2024
pdf
bib
abs
Teaching Large Language Models an Unseen Language on the Fly
Chen Zhang
|
Xiao Liu
|
Jiuheng Lin
|
Yansong Feng
Findings of the Association for Computational Linguistics: ACL 2024
Existing large language models struggle to support numerous low-resource languages, particularly the extremely low-resource ones, for which there is minimal training data available for effective parameter updating. We thus investigate whether LLMs can learn a new language on the fly solely through prompting. To study this question, we collect a research suite for Zhuang, a language supported by no LLMs currently. We introduce DiPMT++, a framework for adapting LLMs to unseen languages by in-context learning. Using a dictionary and 5K parallel sentences only, DiPMT++ significantly enhances the performance of GPT-4 from 0 to 16 BLEU for Chinese-to-Zhuang translation and achieves 32 BLEU for Zhuang-to-Chinese translation. We also validate the effectiveness of our framework on Kalamang, another unseen language. Furthermore, we demonstrate the practical utility of DiPMT++ in aiding humans in translating completely unseen languages, which could contribute to the preservation of linguistic diversity.
pdf
bib
abs
Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering
Jiuheng Lin
|
Yuxuan Lai
|
Yansong Feng
Findings of the Association for Computational Linguistics: EMNLP 2024
Conditional question answering (CQA) is an important task that aims to find probable answers and identify missing conditions. Existing approaches struggle with CQA due to two challenges: (1) precisely identifying necessary conditions and the logical relationship, and (2) verifying conditions to detect any that are missing. In this paper, we propose a novel prompting approach, Chain of condition, by first identifying all conditions and constructing their logical relationships explicitly according to the document, then verifying whether these conditions are satisfied, finally solving the logical expression to indicate any missing conditions and generating the answer accordingly. Experiments on two CQA benchmark datasets show our chain of condition outperforms existing prompting baselines, establishing a new state of the art. Furthermore, with only a few examples, our method can facilitate GPT-3.5-Turbo or GPT-4 to outperform all existing supervised models.
pdf
bib
abs
MC2: Towards Transparent and Culturally-Aware NLP for Minority Languages in China
Chen Zhang
|
Mingxu Tao
|
Quzhe Huang
|
Jiuheng Lin
|
Zhibin Chen
|
Yansong Feng
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Current large language models demonstrate deficiencies in understanding low-resource languages, particularly the minority languages in China. This limitation stems from the scarcity of available pre-training data. To address this accessibility challenge, we present MC2, a Multilingual Corpus of Minority Languages in China, which is the largest open-source corpus of its kind so far. MC2 includes four underrepresented languages: Tibetan, Uyghur, Kazakh, and Mongolian. Notably, we focus on the less common writing systems of Kazakh and Mongolian, i.e., Kazakh Arabic script and traditional Mongolian script, respectively, which have been long neglected in previous corpus construction efforts. Recognizing the prevalence of language contamination within existing corpora, we adopt a quality-centric solution for collecting MC2, prioritizing accuracy while enhancing diversity. Furthermore, we underscore the importance of attending to the multiplicity of writing systems, which is closely related to the cultural awareness of the resulting models. The MC2 corpus and related models are made public to the community.
2023
pdf
bib
abs
How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading Comprehension
Chen Zhang
|
Jiuheng Lin
|
Xiao Liu
|
Yuxuan Lai
|
Yansong Feng
|
Dongyan Zhao
Findings of the Association for Computational Linguistics: ACL 2023
The multi-answer phenomenon, where a question may have multiple answers scattered in the document, can be well handled by humans but is challenging enough for machine reading comprehension (MRC) systems. Despite recent progress in multi-answer MRC, there lacks a systematic analysis of how this phenomenon arises and how to better address it. In this work, we design a taxonomy to categorize commonly-seen multi-answer MRC instances, with which we inspect three multi-answer datasets and analyze where the multi-answer challenge comes from. We further analyze how well different paradigms of current multi-answer MRC models deal with different types of multi-answer instances. We find that some paradigms capture well the key information in the questions while others better model the relation between questions and contexts. We thus explore strategies to make the best of the strengths of different paradigms. Experiments show that generation models can be a promising platform to incorporate different paradigms. Our annotations and code are released for further research.