A survey of word embeddings based on deep learning

The representational basis for downstream natural language processing tasks is word embeddings, which capture lexical semantics in numerical form to handle the abstract semantic concept of words. Recently, the word embeddings approaches, represented by deep learning, has attracted extensive attentio...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computing Ročník 102; číslo 3; s. 717 - 740
Hlavní autori: Wang, Shirui, Zhou, Wenan, Jiang, Chao
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Vienna Springer Vienna 01.03.2020
Springer Nature B.V
Predmet:
Artificial Intelligence
Computer Appl. in Administrative Data Processing
Computer Communication Networks
Computer Science
Deep learning
Information Systems Applications (incl.Internet)
Internet of Things
Machine learning
Natural language
Natural language processing
Neural networks
Semantics
Software Engineering
Words (language)
Distributed hypothesis
Multi-source data
Neural networks
Word embeddings
68T50
ISSN:0010-485X, 1436-5057
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The representational basis for downstream natural language processing tasks is word embeddings, which capture lexical semantics in numerical form to handle the abstract semantic concept of words. Recently, the word embeddings approaches, represented by deep learning, has attracted extensive attention and widely used in many tasks, such as text classification, knowledge mining, question-answering, smart Internet of Things systems and so on. These neural networks-based models are based on the distributed hypothesis while the semantic association between words can be efficiently calculated in low-dimensional space. However, the expressed semantics of most models are constrained by the context distribution of each word in the corpus while the logic and common knowledge are not better utilized. Therefore, how to use the massive multi-source data to better represent natural language and world knowledge still need to be explored. In this paper, we introduce the recent advances of neural networks-based word embeddings with their technical features, summarizing the key challenges and existing solutions, and further give a future outlook on the research and application.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0010-485X
1436-5057
DOI:10.1007/s00607-019-00768-7