Robust to Noise Models in Natural Language Processing Tasks (2019-07-01T00:00:00.000000Z)

TL;DR

This work proposes robust to noise word embeddings model, which outperforms existing commonly used models, like fasttext and word2vec in different tasks, and investigates the noise robustness of current models in different natural language processing tasks.

Abstract

There are a lot of noise texts surrounding a person in modern life. The traditional approach is to use spelling correction, yet the existing solutions are far from perfect. We propose 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, which shows improvement in noise robustness over existing solutions.

Authors

Valentin Malykh

4 papers

TL;DR

Abstract

Authors

References33 items

Noise Robustness in Aspect Extraction Task

Named Entity Recognition in Noisy Domains

Deep Contextualized Word Representations

Fine-tuned Language Models for Text Classification

Application of a Hybrid Bi-LSTM-CRF model to the task of Russian Named Entity Recognition

Application of a Hybrid Bi-LSTM-CRF model to the task of Russian Named Entity Recognition

CAp 2017 challenge: Twitter Named Entity Recognition

Data Sets: Word Embeddings Learned from Tweets and General Data

Spelling Correction for Morphologically Rich Language: a Case Study of Russian

Two-stage approach in Russian named entity recognition

Enriching Word Vectors with Subword Information

Neural Architectures for Named Entity Recognition

Linear Algebraic Structure of Word Senses, with Applications to Polysemy

Character-Aware Neural Language Models

Construction of a Russian Paraphrase Corpus: Unsupervised Paraphrase Extraction

A large annotated corpus for learning natural language inference

Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation

Automatic Term Extraction for Sentiment Classification of Dynamically Updated Text Collections into Three Classes

Convolutional Neural Networks for Sentence Classification

Named Entity Recognition

Distributed Representations of Words and Phrases and their Compositionality

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

Turkish Paraphrase Corpus

Learning Word Vectors for Sentiment Analysis

Spoken Language Understanding: Systems for Extracting Semantic Information from Speech

Dialogue-Oriented Review Summary Generation for Spoken Dialogue Recommendation Systems

Unsupervised Construction of Large Paraphrase Corpora: Exploiting Massively Parallel News Sources

Spelling Correction as an Iterative Process that Exploits the Collective Knowledge of Web Users

Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition

Generalizable Architecture for Robust Word Vectors Tested by Noisy Paraphrases

An Unsupervised Neural Attention Model for Aspect Extraction

Beyond the Stars: Improving Rating Predictions using Review Text Content

Named Entity Recognition

Field of Study

Venue Information

Name

Type

URL

Alternate Names