Analyzing Errors of Neural Models in Named Entity Recognition

Simple item page
dc.contributorSolorio, Thamar
dc.contributor.authorParikh, Dwija
dc.date.accessioned2021-02-11T17:49:22Z
dc.date.available2021-02-11T17:49:22Z
dc.date.issued2020-09-29
dc.description.abstractDespite stellar performance on many NLP tasks, the behavior of neural models like BERT is not properly understood. We attempt to analyze the behavior and recognize patterns in errors for the NER task. We evaluate the predictions and errors generated to gain insight into the model's behavior Our findings show that there are underlying patterns leading to unintended memorization. Future research is required to address these errors and fine-tune the model.
dc.description.departmentComputer Science, Department of
dc.description.departmentHonors College
dc.identifier.urihttps://hdl.handle.net/10657/7484
dc.language.isoen_US
dc.relation.ispartofSummer Undergraduate Research Fellowship
dc.rightsThe author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s).
dc.titleAnalyzing Errors of Neural Models in Named Entity Recognition
dc.typePoster

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
PARIKH_DWIJA_2020URD.pdf
Size:
1.33 MB
Format:
Adobe Portable Document Format
Download

Collections

Undergraduate Research Day Student Projects