Search Results for author: Daniel Edmiston

Found 7 papers, 3 papers with code

Domain Mismatch Doesn’t Always Prevent Cross-lingual Transfer Learning

no code implementations LREC 2022 Daniel Edmiston, Phillip Keung, Noah A. Smith

Cross-lingual transfer learning without labeled target language data or parallel text has been surprisingly effective in zero-shot cross-lingual classification, question answering, unsupervised machine translation, etc.

Bilingual Lexicon Induction Cross-Lingual Transfer +5

Domain Mismatch Doesn't Always Prevent Cross-Lingual Transfer Learning

no code implementations30 Nov 2022 Daniel Edmiston, Phillip Keung, Noah A. Smith

Cross-lingual transfer learning without labeled target language data or parallel text has been surprisingly effective in zero-shot cross-lingual classification, question answering, unsupervised machine translation, etc.

Bilingual Lexicon Induction Cross-Lingual Transfer +5

A Systematic Analysis of Morphological Content in BERT Models for Multiple Languages

1 code implementation6 Apr 2020 Daniel Edmiston

This work describes experiments which probe the hidden representations of several BERT-style models for morphological content.

Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Induction

1 code implementation ICLR 2020 Taeuk Kim, Jihun Choi, Daniel Edmiston, Sang-goo Lee

With the recent success and popularity of pre-trained language models (LMs) in natural language processing, there has been a rise in efforts to understand their inner workings.

Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations

2 code implementations7 Sep 2018 Taeuk Kim, Jihun Choi, Daniel Edmiston, Sanghwan Bae, Sang-goo Lee

Most existing recursive neural network (RvNN) architectures utilize only the structure of parse trees, ignoring syntactic tags which are provided as by-products of parsing.

Natural Language Inference Sentence +2

Cannot find the paper you are looking for? You can Submit a new open access paper.