: Neural Networks and Coreference Resolution for Slot Filling [article]

Heike Adel, Hinrich Schütze
2018 arXiv   pre-print
Our runs for the 2015 evaluation have been designed to directly assess the effect of each network on the end-to-end performance of the system.  ...  The CIS system achieved rank 3 of all slot filling systems participating in the task.  ...  We would like to thank Pankaj Gupta for his eager support with the RNN models.  ... 
arXiv:1811.02230v1 fatcat:wslvcg42hrdvdn4payikwgoj3m

Cross-document Event Identity via Dense Annotation [article]

Adithya Pratapa, Zhengzhong Liu, Kimihiro Hasegawa, Linwei Li, Yukari Yamakawa, Shikun Zhang, Teruko Mitamura
2021 arXiv   pre-print
We propose a dense annotation approach for cross-document event coreference, comprising a rich source of event mentions and a dense annotation effort between related document pairs.  ...  Prior work on cross-document event coreference has two main drawbacks. First, they restrict the annotations to a limited set of event types.  ...  The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the  ... 
arXiv:2109.06417v1 fatcat:6cwedtrjxrg7dkgzbozeteunhy

Multi-lingual Entity Discovery and Linking

Avi Sil, Heng Ji, Dan Roth, Silviu-Petru Cucerzan
2018 Proceedings of ACL 2018, Tutorial Abstracts  
Then we will proceed to cross-lingual neural EL and survey the pipelines that most of these EL systems employ: crosslingual NER and in-document coreference resolution.  ...  We will also present the models for traditional cross-lingual EL (Sil and Florian, 2016; Tsai and Roth, 2016) and discuss some of their challenges: matching context between non-English documents with  ... 
doi:10.18653/v1/p18-5008 dblp:conf/acl/SilJRC18 fatcat:zwhtjcdjnrc6zlcztuvdka2yxq

Entity extraction and disambiguation in finance

James A. Hodson, James Y. Zhang
2014 Proceedings of the first international workshop on Entity recognition & disambiguation - ERD '14  
, instant messaging, emails, and legal documents.  ...  This construction of the problem ignores or obscures the relationship between the phases of entity recognition and resolution, each of which depends heavily on the full stack of Natural Language Processing  ...  ", "World War I"), to entities that are statistically unlikely to be the argument of a coreferent relationship, are key specifiers for coherence relationships (e.g.  ... 
doi:10.1145/2633211.2633212 dblp:conf/sigir/HodsonZ14 fatcat:aw73c2o6xzc47ljcczhtdoqt2u

Discourse Coherence in the Wild: A Dataset, Evaluation and Methods

Alice Lai, Joel Tetreault
2018 Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue  
To address this, we present a new corpus of real-world texts (GCDC) as well as the first large-scale evaluation of leading discourse coherence algorithms.  ...  Acknowledgments The authors would like to thank Yahoo Research and Yelp for making their data available, and Ji-  ...  The coreference system yielded consistent performance improvements of 1-5% accuracy over the corresponding heuristic results, indicating that automatic coreference resolution can help entity-based models  ... 
doi:10.18653/v1/w18-5023 dblp:conf/sigdial/LaiT18 fatcat:etcfk3hs5vfozc62ul557gmthm

Discourse Coherence in the Wild: A Dataset, Evaluation and Methods [article]

Alice Lai, Joel Tetreault
2018 arXiv   pre-print
To address this, we present a new corpus of real-world texts (GCDC) as well as the first large-scale evaluation of leading discourse coherence algorithms.  ...  Acknowledgments The authors would like to thank Yahoo Research and Yelp for making their data available, and Ji-wei Li and Mohsen Mesgar for sharing their code.  ...  for their helpful comments.  ... 
arXiv:1805.04993v1 fatcat:2heidfd265eihngdqpuwz33nvy

A History and Theory of Textual Event Detection and Recognition

Yanping Chen, Zehua Ding, Qinghua Zheng, Yongbin Qin, Ruizhang Huang, Nazaraf Shah
2020 IEEE Access  
Other problems for coreference resolution are the large search space and unbalanced data.  ...  Coreference resolution also suffers from the feature sparsity problem.  ... 
doi:10.1109/access.2020.3034907 fatcat:ng7mbplve5dttao7ro6e2623ti

Using Semantic Linking to Understand Persons' Networks Extracted from Text

Alessio Palmero Aprosio, Sara Tonelli, Stefano Menini, Giovanni Moretti
2017 Frontiers in Digital Humanities  
The gold standard manually developed for evaluation shows that groups of co-occurring entities share in most of the cases a category that can be automatically assigned.  ...  The outcome of this work may be of interest to enhance the readability of large networks and to provide an additional semantic layer on top of cliques.  ...  We also analyze the impact of persons' disambiguation and coreference resolution on the task.  ... 
doi:10.3389/fdigh.2017.00022 fatcat:dqqnhx6qhbadjfw33idop6ajqu

Gesture Salience as a Hidden Variable for Coreference Resolution and Keyframe Extraction

J. Eisenstein, R. Barzilay, R. Davis
2008 The Journal of Artificial Intelligence Research  
We present conditional modality fusion, a conditional hidden-variable model that learns to predict which gestures are salient for coreference resolution, the task of determining whether two noun phrases  ...  In addition, we show that the model of gesture salience learned in the context of coreference accords with human intuition, by demonstrating that gestures judged to be salient by our model can be used  ...  Acknowledgments The authors acknowledge the editor and anonymous reviewers for their helpful comments. We also thank our colleagues Aaron Adler, S.  ... 
doi:10.1613/jair.2450 fatcat:qaula6fcjbfxrp3bwiuuo6n6py

Efficient Name Disambiguation for Large-Scale Databases [chapter]

Jian Huang, Seyda Ertekin, C. Lee Giles
2006 Lecture Notes in Computer Science  
We present an efficient integrative framework for solving the name disambiguation problem: a blocking method retrieves candidate classes of authors with similar names and a clustering method, DBSCAN, clusters  ...  Name disambiguation can occur when one is seeking a list of publications of an author who has used different name variations and when there are multiple other authors with the same name.  ...  This work was partially supported by grants from Microsoft Research and the National Science Foundation (NSF).  ... 
doi:10.1007/11871637_53 fatcat:e4pkgnrndjbshn7yv6tbzkbep4

BioNLP Shared Task - The Bacteria Track

Robert Bossy, Julien Jourde, Alain-Pierre Manine, Philippe Veber, Erick Alphonse, Maarten van de Guchte, Philippe Bessi.res, Claire N.dellec
2012 BMC Bioinformatics  
The three tasks of the Bacteria Track offer participants a chance to address a wide range of issues in Information Extraction, including entity recognition, semantic typing and coreference resolution.  ...  We describe the process of creation for the three corpora, including document acquisition and manual annotation, as well as the metrics used to evaluate the participants' submissions.  ...  The full contents of the supplement are available online at http://www.  ... 
doi:10.1186/1471-2105-13-s11-s3 pmid:22759457 pmcid:PMC3384254 fatcat:g44dq2dgq5f6jftar23f3mxufq
« Previous Showing results 1 — 15 out of 277 results