Skip to content
conftrace_
2018 EMNLP EMNLP 2018

Does Syntactic Knowledge in Multilingual Language Models Transfer Across Languages?

Abstract

AbstractRecent work has shown that neural models can be successfully trained on multiple languages simultaneously. We investigate whether such models learn to share and exploit common syntactic knowledge among the languages on which they are trained. This extended abstract presents our preliminary results.

❓ The Questioner
🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing
🐣 Hot Topic Early Bird - multilingual language model

Authors

Prajit Dhar, Arianna Bisazza

Topics

Artificial Intelligence > Learning Paradigms > Transfer Learning Natural Language Processing > Understanding > Syntax Natural Language Processing > Resources & Methods > Multilingual NLP Artificial Intelligence > Core AI > Language Deep Learning > Learning Types > Multi-Lingual Learning

Keywords

transfer learning cross-lingual transfer multilingual language model syntactic knowledge
Download PDF

More from EMNLP 2018

All EMNLP 2018 papers →
Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model
Interpretable Structure Induction via Sparse Attention
Debugging Sequence-to-Sequence Models with Seq2Seq-Vis
Exploiting Attention to Reveal Shortcomings in Memory Models
End-to-end Image Captioning Exploits Distributional Similarity in Multimodal Space
Limitations in learning an interpreted language with recurrent models