ASOC 2022: Downstream tasks code implementation of StructBERT

[wangwei7175878]

Background

This is an advance subject of ASoC 2022 and https://github.com/alibaba/AliceMind/issues/44 .

Supplementing the implementation of common downstream tasks such as regression/multi-label classification/sequence labeling/machine reading comprehension of StructBERT.

Target

Design and implement regression/multi-label classification/sequence labeling/machine reading comprehension code of StructBERT.

Difficulty

Normal

Mentor

Wei Wang (@wangwei7175878 )([email protected])

背景

这是一个阿里巴巴编程之夏 2022 的基础课题 https://github.com/alibaba/AliceMind/issues/44 补充StructBERT在回归/多标签分类/序列标注/机器阅读理解等常见下游任务的代码实现。

目标

补充StructBERT在回归/多标签分类/序列标注/机器阅读理解等常见下游任务的代码实现。

难度

正常

导师

Wei Wang(@wangwei7175878 )([email protected])

[Destiny-Lu]

Hello, this project is very appealing to me. But I still have some doubts about its specific works. As far as I know, the Huggingface Transformers provide many downstream tasks' APIs (e.g., BertForTokenClassification) in Bert and other PLMs. Does this project want to implement such interfaces on StructBert, or do corresponding API implementations for the given tasks (e.g., sentiment analysis, NER)?