Spatial Role Labeling based on Improved Pre-trained Word Embeddings and Transfer Learning

In several real-world applications, extracting spatial semantics from text is critical. Spatial Role Labeling (SpRL) introduces a language-independent annotation scheme used in these applications, particularly for reasoning purposes. This paper proposes, first of all, a transfer learning method with...

Full description

Saved in:
Bibliographic Details
Published in:Procedia computer science 2021, Vol.192, p.1218-1226
Main Authors: Moussa, Alaeddine, Fournier, Sébastien, Mahmoudi, Khaoula, Espinasse, Bernard, Faiz, Sami
Format: Article
Language:English
Subjects:
Artificial Intelligence
Computer Science
Deep Learning
Natural language processing
Spatial Role Labeling
Transfer Learning
Word Embedding
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In several real-world applications, extracting spatial semantics from text is critical. Spatial Role Labeling (SpRL) introduces a language-independent annotation scheme used in these applications, particularly for reasoning purposes. This paper proposes, first of all, a transfer learning method with a word embeddings-based approach for SpRL. Then, we enhance the word vectors with POS tags and CNN-based character-level representations. Finally, we propose a Residual BiLSTM CRF deep learning model to identify the spatial roles. The experimental results on two datasets: SemEval-2012 and SemEval-2013 Task 3, show that the proposed model outperforms other machine learning approaches.
ISSN:1877-0509
1877-0509
DOI:10.1016/j.procs.2021.08.125