Work

Robust to Noise Models in Natural Language Processing Tasks

Year: 2019

Type: conference-paper

Abstract: There are a lot of noisy texts surrounding a person in modern life.A traditional approach is to use spelling correction, yet the existing solutions are far from perfect.We propose a robust to noise word embeddings model which outperforms existing commonly used models like fasttext and word2vec in different tasks.In addition, we investigate the noise robustness of current models in different natural language processing tasks.We propose extensions for modern models in three downstream tasks, i.e. text classification, named entity recognition and aspect extraction, these extensions show improvement in noise robustness over existing solutions.

Source: Annual Meeting of the Association for Computational Linguistics: Student Research Workshop (ACL SRW)

DOI: 10.18653/v1/p19-2002

Author: Valentin Malykh

Institutions: Moscow Institute of Physics and Technology, St. Petersburg Department of Steklov Institute of Mathematics, Steklov Mathematical Institute

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W2951004499

FWCI: 0.765

Cites: 35

Cited by: 10

Related to: 10