paper-with-me

홈 › Papers

Identifying the Correlation Between Language Distance and Cross-Lingual Transfer in a Multilingual Representation Space

2023-05-03 · Fred Philippy, Siwen Guo, Shohreh Haddadan

Prior research has investigated the impact of various linguistic features on cross-lingual transfer performance. In this study, we investigate the manner in which this effect can be mapped onto the representation space. While past studies have focused on the impact on cross-lingual alignment in multilingual language models during fine-tuning, this study examines the absolute evolution of the respective language representation spaces produced by MLLMs. We place a specific emphasis on the role of linguistic characteristics and investigate their inter-correlation with the impact on representation spaces and cross-lingual transfer performance. Additionally, this paper provides preliminary evidence of how these findings can be leveraged to enhance transfer to linguistically distant languages.

📄 PDF Abstract BibTeX arXiv:2305.02151

Code (1)

fredxlpy/crosslingualspaceimpactanalysis 공식 구현 pytorch

Tasks

Cross-Lingual Transfer

Similar Papers 제목 키워드 기반

On the Versatile Uses of Partial Distance Correlation in Deep Learning

2022-07-20 · Xingjian Zhen, Zihang Meng, Rudrasis Chakraborty, Vikas Singh

Comparing the functional behavior of neural network models, whether it is a single network over time or two (or more networks) during or post-training, is an essential step in understanding what they are learning (and wh…

Estimating Feature-Label Dependence Using Gini Distance Statistics

2019-06-05 · Silu Zhang, Xin Dang, Dao Nguyen, Dawn Wilkins 외

Identifying statistical dependence between the features and the label is a fundamental problem in supervised learning. This paper presents a framework for estimating dependence between numerical features and a categorica…

Density Estimation

On the Credibility of Evaluating LLMs using Survey Questions

2026-02-03 · Jindřich Libovický arxiv

Recent studies evaluate the value orientation of large language models (LLMs) using adapted social surveys, typically by prompting models with survey questions and comparing their responses to average human responses. Th…

Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge Distillation

2021-12-07 · Thong Nguyen, Luu Anh Tuan

Current state-of-the-art cross-lingual summarization models employ multi-task learning paradigm, which works on a shared vocabulary module and relies on the self-attention mechanism to attend among tokens in two language…

Knowledge DistillationMulti-Task Learning

How to Distinguish Languages and Dialects

2019-12-01 · CL 2019 12 · S{\o}ren Wichmann

The terms {``}language{''} and {``}dialect{''} are ingrained, but linguists nevertheless tend to agree that it is impossible to apply a non-arbitrary distinction such that two speech varieties can be identified as either…