Filters








6,029 Hits in 2.9 sec

Model-based annotation of coreference [article]

Rahul Aralikatte, Anders Søgaard
2020 arXiv   pre-print
Humans do not make inferences over texts, but over models of what texts are about. When annotators are asked to annotate coreferent spans of text, it is therefore a somewhat unnatural task.  ...  Model-based annotation is shown to lead to faster annotation and higher inter-annotator agreement, and we argue that it also opens up for an alternative approach to coreference resolution.  ...  Acknowledgement We would like to thank all the members of CoAStaL NLP, Matt Lamm and Vidhyashree Murthy for their valuable feedback on the annotation interface.  ... 
arXiv:1906.10724v3 fatcat:fy2swe3lynb2lks52pcar7exge

Coreference Resolution for the Biomedical Domain: A Survey [article]

Pengcheng Lu, Massimo Poesio
2021 arXiv   pre-print
In recent years this interest has grown enormously leading to the development of a number of substantial datasets, of domain-specific contextual language models, and of several architectures.  ...  In this paper we review the state-of-the-art of coreference in the biomedical domain with a particular attention on these most recent developments.  ...  Machine learning-based models In the early years, due to the lack of publicly available annotated corpora, researchers have to annotate their own corpora for developing machine learning approaches (Yang  ... 
arXiv:2109.12424v1 fatcat:tsuinvv5snburjgkkqkzyxoeky

CoreLM: Coreference-aware Language Model Fine-Tuning [article]

Nikolaos Stylianou, Ioannis Vlahavas
2021 arXiv   pre-print
We also compare the models' performance in terms of Accuracy in LAMBADA and Children's Book Test, with and without the use of model-created coreference annotations.  ...  Language Models are the underpin of all modern Natural Language Processing (NLP) tasks.  ...  This research is co-financed by Greece and the European Union (European Social Fund -ESF) through the Operational Programme "Human Resources Development, Education and Lifelong Learning" in the context of  ... 
arXiv:2111.02687v1 fatcat:53g7vlswhrf6rgs4lfv3q52fci

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  
Recent years have seen a gradual shift of focus from entity-based tasks to event-based tasks in information extraction research.  ...  Being a core event-based task, event coreference resolution is less studied but arguably more challenging than entity coreference resolution.  ...  Acknowledgments We thank the two anonymous reviewers for their detailed comments on an earlier draft of the paper. This work was supported in part by NSF Grants IIS-1219142 and IIS-1528037.  ... 
doi:10.24963/ijcai.2018/773 dblp:conf/ijcai/LuN18 fatcat:x4d7nnuhgzbhhfcu6e2dlwln5a

Coreference Reasoning in Machine Reading Comprehension [article]

Mingzhu Wu, Nafise Sadat Moosavi, Dan Roth, Iryna Gurevych
2021 arXiv   pre-print
evaluate the ability of MRC models to reason about coreference.  ...  This allows us to show an improvement in the coreference reasoning abilities of state-of-the-art models.  ...  The first author of the paper is supported by a scholarship from Technical University of Darmstadt.  ... 
arXiv:2012.15573v2 fatcat:lxmoeb375neqjmvq6eaaq6zz4u

Rewarding Coreference Resolvers for Being Consistent with World Knowledge [article]

Rahul Aralikatte, Heather Lent, Ana Valeria Gonzalez, Daniel Hershcovich, Chen Qiu, Anders Sandholm, Michael Ringaard, Anders Søgaard
2019 arXiv   pre-print
We show how to improve coreference resolvers by forwarding their input to a relation extraction system and reward the resolvers for producing triples that are found in knowledge bases.  ...  Since relation extraction systems can rely on different forms of supervision and be biased in different ways, we obtain the best performance, improving over the state of the art, using multi-task reinforcement  ...  Chen Qiu is funded in part by the National Natural Science Foundation of China under grant No. 61773355 and the China Scholarship Council.  ... 
arXiv:1909.02392v2 fatcat:q6jgtusjkbh3rferfxlsecbvzi

Removing the Training Wheels: A Coreference Dataset that Entertains Humans and Challenges Computers

Anupam Guha, Mohit Iyyer, Danny Bouman, Jordan Boyd-Graber
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
We also successfully integrate active learning into this annotation pipeline to collect documents maximally useful to coreference models.  ...  annotation framework that can tag any text data with coreferences and named entities.  ...  Any opinions, findings, results, or recommendations expressed here are of the authors and do not necessarily reflect the view of the sponsor.  ... 
doi:10.3115/v1/n15-1117 dblp:conf/naacl/GuhaIBB15 fatcat:4tzxyh5kebggde6bwgcwmyotci

Rewarding Coreference Resolvers for Being Consistent with World Knowledge

Rahul Aralikatte, Heather Lent, Ana Valeria Gonzalez, Daniel Herschcovich, Chen Qiu, Anders Sandholm, Michael Ringaard, Anders Søgaard
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)  
Typed tensor decomposition of knowledge bases for relation extraction. In EMNLP. Kevin Clark and Christopher D Manning. 2016. Deep reinforcement learning for mention-ranking coreference models. In  ...  We show how to improve coreference resolvers by forwarding their input to a relation extraction system and reward the resolvers for producing triples that are found in knowledge bases.  ...  Chen Qiu is funded in part by the National Natural Science Foundation of China under grant No. 61773355 and the China Scholarship Council.  ... 
doi:10.18653/v1/d19-1118 dblp:conf/emnlp/AralikatteLGHQS19 fatcat:qvblhbwctnbsvpppmrvpphbaju

A Benchmark of Rule-Based and Neural Coreference Resolution in Dutch Novels and News [article]

Corbèn Poot, Andreas van Cranenburgh
2020 arXiv   pre-print
We evaluate a rule-based (Lee et al., 2013) and neural (Lee et al., 2018) coreference system on Dutch datasets of two domains: literary novels and news/Wikipedia text.  ...  The results provide insight into the relative strengths of data-driven and knowledge-driven systems, as well as the influence of domain, document length, and annotation schemes.  ...  Coreference was annotated from scratch (i.e., annotation did not proceed by correcting the output of a system), based on automatically extracted markables.  ... 
arXiv:2011.01615v1 fatcat:pohlqo2k5fhmhmisb7ufk6344i

Coreference based event-argument relation extraction on biomedical text

Katsumasa Yoshikawa, Sebastian Riedel, Tsutomu Hirao, Masayuki Asahara, Yuji Matsumoto
2011 Journal of Biomedical Semantics  
We propose two coreference-based models: a pipeline based on Support Vector Machine (SVM) classifiers, and a joint Markov Logic Network (MLN).  ...  We show the effectiveness of these models on a biomedical event corpus. The both models outperform the systems without coreference information.  ...  We propose two coreference-based models. One is an SVM based model that extracts intra-links first and then cross-links as a post-processing step.  ... 
doi:10.1186/2041-1480-2-s5-s6 pmid:22166257 pmcid:PMC3239306 fatcat:yrmsj5w44ve4fbykojlcaftuaq

A Probabilistic Annotation Model for Crowdsourcing Coreference

Silviu Paun, Jon Chamberlain, Udo Kruschwitz, Juntao Yu, Massimo Poesio
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
The results suggest that our model can extract from crowdsourced annotations coreference chains of comparable quality to those obtained with expert annotation.  ...  The availability of large scale annotated corpora for coreference is essential to the development of the field.  ...  Our proposal for a probabilistic model of this type of annotation is based on one of the most widely used models of coreference resolution: the mention pair model.  ... 
doi:10.18653/v1/d18-1218 dblp:conf/emnlp/PaunCKYP18 fatcat:6mhyg2gytvas7ehrvckg4lq2vm

Multilingual Coreference Resolution with Harmonized Annotations [article]

Ondřej Pražák, Miloslav Konopík, Jakub Sido
2021 arXiv   pre-print
Our results show that we can profit from harmonized annotations, and using joined models helps significantly for the languages with smaller training data.  ...  In this paper, we present coreference resolution experiments with a newly created multilingual corpus CorefUD.  ...  SGS-2019-018 Processing of heterogeneous data and its specialized applications.  ... 
arXiv:2107.12088v2 fatcat:re5j4t5yqvfh7ednnnuejfknke

CEREC: A Corpus for Entity Resolution in Email Conversations [article]

Parag Pravin Dakle, Dan I. Moldovan
2021 arXiv   pre-print
For the task of mention identification and coreference resolution, a best performance of 60.08 F1 is reported, highlighting the room for improvement.  ...  The corpus consists of 6001 email threads from the Enron Email Corpus containing 36,448 email messages and 60,383 entity coreference chains.  ...  Second, a VanillaSpanBERT model is trained on the coreference annotations of SC to obtain annotations on the MAC.  ... 
arXiv:2105.10606v1 fatcat:3aqpomyy4fcaffvaolcmyy7pky

Within-Document Event Coreference with BERT-Based Contextualized Representations [article]

Shafiuddin Rehan Ahmed, James H. Martin
2021 arXiv   pre-print
With the absence of any external knowledge bases for events, coreference becomes a clustering task that relies on effective representations of the context in which event mentions appear.  ...  We achieve state of the art results with this model on two standard datasets for within-document event coreference task and establish a new standard on a third newer dataset.  ...  Related Work A great deal of previous work is based on modeling the probability of coreference between pairs of mentions.  ... 
arXiv:2102.09600v1 fatcat:ocmnbryxsfen7bwvfgj7xaqrji

From concrete to virtual annotation mark-up language

Renata Vieira, Caroline Gasperin, Rodrigo Goulart, Susanne Salmon-Alt
2003 Proceedings of the ACL 2003 workshop on Linguistic annotation getting the model right -  
This work presents the data model we adopted for annotating coreference. Our data model includes different levels of annotation, such as part-of-speech, syntax and discourse.  ...  We also present our tool for coreference resolution that handles our data model.  ...  We would like to thank the help of Eckhard Bick, Christoph Müller, Michael Strube and Paulo Quaresma.  ... 
doi:10.3115/1119296.1119298 dblp:conf/acl/VieiraGGS03 fatcat:wnosyatolbfwlbj5btsxdzxvsq
« Previous Showing results 1 — 15 out of 6,029 results