Syntax-based Transfer Learning for the Task of Biomedical Relation Extraction

Joël Legrand 1 Yannick Toussaint 1 Chedy Raïssi 1 Adrien Coulet 1, 2
1 ORPAILLEUR - Knowledge representation, reasonning
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : Transfer learning (TL) proposes to enhance machine learning performance on a problem, by reusing labeled data originally designed for a related problem. In particular, domain adaptation consists, for a specific task, in reusing training data developed for the same task but a distinct domain. This is particularly relevant to the applications of deep learning in Natural Language Processing, because those usually require large annotated corpora that may not exist for the targeted domain, but exist for side domains. In this paper, we experiment with TL for the task of Relation Extraction (RE) from biomedical texts, using the TreeLSTM model. We empirically show the impact of TreeLSTM alone and with domain adaptation by obtaining better performances than the state of the art on two biomedical RE tasks and equal performances for two others, for which few annotated data are available. Furthermore, we propose an analysis of the role that syntactic features may play in TL for RE.
Complete list of metadatas

Cited literature [35 references]  Display  Hide  Download

https://hal.inria.fr/hal-01869071
Contributor : Joël Legrand <>
Submitted on : Thursday, September 6, 2018 - 11:13:38 AM
Last modification on : Tuesday, December 18, 2018 - 4:38:02 PM
Long-term archiving on : Friday, December 7, 2018 - 3:03:51 PM

File

louhi-syntax-based(1).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01869071, version 1

Collections

Citation

Joël Legrand, Yannick Toussaint, Chedy Raïssi, Adrien Coulet. Syntax-based Transfer Learning for the Task of Biomedical Relation Extraction. LOUHI 2018 - The Ninth International Workshop on Health Text Mining and Information Analysis, Oct 2018, Brussels, Belgium. ⟨hal-01869071⟩

Share

Metrics

Record views

267

Files downloads

312