Papers by Paul Groth

2 papers
Open Information Extraction on Scientific Text: An Evaluation (C18-1)

Copied to clipboard

Challenge: Open Information Extraction (OIE) is the unsupervised creation of structured information from text.
Approach: They propose to use two state-of-the-art OIE systems to evaluate the performance of OIE on scientific texts originating from 10 different disciplines.
Outcome: The proposed methods perform significantly worse on scientific text than encyclopedic text.
Towards Entity Spaces (2020.lrec-1)

Copied to clipboard

Challenge: Entities are a central element of knowledge bases and are used in many knowledge-centric tasks including text analysis.
Approach: They propose to use entity spaces to represent a set of associated entities with near-identity to provide a handle to an amorphous grouping of entities.
Outcome: The proposed representations improve recall of entity linking in English by using disambiguation pages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations