Intrinsic and Extrinsic Evaluations of Word Embeddings

被引：0

作者：

Zhai, Michael ^{[1
]}

Tan, Johnny ^{[1
]}

Choi, Jinho D. ^{[1
]}

机构：

[1] Emory Univ, Dept Math & Comp Sci, Atlanta, GA 30322 USA

来源：

THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE | 2016年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we first analyze the semantic composition of word embeddings by cross-referencing their clusters with the manual lexical database, WordNet. We then evaluate a variety of word embedding approaches by comparing their contributions to two NLP tasks. Our experiments show that the word embedding clusters give high correlations to the synonym and hyponym sets in WordNet, and give 0.88% and 0.17% absolute improvements in accuracy to named entity recognition and part-of-speech tagging, respectively.

引用

页码：4282 / 4283

页数：2

共 50 条

[1] Evaluating Natural Alpha Embeddings on Intrinsic and Extrinsic Tasks
Volpi, Riccardo
Malago, Luigi
[J]. 5TH WORKSHOP ON REPRESENTATION LEARNING FOR NLP (REPL4NLP-2020), 2020, : 61 - 71
[2] WORD CODING - ROLE OF INTRINSIC AND EXTRINSIC FEATURES
NELSON, DL
[J]. BULLETIN OF THE PSYCHONOMIC SOCIETY, 1973, 1 (04) : 241 - 243
[3] Intrinsic and Extrinsic Evaluation of the Quality of Biomedical Embeddings in Different Languages
Franceschini, Paula M.
dos Santos, Henrique D. P.
Vieira, Renata
[J]. 2020 IEEE 33RD INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS(CBMS 2020), 2020, : 271 - 276
[4] AUDITORY WORD RECOGNITION - EXTRINSIC AND INTRINSIC EFFECTS OF WORD-FREQUENCY
CONNINE, CM
TITONE, D
WANG, J
[J]. JOURNAL OF EXPERIMENTAL PSYCHOLOGY-LEARNING MEMORY AND COGNITION, 1993, 19 (01) : 81 - 94
[5] A Fistful of Vectors: A Tool for Intrinsic Evaluation of Word Embeddings
Ascari, Roberto
Giabelli, Anna
Malandri, Lorenzo
Mercorio, Fabio
Mezzanzanica, Mario
[J]. COGNITIVE COMPUTATION, 2024, 16 (03) : 949 - 963
[6] Intrinsic Evaluation of Lithuanian Word Embeddings Using WordNet
Kapociute-Dzikiene, Jurgita
Damasevicius, Robertas
[J]. ARTIFICIAL INTELLIGENCE AND ALGORITHMS IN INTELLIGENT SYSTEMS, 2019, 764 : 394 - 404
[7] Intrinsic or Extrinsic Evaluation: An Overview of Word Embedding Evaluation
Shi, Yong
Zheng, Yuanchun
Guo, Kun
Zhu, Luyao
Qu, Yi
[J]. 2018 18TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW), 2018, : 1255 - 1262
[8] An Exploration of Semantic Relations in Neural Word Embeddings Using Extrinsic Knowledge
Chen, Zhiwei
He, Zhe
Liu, Xiuwen
Bian, Jiang
[J]. 2017 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), 2017, : 1246 - 1251
[9] An inequality between intrinsic and extrinsic scalar curvature invariants for codimension 2 embeddings
Dillen, F
Haesen, S
Petrovic-Torgasev, M
Verstraelen, L
[J]. JOURNAL OF GEOMETRY AND PHYSICS, 2004, 52 (02) : 101 - 112
[10] Training and intrinsic evaluation of lightweight word embeddings for the clinical domain in Spanish
Chiu, Carolina
Villena, Fabian
Martin, Kinan
Nunez, Fredy
Besa, Cecilia
Dunstan, Jocelyn
[J]. FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2022, 5

← 1 2 3 4 5 →