scholarly journals Multi-Task Learning for Metaphor Detection with Graph Convolutional Neural Networks and Word Sense Disambiguation

2020 ◽  
Vol 34 (05) ◽  
pp. 8139-8146
Author(s):  
Duong Le ◽  
My Thai ◽  
Thien Nguyen
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Word Sense Disambiguation ◽  
Word Sense ◽  
Knowledge Resources ◽  
Useful Knowledge ◽  
Learning Framework ◽  
Task Learning ◽  
Sense Disambiguation

The current deep learning works on metaphor detection have only considered this task independently, ignoring the useful knowledge from the related tasks and knowledge resources. In this work, we introduce two novel mechanisms to improve the performance of the deep learning models for metaphor detection. The first mechanism employs graph convolutional neural networks (GCN) with dependency parse trees to directly connect the words of interest with their important context words for metaphor detection. The GCN networks in this work also present a novel control mechanism to filter the learned representation vectors to retain the most important information for metaphor detection. The second mechanism, on the other hand, features a multi-task learning framework that exploits the similarity between word sense disambiguation and metaphor detection to transfer the knowledge between the two tasks. The extensive experiments demonstrate the effectiveness of the proposed techniques, yielding the state-of-the-art performance over several datasets.

scholarly journals Abstractive text summarization: enhancing sequence to sequence models using word sense disambiguation and semantic content generalization

2021 ◽  
pp. 1-41
Author(s):  
Panagiotis Kouris ◽  
Georgios Alexandridis ◽  
Andreas Stafylopatis
Keyword(s):  
Deep Learning ◽  
Heuristic Algorithms ◽  
Word Sense Disambiguation ◽  
Text Summarization ◽  
Word Sense ◽  
Post Processing ◽  
Knowledge Resources ◽  
Processing Task ◽  
Knowledge Based ◽  
Sense Disambiguation

Abstract Nowadays, most research conducted in the field of abstractive text summarization focuses on neural-based models alone, without considering their combination with knowledge-based that could further enhance their efficiency. In this direction, this work presents a novel framework that combines sequence to sequence neural-based text summarization along with structure and semantic-based methodologies. The proposed framework is capable of dealing with the problem of out-of-vocabulary or rare words, improving the performance of the deep learning models. The overall methodology is based on a well defined theoretical model of knowledge-based content generalization and deeplearning predictions for generating abstractive summaries. The framework is comprised of three key elements: (i) a pre-processing task, (ii) a machine learning methodology and (iii) a post-processing task. The pre-processing task is a knowledge-based approach, based on ontological knowledge resources, word-sense-disambiguation and namedentity recognition, along with content generalization, that transforms ordinary text into a generalized form. A deep learning model of attentive encoder-decoder architecture, which is expanded to enable a coping and coverage mechanism, as well as reinforcement learning and transformer-based architectures, is trained on a generalized version of text-summary pairs, learning to predict summaries in a generalized form. The post-processing task utilizes knowledge resources, word embeddings, word-sense disambiguation and heuristic algorithms based on text similarity methods in order to transform the generalized version of a predicted summary to a final, humanreadable form. An extensive experimental procedure on three popular datasets evaluates key aspects of the proposed framework, while the obtained results exhibit promising performance, validating the robustness of the proposed approach.

scholarly journals Toward Universal Word Sense Disambiguation Using Deep Neural Networks

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 60264-60275 ◽  
Author(s):  
Hiram Calvo ◽  
Arturo P. Rocha-Ramirez ◽  
Marco A. Moreno-Armendariz ◽  
Carlos A. Duchanoy
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Word Sense Disambiguation ◽  
Word Sense ◽  
Sense Disambiguation

Evolving Neural Networks for Word Sense Disambiguation

2008 ◽  
Author(s):  
A. Azzini ◽  
C. da Costa Pereira ◽  
M. Dragoni ◽  
A.G.B. Tettamanzi
Keyword(s):  
Neural Networks ◽  
Word Sense Disambiguation ◽  
Word Sense ◽  
Sense Disambiguation

scholarly journals Knowledge-Based Method for Word Sense Disambiguation by Using Hindi WordNet

2019 ◽  
Vol 9 (2) ◽  
pp. 3985-3989 ◽  
Author(s):  
P. Sharma ◽  
N. Joshi
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Speech Processing ◽  
Text Processing ◽  
Word Sense Disambiguation ◽  
Problem Area ◽  
Word Sense ◽  
Knowledge Resources ◽  
Knowledge Based ◽  
Sense Disambiguation

The purpose of word sense disambiguation (WSD) is to find the meaning of the word in any context with the help of a computer, to find the proper meaning of a lexeme in the available context in the problem area and the relationship between lexicons. This is done using natural language processing (NLP) techniques which involve queries from machine translation (MT), NLP specific documents or output text. MT automatically translates text from one natural language into another. Several application areas for WSD involve information retrieval (IR), lexicography, MT, text processing, speech processing etc. Using this knowledge-based technique, we are investigating Hindi WSD in this article. It involves incorporating word knowledge from external knowledge resources to remove the equivocalness of words. In this experiment, we tried to develop a WSD tool by considering a knowledge-based approach with WordNet of Hindi. The tool uses the knowledge-based LESK algorithm for WSD for Hindi. Our proposed system gives an accuracy of about 71.4%.

Sign in / Sign up

Export Citation Format

Share Document