CLLGMay 3, 2022

XLTime: A Cross-Lingual Knowledge Transfer Framework for Temporal Expression Extraction

arXiv:2205.01757v1630 citationsh-index: 167
Originality Highly original
AI Analysis

This addresses the scarcity of labeled data for temporal expression extraction in languages other than English, enabling better NLP applications like question answering and information retrieval across multiple languages.

The paper tackles the problem of temporal expression extraction in non-English languages by proposing XLTime, a cross-lingual knowledge transfer framework that outperforms previous automatic state-of-the-art methods on French, Spanish, Portuguese, and Basque by large margins and significantly closes the gap with handcrafted methods.

Temporal Expression Extraction (TEE) is essential for understanding time in natural language. It has applications in Natural Language Processing (NLP) tasks such as question answering, information retrieval, and causal inference. To date, work in this area has mostly focused on English as there is a scarcity of labeled data for other languages. We propose XLTime, a novel framework for multilingual TEE. XLTime works on top of pre-trained language models and leverages multi-task learning to prompt cross-language knowledge transfer both from English and within the non-English languages. XLTime alleviates problems caused by a shortage of data in the target language. We apply XLTime with different language models and show that it outperforms the previous automatic SOTA methods on French, Spanish, Portuguese, and Basque, by large margins. XLTime also closes the gap considerably on the handcrafted HeidelTime method.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes