search

IBM / transition-amr-parser

SoTA Abstract Meaning Representation (AMR) parsing with word-node alignments in Pytorch. Includes checkpoints and other tools such as statistical significance Smatch.
Apache License 2.0
245 stars 48 forks source link

How to use this parser on other languages #26

Closed zirui-HIT closed 2 years ago

zirui-HIT commented 2 years ago

I want to use this Parser with Chinese Dataset, and try to use mbart(https://github.com/pytorch/fairseq/tree/main/examples/mbart). But the difference of data preprocess and encode/decode makes it hard to use this parser with Chinese. How can I do that?

xxllp commented 2 years ago

+1

ramon-astudillo commented 2 years ago

we will release a structured-mbart branch next week, check https://twitter.com/RamonAstudill12/ for updates

ramon-astudillo commented 2 years ago

@WDZRMPCBIT @xxllp see https://github.com/IBM/transition-amr-parser/tree/structured-mbart

pournaki commented 4 months ago

I am using the code from your README to parse EN sentences: https://github.com/IBM/transition-amr-parser?tab=readme-ov-file#parse-with-a-pretrained-model

Is there a straightforward way to adapt it for parsing the other available languages using one of your pre-trained models?