Leveraging Knowledge in Multilingual Commonsense Reasoning

10/16/2021
by   Yuwei Fang, et al.
0

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. Thus, it remains unclear how to effectively conduct multilingual commonsense reasoning (XCSR) for various languages. In this work, we propose to utilize English knowledge sources via a translate-retrieve-translate (TRT) strategy. For multilingual commonsense questions and choices, we collect related knowledge via translation and retrieval from the knowledge sources. The retrieved knowledge is then translated into the target language and integrated into a pre-trained multilingual language model via visible knowledge attention. Then we utilize a diverse of 4 English knowledge sources to provide more comprehensive coverage of knowledge in different formats. Extensive results on the XCSR benchmark demonstrate that TRT with external knowledge can significantly improve multilingual commonsense reasoning in both zero-shot and translate-train settings, outperforming 3.3 and 3.6 points over the previous state-of-the-art on XCSR benchmark datasets (X-CSQA and X-CODAH).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/26/2023

CLICKER: Attention-Based Cross-Lingual Commonsense Knowledge Transfer

Recent advances in cross-lingual commonsense reasoning (CSR) are facilit...
research
12/01/2022

A Commonsense-Infused Language-Agnostic Learning Framework for Enhancing Prediction of Political Polarity in Multilingual News Headlines

Predicting the political polarity of news headlines is a challenging tas...
research
05/24/2022

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

Recent work has shown that Pre-trained Language Models (PLMs) have the a...
research
08/02/2023

Do Multilingual Language Models Think Better in English?

Translate-test is a popular technique to improve the performance of mult...
research
01/01/2022

Zero-shot Commonsense Question Answering with Cloze Translation and Consistency Optimization

Commonsense question answering (CQA) aims to test if models can answer q...
research
06/22/2021

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

Commonsense reasoning is one of the key problems in natural language pro...
research
12/15/2021

KGR^4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation

Generative commonsense reasoning requires machines to generate sentences...

Please sign up or login with your details

Forgot password? Click here to reset