Biomedical relation extraction with pre-trained language representations and minimal task-specific architecture

no code implementations • WS 2019 • Ashok Thillaisundaram, Theodosia Togia

This paper presents our participation in the AGAC Track from the 2019 BioNLP Open Shared Tasks.

Language Modelling Relation +1

Constructing large scale biomedical knowledge bases from scratch with rapid annotation of interpretable patterns

no code implementations • WS 2019 • Julien Fauqueur, Ashok Thillaisundaram, Theodosia Togia

In this paper, we present a simple and effective method of extracting new facts with a pre-specified binary relationship type from the biomedical literature, without requiring any training data or hand-crafted rules.

Drug Discovery Knowledge Base Completion +1

The Effect of Negative Sampling Strategy on Capturing Semantic Similarity in Document Embeddings

no code implementations • WS 2017 • Marzieh Saeidi, Ritwik Kulkarni, Theodosia Togia, Michele Sama

Answer Selection Community Question Answering +2

TagNText: A parallel corpus for the induction of resource-specific non-taxonomical relations from tagged images

no code implementations • LREC 2014 • Theodosia Togia, Ann Copestake

In particular, our work attempts to answer the following questions: if users were to use full descriptions, would their current tags be words present in these hypothetical sentences?

Relation Extraction TAG