Building effective representations for domain adaptation in coreference resolution

Simple item page
dc.contributor.advisorDurrett, Greg
dc.creatorLestari, Victoria Anugrah
dc.creator.orcid0000-0003-3407-5185
dc.date.accessioned2018-08-29T22:21:31Z
dc.date.available2018-08-29T22:21:31Z
dc.date.created2018-05
dc.date.issued2018-05-04
dc.date.submittedMay 2018
dc.date.updated2018-08-29T22:21:31Z
dc.description.abstractOver the past few years, research in coreference resolution, one of the core tasks in Natural Language processing, has displayed significant improvement. However, the field of domain adaptation in coreference resolution is yet to be explored; Moosavi and Strube [2017] have shown that the performance of state-of-the-art coreference resolution systems drop when the systems are tested on datasets from different domains. We modify e2e-coref [Lee et al., 2017], a state-of-the-art coreference resolution system, to perform well on new domains by adding sparse linguistic features, incorporating information from Wikipedia, and implementing a domain adversarial network to the system. Our experiments show that each modification improves the precision of the system. We train the model on CoNLL-2012 datasets and test it on several datasets: WikiCoref, the pt documents, and the wb documents from CoNLL-2012. Our best results gains 0.50, 0.52, and 1.14 F1 improvements over the baselines of the respective test sets.
dc.description.departmentComputer Science
dc.format.mimetypeapplication/pdf
dc.identifierdoi:10.15781/T2NP1X34P
dc.identifier.urihttp://hdl.handle.net/2152/68211
dc.language.isoen
dc.subjectDomain adaptation
dc.subjectDomain adversarial
dc.subjectCoreference resolution
dc.subjectWikipedia
dc.subjectInformation extraction
dc.subjectNatural language processing
dc.subjectNeural network
dc.titleBuilding effective representations for domain adaptation in coreference resolution
dc.typeThesis
dc.type.materialtext
thesis.degree.departmentComputer Sciences
thesis.degree.disciplineComputer Science
thesis.degree.grantorThe University of Texas at Austin
thesis.degree.levelMasters
thesis.degree.nameMaster of Science in Computer Sciences

Access full-text files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
LESTARI-THESIS-2018.pdf
Size:
689.57 KB
Format:
Adobe Portable Document Format
Description:
Download

License bundle

Now showing 1 - 3 of 3
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
4.46 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
1.85 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LESTARI2018_wvita.pdf
Size:
708.61 KB
Format:
Adobe Portable Document Format
Description:
Original thesis with vita
Download

Collections

UT Electronic Theses and Dissertations