Papers by Jan A. Botha

4 papers
Entity Linking in 100 Languages (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to multilingual entity linking are cross-lingual, with a focus on zero-shot evaluation.
Approach: They propose a new formulation for multilingual entity linking where language-specific mentions resolve to a language-agnostic Knowledge Base.
Outcome: The proposed model outperforms state-of-the-art models on a large multilingual dataset and shows that frequency-based analysis provided key insights for the model and training enhancements.
FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation (2023.tacl-1)

Copied to clipboard

Challenge: a new dataset and evaluation benchmark for Few-shot Region-aware Machine Translation is presented . FRMT is a type of style-targeted translation that uses labeled training data to perform tasks.
Approach: They propose a dataset and evaluation benchmark for Few-shot Region-aware Machine Translation.
Outcome: The proposed model is based on two translations from English into Portuguese and Mandarin Chinese.
Asking without Telling: Exploring Latent Ontologies in Contextual Representations (2020.emnlp-main)

Copied to clipboard

Challenge: Recent work on model analysis indicates that they may learn a lot about linguistic structure, including part of speech, syntax, word sense, and more.
Approach: They introduce latent subclass learning, a modification to classifier-based probing that induces a latent categorization (or ontology) of the probe’s inputs.
Outcome: The proposed model induces a latent categorization (or ontology) of the probe’s inputs without access to fine-grained gold labels.
Learning To Split and Rephrase From Wikipedia Edit History (D18-1)

Copied to clipboard

Challenge: Performing split and rephrase tasks is one of the main operations in text simplification, alongside paraphrasing and dropping less salient content.
Approach: They propose to use Wikipedia's edit history to extract a rich new dataset for the task.
Outcome: The proposed model scores 32 BLEU points above the previous best on the WebSplit benchmark.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations