paper-with-me

홈 › Papers

A Comparison of Word-based and Context-based Representations for Classification Problems in Health Informatics

2019-06-13 · WS 2019 8 · Aditya Joshi, Sarvnaz Karimi, Ross Sparks, Cecile Paris, C Raina MacIntyre

Distributed representations of text can be used as features when training a statistical classifier. These representations may be created as a composition of word vectors or as context-based sentence vectors. We compare the two kinds of representations (word versus context) for three classification problems: influenza infection classification, drug usage classification and personal health mention classification. For statistical classifiers trained for each of these problems, context-based representations based on ELMo, Universal Sentence Encoder, Neural-Net Language Model and FLAIR are better than Word2Vec, GloVe and the two adapted using the MESH ontology. There is an improvement of 2-4% in the accuracy when these context-based representations are used instead of word-based representations.

📄 PDF Abstract BibTeX arXiv:1906.05468

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral ClassificationLanguage ModelingLanguage ModellingSentence

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
ELMo Embeddings from Language Models, or ELMo, is a type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and…
GloVe GloVe Embeddings are a type of word embedding that encode the co-occurrence probability ratio between two words as vector differences. GloVe uses a weighted least squares…

Similar Papers 제목 키워드 기반

A Comparison of Context-sensitive Models for Lexical Substitution

2019-05-01 · WS 2019 5 · Aina Gar{\'\i} Soler, Anne Cocos, Marianna Apidianaki, Chris Callison-Burch

Word embedding representations provide good estimates of word meaning and give state-of-the art performance in semantic tasks. Embedding approaches differ as to whether and how they account for the context surrounding a …

Word Embeddings

Comparison of Turkish Word Representations Trained on Different Morphological Forms

2020-02-13 · Gökhan Güler, A. Cüneyd Tantuğ

Increased popularity of different text representations has also brought many improvements in Natural Language Processing (NLP) tasks. Without need of supervised data, embeddings trained on large corpora provide us meanin…

Language ModelingLanguage ModellingLEMMAtext-classification+1

Comparing Text Representations: A Theory-Driven Approach

2021-09-15 · EMNLP 2021 11 · Gregory Yauney, David Mimno

Much of the progress in contemporary NLP has come from learning representations, such as masked language model (MLM) contextual embeddings, that turn challenging problems into simple classification tasks. But how do we q…

Language ModelingLanguage ModellingLearning TheoryNatural Language Inference

Comparative Analysis of Text Classification Approaches in Electronic Health Records

2020-05-08 · WS 2020 7 · Aurelie Mascio, Zeljko Kraljevic, Daniel Bean, Richard Dobson 외

Text classification tasks which aim at harvesting and/or organizing information from electronic health records are pivotal to support clinical and translational research. However these present specific challenges compare…

ClassificationGeneral Classificationtext-classificationText Classification

Word Usage Similarity Estimation with Sentence Representations and Automatic Substitutes

2019-05-20 · SEMEVAL 2019 6 · Aina Garí Soler, Marianna Apidianaki, Alexandre Allauzen

Usage similarity estimation addresses the semantic proximity of word instances in different contexts. We apply contextualized (ELMo and BERT) word and sentence embeddings to this task, and propose supervised models that …

SentenceSentence Embeddings