paper-with-me

홈 › Papers

CLICKER: Attention-Based Cross-Lingual Commonsense Knowledge Transfer

2023-02-26 · Ruolin Su, Zhongkai Sun, Sixing Lu, Chengyuan Ma, Chenlei Guo

Recent advances in cross-lingual commonsense reasoning (CSR) are facilitated by the development of multilingual pre-trained models (mPTMs). While mPTMs show the potential to encode commonsense knowledge for different languages, transferring commonsense knowledge learned in large-scale English corpus to other languages is challenging. To address this problem, we propose the attention-based Cross-LIngual Commonsense Knowledge transfER (CLICKER) framework, which minimizes the performance gaps between English and non-English languages in commonsense question-answering tasks. CLICKER effectively improves commonsense reasoning for non-English languages by differentiating non-commonsense knowledge from commonsense knowledge. Experimental results on public benchmarks demonstrate that CLICKER achieves remarkable improvements in the cross-lingual CSR task for languages other than English.

📄 PDF Abstract BibTeX arXiv:2302.13201

Code (0)

등록된 구현이 없습니다.

Tasks

Question AnsweringTransfer Learning

Similar Papers 제목 키워드 기반

Leveraging Knowledge in Multilingual Commonsense Reasoning

2021-10-16 · Findings (ACL) 2022 5 · Yuwei Fang, Shuohang Wang, Yichong Xu, Ruochen Xu 외

Commonsense reasoning (CSR) requires the model to be equipped with general world knowledge. While CSR is a language-agnostic process, most comprehensive knowledge sources are in few popular languages, especially English.…

Language ModelingLanguage ModellingRetrievalTranslation+1

It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning

2021-06-22 · Alexey Tikhonov, Max Ryabinin

Commonsense reasoning is one of the key problems in natural language processing, but the relative scarcity of labeled data holds back the progress for languages other than English. Pretrained cross-lingual models are a s…

AllCross-Lingual Transfer

It’s All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning

2021-08-01 · Findings (ACL) 2021 8 · Alexey Tikhonov, Max Ryabinin
AllCross-Lingual Transfer

GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models

2022-05-24 · Da Yin, Hritik Bansal, Masoud Monajatipoor, Liunian Harold Li 외

Recent work has shown that Pre-trained Language Models (PLMs) store the relational knowledge learned from data and utilize it for performing downstream tasks. However, commonsense knowledge across different regions may v…

DiversityLanguage Modelling

Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution

2021-11-01 · EMNLP 2021 11 · Denis Emelin, Rico Sennrich

Winograd schemas are a well-established tool for evaluating coreference resolution (CoR) and commonsense reasoning (CSR) capabilities of computational models. So far, schemas remained largely confined to English, limitin…

Common Sense Reasoningcoreference-resolutionCoreference ResolutionMachine Translation+3