We evaluate the reasoning abilities of large language models in multilingual settings. We
introduce the Multilingual Grade School Math (MGSM) benchmark, by manually translating …

Unsupervised cross-lingual transfer has been shown great potentials for dependency
parsing of the low-resource languages when there is no annotated treebank available …

Abstract We present Expected Statistic Regulariza tion (ESR), a novel regularization
technique that utilizes low-order multi-task structural statistics to shape model distributions …

Language is highly structured, with syntactic and semantic structures, to some extent,
agreed upon by speakers of the same language. With implicit or explicit awareness of such …

Large Language Models (LLMs) have become capable of generating highly fluent text in
certain languages, without modules specially designed to capture grammar or semantic …

Unsupervised cross-lingual transfer involves transferring knowledge between languages
without explicit supervision. Although numerous studies have been conducted to improve …

Syntactic parsing is a highly linguistic processing task whose parser requires training on
treebanks from the expensive human annotation. As it is unlikely to obtain a treebank for …

Source-Free Transductive Transfer Learning for Structured Prediction Page 1 Source-Free
Transductive Transfer Learning for Structured Prediction by Kemal Maulana Kurniawan …

The goal of this thesis is to improve the feasibility of building applied NLP systems for more
diverse and niche real-world use-cases of extracting structured information from text. A core …