Sarcastic RoBERTa: A RoBERTa-Based Deep Neural Network Detecting Sarcasm on Twitter

被引：2

作者：

Hercog, Maciej ^{[1
]}

Jaronski, Piotr ^{[1
]}

Kolanowski, Jan ^{[1
,3
]}

Mieczynski, Pawel ^{[1
]}

Wisniewski, Dawid ^{[1
]}

Potoniec, Jedrzej ^{[1
,2
]}

机构：

[1] Poznan Univ Tech, Inst Comp Sci, Ul Piotrowo 2, PL-60965 Poznan, Poland

[2] Poznan Univ Tech, Ctr Artificial Intelligence & Machine Learning, Ul Piotrowo 2, PL-60965 Poznan, Poland

[3] Cisco Syst Poland, Warsaw, Poland

来源：

BIG DATA ANALYTICS AND KNOWLEDGE DISCOVERY, DAWAK 2022 | 2022年 / 13428卷

关键词：

Text classification; Sarcasm detection; RoBERTa; iSarcasm; SARC; Knowledge transfer;

D O I：

10.1007/978-3-031-12670-3_4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Sarcastic RoBERTa is an approach to recognizing sarcastic tweets written in English. It is based on a pre-trained RoBERTa model supported by a 3-layer feed-forward fully-connected neural network. It establishes a new state-of-the-art result on the iSarcasm dataset, attaining the F-1 score of 0.526, and being not far from the human performance of 0.616.

引用

页码：46 / 52

页数：7

共 23 条

[1]

Abercrombie G., 2016, P ACL 2016 STUD RES, P107, DOI [DOI 10.18653/V1/P16-3016, 10.18653/v1/P16-3016]

[2]

[Anonymous], 2010, Proceedings of the Fourteenth Conference on Computational Natural Language Learning

[3]

[Anonymous], 2014, P COLING 2014 25 INT

[4]

Bamman D., 2015, 9 INT AAAI C WEB SOC, P574, DOI [10.1609/icwsm.v9i1.14655, DOI 10.1609/ICWSM.V9I1.14655]

[5]

Barbieri F., 2014, P 5 WORKSHOP COMPUTA, P50

[6]

Barbieri F, 2020, FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, P1644

[7]

Filatova E, 2012, LREC 2012 - EIGHTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, P392

[8]

Gregory H, 2020, FIGURATIVE LANGUAGE PROCESSING, P270

[9]

Guo X, 2021, 2021 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL-HLT 2021), P5394

[10]

Handoyo A, 2021, Arxiv, DOI arXiv:2108.09924

← 1 2 3 →