paper-with-me

홈 › Papers

Analyzing Bayesian Crosslingual Transfer in Topic Models

2019-06-01 · NAACL 2019 6 · Shudong Hao, Michael J. Paul

We introduce a theoretical analysis of crosslingual transfer in probabilistic topic models. By formulating posterior inference through Gibbs sampling as a process of language transfer, we propose a new measure that quantifies the loss of knowledge across languages during this process. This measure enables us to derive a PAC-Bayesian bound that elucidates the factors affecting model quality, both during training and in downstream applications. We provide experimental validation of the analysis on a diverse set of five languages, and discuss best practices for data collection and model design based on our analysis.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Topic Models

Similar Papers 제목 키워드 기반

An Empirical Study on Crosslingual Transfer in Probabilistic Topic Models

2018-10-13 · CL 2020 3 · Shudong Hao, Michael J. Paul

Probabilistic topic modeling is a popular choice as the first step of crosslingual tasks to enable knowledge transfer and extract multilingual features. While many multilingual topic models have been developed, their ass…

Topic ModelsTransfer Learning

Crosslingual Topic Modeling with WikiPDA

2020-09-23 · Tiziano Piccardi, Robert West

We present Wikipedia-based Polyglot Dirichlet Allocation (WikiPDA), a crosslingual topic model that learns to represent Wikipedia articles written in any language as distributions over a common set of language-independen…

ArticlesMatrix Completion

A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters

2020-12-31 · ACL 2021 5 · Mengjie Zhao, Yi Zhu, Ehsan Shareghi, Ivan Vulić 외

Few-shot crosslingual transfer has been shown to outperform its zero-shot counterpart with pretrained encoders like multilingual BERT. Despite its growing popularity, little to no attention has been paid to standardizing…

Few-Shot Learning

Learning Multilingual Topics from Incomparable Corpus

2018-06-11 · Shudong Hao, Michael J. Paul

Multilingual topic models enable crosslingual tasks by extracting consistent topics from multilingual corpora. Most models require parallel or comparable training corpora, which limits their ability to generalize. In thi…

Topic ModelsTransfer Learning

Learning Multilingual Topics from Incomparable Corpora

2018-08-01 · COLING 2018 8 · Shudong Hao, Michael J. Paul

Multilingual topic models enable crosslingual tasks by extracting consistent topics from multilingual corpora. Most models require parallel or comparable training corpora, which limits their ability to generalize. In thi…

Topic ModelsTransfer Learning