Hitachi at SemEval-2023 Task 3: Exploring Cross-lingual Multi-task Strategies for Genre and Framing Detection in Online News

被引：0

作者：

Koreeda, Yuta ^{[1
]}

Yokote, Ken-ichi ^{[1
]}

Ozaki, Hiroaki ^{[1
]}

Yamaguchi, Atsuki ^{[1
]}

Tsunokake, Masaya ^{[1
]}

Sogawa, Yasuhiro ^{[1
]}

机构：

[1] Hitachi Ltd, Res & Dev Grp, Kokubunji, Tokyo, Japan

来源：

17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023 | 2023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：

This paper explains the participation of team Hitachi to SemEval-2023 Task 3 "Detecting the genre, the framing, and the persuasion techniques in online news in a multi-lingual setup." Based on the multilingual, multi-task nature of the task and the low-resource setting, we investigated different cross-lingual and multi-task strategies for training the pretrained language models. Through extensive experiments, we found that (a) cross-lingual/multi-task training, and (b) collecting an external balanced dataset, can benefit the genre and framing detection. We constructed ensemble models from the results and achieved the highest macro-averaged F1 scores in Italian and Russian genre categorization subtasks.

引用

页码：1702 / 1711

页数：10

共 50 条

[1] SemEval-2023 Task 3: Detecting the Category, the Framing, and the Persuasion Techniques in Online News in a Multi-lingual Setup
Piskorski, Jakub
Stefanovitch, Nicolas
Da San Martino, Giovanni
Nakov, Preslav
17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 2343 - 2361
[2] QCRI at SemEval-2023 Task 3: News Genre, Framing and Persuasion Techniques Detection using Multilingual Models
Hasanain, Maram
El-Shangiti, Ahmed Oumar
Nandi, Rabindra Nath
Nakov, Preslav
Alam, Firoj
17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 1237 - 1244
[3] MLModeler5 at SemEval-2023 Task 3: Detecting the Category and the Framing Techniques in Online News in a Multi-lingual Setup
Khanchandani, Arjun
Jain, Nitansh
Bedi, Jatin
17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 1096 - 1101
[4] MarsEclipse at SemEval-2023 Task 3: Multi-Lingual and Multi-Label Framing Detection with Contrastive Learning
Liao, Qisheng
Lai, Meiting
Nakov, Preslav
17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 83 - 87
[5] Team TheSyllogist at SemEval-2023 Task 3: Language-Agnostic Framing Detection in Multi-Lingual Online News: A Zero-Shot Transfer Approach
Afzal, Osama Mohammed
Nakov, Preslav
17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 2058 - 2061
[6] UMUTeam at SemEval-2023 Task 3: Multilingual transformer-based model for detecting the Genre, the Framing, and the Persuasion Techniques in Online News
Pan, Ronghao
Garcia-Diaz, Jose Antonio
Rodriguez-Garcia, Miguel Angel
Valencia-Garcia, Rafael
17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 609 - 615
[7] PingAnLifeInsurance at SemEval-2023 Task 10: Using Multi-Task Learning to Better Detect Online Sexism
Zhou, Mengyuan
Hou, Xiaolong
Jin, Meizhi
Du, Xiyang
Chen, Cheng
Jiang, Lianxin
Li, Jianyu
Wei, Zhenggang
17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 2188 - 2192
[8] Team QUST at SemEval-2023 Task 3: A Comprehensive Study of Monolingual and Multilingual Approaches for Detecting Online News Genre, Framing and Persuasion Techniques
Jiang, Ye
17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 300 - 306
[9] Appeal for attention at SemEval-2023 Task 3: Data augmentation and extension strategies for detection of online news persuasion techniques
Sergiu, Amihaesei
Laura, Cornei
George, Stoica
17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 616 - 623
[10] TeamAmpa at SemEval-2023 Task 3: Exploring Multilabel and Multilingual RoBERTa Models for Persuasion and Framing Detection
Pauli, Amalie Brogaard
Sarabia, Rafael Pablos
Derczynski, Leon
Assent, Ira
17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 847 - 855

← 1 2 3 4 5 →