Filters








23 Hits in 2.5 sec

Sortal anaphora resolution to enhance relation extraction from biomedical literature

Halil Kilicoglu, Graciela Rosemblat, Marcelo Fiszman, Thomas C. Rindflesch
2016 BMC Bioinformatics  
Results: We evaluated our sortal anaphora resolution method in several ways. The first evaluation specifically focused on sortal anaphora relations.  ...  We estimate that anaphora resolution results in changes in about 1.5 % of approximately 82 million semantic relations extracted from the entire PubMed.  ...  Castaño and Pustejovsky [2] found that approximately 60 % of anaphora instances in their corpus of MEDLINE abstracts were sortal.  ... 
doi:10.1186/s12859-016-1009-6 pmid:27080229 pmcid:PMC4832532 fatcat:7pfgl46einbtvfau7cyi3wduzq

What kind of problems do protein interactions raise for anaphora resolution? - A preliminary analysis

Olivia Sanchez-Graillet, Massimo Poesio, Mijail A. Kabadjov, Roman Tesar
2006 International Symposium for Semantic Mining in Biomedicine  
full texts as well as abstracts.  ...  We also studied the impact of anaphora resolution on protein interaction extraction, when an off-the-shelf anaphoric resolver (i.e., not one specially developed for this domain) is used, and looking at  ...  Medstract contains 32 Medline abstracts. We found 74 explicit anaphoric pairs across all the abstracts. Out of the 74 pairs, 24 are pronominal and 50 are sortal.  ... 
dblp:conf/smbm/Sanchez-Graillet06 fatcat:6wbv555pvfgsrgr3veutmvr4wu

Resolving "This-issue" Anaphora

Varada Kolhatkar, Graeme Hirst
2012 Conference on Empirical Methods in Natural Language Processing  
We propose a candidate ranking model for this-issue anaphora resolution that explores different issuespecific and general abstract-anaphora features.  ...  We annotate and resolve a particular case of abstract anaphora, namely, thisissue anaphora.  ...  observed that sortal anaphors are prevalent in the biomedical literature. They noted that among 100 distinct anaphors derived from a corpus of 70 Medline abstracts, 60% were sortal anaphors.  ... 
dblp:conf/emnlp/KolhatkarH12 fatcat:o2s4qaoxw5akjdwvnbkq3324iq

Broad-coverage biomedical relation extraction with SemRep

Halil Kilicoglu, Graciela Rosemblat, Marcelo Fiszman, Dongwook Shin
2020 BMC Bioinformatics  
In this paper, we present an in-depth description of SemRep, an NLP system that extracts semantic relations from PubMed abstracts using linguistic principles and UMLS domain knowledge.  ...  In ongoing development, we are redesigning SemRep to increase its modularity and flexibility, and addressing weaknesses identified in the error analysis.  ...  Sortal anaphora resolution in SemRep and its effect on relation extraction is discussed in depth in Kilicoglu et al. [50] .  ... 
doi:10.1186/s12859-020-3517-7 pmid:32410573 fatcat:2rsnzh7q4nghjdeh2kpqsxozyy

Coreference annotation and resolution in the Colorado Richly Annotated Full Text (CRAFT) corpus of biomedical journal articles

K. Bretonnel Cohen, Arrick Lanfranchi, Miji Joo-young Choi, Michael Bada, William A. Baumgartner, Natalya Panteleyeva, Karin Verspoor, Martha Palmer, Lawrence E. Hunter
2017 BMC Bioinformatics  
Coreference resolution is the task of finding strings in text that have the same referent as other strings.  ...  Failures of coreference resolution are a common cause of false negatives in information extraction from the scientific literature.  ...  guidelines; Massimo Poesio for helpful discussions; Guergana Savova for the scoring code that was used to calculate the inter-annotator agreement; and Sameer Pradhan for help with the CoNLL coreference resolution  ... 
doi:10.1186/s12859-017-1775-9 pmid:28818042 pmcid:PMC5561560 fatcat:iyhpkgis7fbopa7hfnz45f7hfe

Inferring Implicit Causal Relationships in Biomedical Literature

Halil Kilicoglu
2016 Proceedings of the 15th Workshop on Biomedical Natural Language Processing  
Inferring these discourse-level relations can be challenging in the absence of syntactic clues.  ...  However, a significant portion of such relations (in particular, causal relations) are expressed implicitly across sentence boundaries.  ...  To address anaphora, we include a binary feature that indicates whether the abstract contains any sortal anaphors that can refer to chemical or disease mentions (e.g., this drug, the condition).  ... 
doi:10.18653/v1/w16-2906 dblp:conf/bionlp/Kilicoglu16 fatcat:dvixzmljz5e5bmnriu274nt4uy

Relation Mining over a Corpus of Scientific Literature [chapter]

Fabio Rinaldi, Gerold Schneider, Kaarel Kaljurand, Michael Hess, Christos Andronis, Andreas Persidis, Ourania Konstanti
2005 Lecture Notes in Computer Science  
The amount of new discoveries (as published in the scientific literature) in the area of Molecular Biology is currently growing at an exponential rate.  ...  Therefore, there is a growing interest in text processing approaches that can deliver selected information from scientific publications, which can limit the amount of human intervention normally needed  ...  An advantage of their system is the anaphora resolution module, which can resolve many cases of pronominal anaphora and anaphora of the sortal type (e.g.  ... 
doi:10.1007/11527770_70 fatcat:bwmczbjm2jg2pabj3tvngami74

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

Pengcheng Lu, Massimo Poesio
2021 arXiv   pre-print
Thus, the biomedical genre has long been the second most researched genre for coreference resolution after the news domain, and the subject of a great deal of research for NLP in general.  ...  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.  ...  Acknowledgements This research was supported in part by the China Scholarship Council, and the DALI project, ERC Grant 695662.  ... 
arXiv:2109.12424v1 fatcat:tsuinvv5snburjgkkqkzyxoeky

Bio-SCoRes: A Smorgasbord Architecture for Coreference Resolution in Biomedical Text

Halil Kilicoglu, Dina Demner-Fushman, Tudor Groza
2016 PLoS ONE  
One of the difficulties in coreference resolution stems from the fact that distinct types of coreference (e.g., anaphora, appositive) are expressed with a variety of lexical and syntactic means (e.g.,  ...  In the current work, we aim to address some of these concerns regarding coreference resolution in biomedical text.  ...  We evaluated our results on MEDLINE abstracts in the same way.  ... 
doi:10.1371/journal.pone.0148538 pmid:26934708 pmcid:PMC4774913 fatcat:eqtpgxqjivg2rgn4oqbpbiiqqq

Anaphora and Coreference Resolution: A Review [article]

Rhea Sukthanker, Soujanya Poria, Erik Cambria, Ramkumar Thirunavukarasu
2018 arXiv   pre-print
The area of entity resolution in NLP has seen proliferation of research in two separate sub-areas namely: anaphora resolution and coreference resolution.  ...  Through this review article, we aim at clarifying the scope of these two tasks in entity resolution.  ...  It is mainly concerned with two types of anaphora namely pronominal and sortal anaphora.  ... 
arXiv:1805.11824v1 fatcat:ighrkr6f2nexphrw3qfojatmde

Biological event composition

Halil Kilicoglu, Sabine Bergler
2012 BMC Bioinformatics  
One notable feature of our system is that its performance across abstracts and articles bodies is stable. Coreference resolution results in minor improvement in system performance.  ...  The first competition (BioNLP'09) focused on extracting biological events from Medline abstracts from a narrow domain, while the theme of the latest competition (BioNLP-ST'11) was generalization and a  ...  The GENIA event corpus, for instance, contains only Medline abstracts on transcription factors in human blood cells.  ... 
doi:10.1186/1471-2105-13-s11-s7 pmid:22759461 pmcid:PMC3384260 fatcat:n25ycbxltnbnpfem64mvkotgk4

Challenges for automatically extracting molecular interactions from full-text articles

Tara McIntosh, James R Curran
2009 BMC Bioinformatics  
However, most Information Retrieval (IR) and Extraction (IE) tools currently process only abstracts.  ...  The traditional keyword-based Information Retrieval (IR) over abstracts often retrieves too many arti-  ...  We have separated the coreference expressions into three main groups: pronominal and sortal anaphora (anaphora), event anaphora, and cataphora.  ... 
doi:10.1186/1471-2105-10-311 pmid:19778419 pmcid:PMC2761905 fatcat:s6wm264gxjcw7ltw64lny5on2a

MCORES: a system for noun phrase coreference resolution for clinical records

Andreea Bodnari, Peter Szolovits, Özlem Uzuner
2012 JAMIA Journal of the American Medical Informatics Association  
In addition to the baseline, MCORES was compared against two available third-party, open-domain systems, RECONCILE ACL09 and the Beautiful Anaphora Resolution Toolkit (BART).  ...  Coreference resolution is a step in the transformation of narratives into a structured form.  ...  PS provided expertise in data analysis and reviewed and edited the manuscript.  ... 
doi:10.1136/amiajnl-2011-000591 pmid:22419739 pmcid:PMC3422821 fatcat:qs467xlwz5grdmdaebxrnuurf4

Accelerating COVID-19 Research with Graph Mining and Transformer-Based Learning

Ilya Tyagin, Ankit Kulshrestha, Justin Sybrandt, Krish Matta, Michael Shtutman, Ilya Safro
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
The systems are massively validated using retrospective information rediscovery and proactive analysis involving human-in-the-loop expert analysis.  ...  Both systems achieve high-quality predictions across domains in fast computational time and are released to the broad scientific community to accelerate biomedical research.  ...  SemRep also allows to perform optional sortal anaphora resolution to extract co-references to the entities from neighbouring sentences, which was shown to be useful in (Kilicoglu et al. 2016) and is  ... 
doi:10.1609/aaai.v36i11.21543 fatcat:obcxy5su6zejxjdmheuxjjgjfa

Mining metalinguistic activity in corpora to create lexical resources using information extraction techniques

Carlos Rodríguez Penagos
2004 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04  
The kind of categorization information implicit in many definitions can help improve anaphora resolution, semantic typing or acronym identification in these corpora, as well as enhance "semantic rerendering  ...  We have not included an anaphora-resolution module in our present system, so that instances 7, 8 and 10 will only display in the output as unresolved surface element or as existential variable place-holders  ... 
doi:10.3115/1218955.1218983 dblp:conf/acl/Penagos04 fatcat:bp5wupqb25cqjfctwnoln5xveu
« Previous Showing results 1 — 15 out of 23 results