|
A Multi-Source Trainable Parser with Deep Contextualized Lexical Representations with Case Studies| old_uid | 16976 |
|---|
| title | A Multi-Source Trainable Parser with Deep Contextualized Lexical Representations with Case Studies |
|---|
| start_date | 2018/12/07 |
|---|
| schedule | 11h |
|---|
| online | no |
|---|
| summary | In this talk, we describe a multi-source trainable parser developed at Lattice for the CoNLL 2018 Shared Task (Multilingual Parsing from Raw Text to Universal Dependencies). The main characteristic of our work is the encoding of three different modes of contextual information for parsing: (i) Treebank feature representations, (ii) Multilingual word representations, (iii) ELMo representations obtained via unsupervised learning from external resources. In the talk, we investigated more about parsing low-resource languages with very small training corpora using multilingual word embeddings and annotated corpora of larger languages. The study demonstrates that specific language combinations enable improved dependency parsing when compared to previous work, allowing for wider reuse of pre-existing resources when parsing low resource languages. The study also explores the question of whether contemporary contact languages or genetically related languages would be the most fruitful starting point for multilingual parsing scenarios. |
|---|
| responsibles | Seddah |
|---|
| |
|