Lydia Lazib - Academia.edu (original) (raw)

Lydia Lazib

Uploads

Papers by Lydia Lazib

Research paper thumbnail of Word Embeddings for a Disciplinary Tutoring System

2022 5th International Symposium on Informatics and its Applications (ISIA)

Research paper thumbnail of Disciplinary E-Tutoring Based on the Domain Ontology ONTO-TDM

2022 4th International Conference on Computer Science and Technologies in Education (CSTE)

Research paper thumbnail of A syntactic path-based hybrid neural network for negation scope detection

Frontiers of Computer Science, 2018

The automatic detection of negation is a crucial task in a wide-range of natural language process... more The automatic detection of negation is a crucial task in a wide-range of natural language processing (NLP) applications, including medical data mining, relation extraction, question answering, and sentiment analysis. In this paper, we present a syntactic path-based hybrid neural network architecture, a novel approach to identify the scope of negation in a sentence. Our hybrid architecture has the particularity to capture salient information to determine whether a token is in the scope or not, without relying on any human intervention. This approach combines a bidirectional long shortterm memory (Bi-LSTM) network and a convolutional neural network (CNN). The CNN model captures relevant syntactic features between the token and the cue within the shortest syntactic path in both constituency and dependency parse trees. The Bi-LSTM learns the context representation along the sentence in both forward and backward directions. We evaluate our model on the Bioscope corpus, and get 90.82% F-score (78.31% PCS) on the abstract sub-corpus, outperforming features-dependent approaches.

Research paper thumbnail of Word Embeddings for a Disciplinary Tutoring System

2022 5th International Symposium on Informatics and its Applications (ISIA)

Research paper thumbnail of Disciplinary E-Tutoring Based on the Domain Ontology ONTO-TDM

2022 4th International Conference on Computer Science and Technologies in Education (CSTE)

Research paper thumbnail of A syntactic path-based hybrid neural network for negation scope detection

Frontiers of Computer Science, 2018

The automatic detection of negation is a crucial task in a wide-range of natural language process... more The automatic detection of negation is a crucial task in a wide-range of natural language processing (NLP) applications, including medical data mining, relation extraction, question answering, and sentiment analysis. In this paper, we present a syntactic path-based hybrid neural network architecture, a novel approach to identify the scope of negation in a sentence. Our hybrid architecture has the particularity to capture salient information to determine whether a token is in the scope or not, without relying on any human intervention. This approach combines a bidirectional long shortterm memory (Bi-LSTM) network and a convolutional neural network (CNN). The CNN model captures relevant syntactic features between the token and the cue within the shortest syntactic path in both constituency and dependency parse trees. The Bi-LSTM learns the context representation along the sentence in both forward and backward directions. We evaluate our model on the Bioscope corpus, and get 90.82% F-score (78.31% PCS) on the abstract sub-corpus, outperforming features-dependent approaches.

Log In