Augmenting Semantic Lexicons Using Word Embeddings and Transfer Learning

被引:3
|
作者
Alshaabi, Thayer [1 ,2 ]
Van Oort, Colin M. M. [2 ,3 ]
Fudolig, Mikaela Irene [2 ]
Arnold, Michael V. V. [2 ]
Danforth, Christopher M. M. [2 ,4 ]
Dodds, Peter Sheridan [2 ,5 ]
机构
[1] Univ Calif Berkeley, Adv Bioimaging Ctr, Berkeley, CA 94720 USA
[2] Univ Vermont, Vermont Complex Syst Ctr, Burlington, VT 05405 USA
[3] MITRE Corp, Mclean, VA USA
[4] Univ Vermont, Dept Math & Stat, Burlington, VT USA
[5] Univ Vermont, Dept Comp Sci, Burlington, VT USA
来源
FRONTIERS IN ARTIFICIAL INTELLIGENCE | 2022年 / 4卷
基金
美国国家科学基金会;
关键词
sentiment analysis; semantic lexicons; transformers; BERT; FastText; word embedding; labMT; SENTIMENT ANALYSIS; NEURAL-NETWORK; SOCIAL MEDIA;
D O I
10.3389/frai.2021.783778
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Sentiment-aware intelligent systems are essential to a wide array of applications. These systems are driven by language models which broadly fall into two paradigms: Lexicon-based and contextual. Although recent contextual models are increasingly dominant, we still see demand for lexicon-based models because of their interpretability and ease of use. For example, lexicon-based models allow researchers to readily determine which words and phrases contribute most to a change in measured sentiment. A challenge for any lexicon-based approach is that the lexicon needs to be routinely expanded with new words and expressions. Here, we propose two models for automatic lexicon expansion. Our first model establishes a baseline employing a simple and shallow neural network initialized with pre-trained word embeddings using a non-contextual approach. Our second model improves upon our baseline, featuring a deep Transformer-based network that brings to bear word definitions to estimate their lexical polarity. Our evaluation shows that both models are able to score new words with a similar accuracy to reviewers from Amazon Mechanical Turk, but at a fraction of the cost.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] Revisit Word Embeddings With Semantic Lexicons for Modeling Lexical Contrast
    Liu, Jiawei
    Liu, Zhenyu
    Chen, Huanhuan
    2017 IEEE INTERNATIONAL CONFERENCE ON BIG KNOWLEDGE (IEEE ICBK 2017), 2017, : 72 - 79
  • [2] On the Role of Seed Lexicons in Learning Bilingual Word Embeddings
    Vulic, Ivan
    Korhonen, Anna
    PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, 2016, : 247 - 257
  • [3] A constrained optimization algorithm for learning GloVe embeddings with semantic lexicons
    Sakketou, Flora
    Ampazis, Nicholas
    KNOWLEDGE-BASED SYSTEMS, 2020, 195
  • [4] Learning Semantic Hierarchies via Word Embeddings
    Fu, Ruiji
    Guo, Jiang
    Qin, Bing
    Che, Wanxiang
    Wang, Haifeng
    Liu, Ting
    PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, 2014, : 1199 - 1209
  • [5] Augmenting Transfer Learning with Semantic Reasoning
    Lecue, Freddy
    Chen, Jiaoyan
    Pan, Jeff Z.
    Chen, Huajun
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 1779 - 1785
  • [6] Improved Learning of Word Embeddings with Word Definitions and Semantic Injection
    Zhang, Yichi
    Dai, Yinpei
    Ou, Zhijian
    Wang, Huixin
    Feng, Junlan
    INTERSPEECH 2020, 2020, : 4253 - 4257
  • [7] Expansion of domain-specific opinion lexicons using word embeddings
    Lopez Solaz, Tomas
    Cruz, Fermin L.
    Enriquez, Fernando
    PROCESAMIENTO DEL LENGUAJE NATURAL, 2016, (57): : 49 - 56
  • [8] Improved Learning of Chinese Word Embeddings with Semantic Knowledge
    Yang, Liner
    Sun, Maosong
    CHINESE COMPUTATIONAL LINGUISTICS AND NATURAL LANGUAGE PROCESSING BASED ON NATURALLY ANNOTATED BIG DATA (CCL 2015), 2015, 9427 : 15 - 25
  • [9] Learning semantic information from Internet Domain Names using word embeddings
    Lopez, Waldemar
    Merlino, Jorge
    Rodriguez-Bocca, Pablo
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2020, 94
  • [10] Leveraging Multilingual Transfer for Unsupervised Semantic Acoustic Word Embeddings
    Jacobs, Christiaan
    Kamper, Herman
    IEEE SIGNAL PROCESSING LETTERS, 2024, 31 : 311 - 315