[Colloquium] Qiming Wang MS Presentation/Dec 1, 2021

[meganwoodward at uchicago.edu]

This is an announcement of Qiming Wang's MS Presentation
===============================================
Candidate: Qiming Wang

Date: Wednesday, December 01, 2021

Time:  1:30 pm CST

Remote Location: https://uchicago.zoom.us/j/96972668372?pwd=WmVUOTZMNCttY3RiN2VJU21iNXVZUT09
Meeting ID: 969 7266 8372 Passcode: 265335

Location: JCL 298

M.S. Paper Title: FabricQA-Extractor: A Question Answering System to Extract Information from Documents using Natural Language Questions

Abstract: Reading comprehension models answer questions posed in natural language when provided with a short passage of text. They present an opportunity to address a long-standing challenge in data management: the extraction of structured data from unstructured text. Consequently, several approaches are using these models to perform information extraction. However, these modern approaches leave an opportunity behind by not exploiting the relational structure of the target extraction table. In this paper, we introduce a new model, Relation Coherence that exploits knowledge of the relational structure to improve the extraction quality. We incorporate the Relation Coherence model as part of FabricQA-Extractor, an end-to-end system we built from scratch to conduct large scale extraction tasks over millions of documents. We demonstrate on two datasets with millions of passages that Relation Coherence boosts extraction performance and evaluate FabricQA-Extractor on large scale datasets.

Advisors: Raul Castro Fernandez

Committee Members: Sanjay Krishnan, Aaron Elmore, and Raul Castro Fernandez