Three syntactic probing tasks for hidden states

Name: Three syntactic probing tasks for hidden states
Creator: Jianyu Zheng
Published: 2023-04-29T00:00:00+08:00

Zenodo2023-04-29 更新2026-04-07 收录

句法分析

模型可解释性

数据链接：

https://zenodo.org/record/7878394 数据链接链接失效反馈

官方服务：

资源简介：

This is a dataset for syntactic probes, used in the article "What does Chinese BERT learn about syntactic knowledge?"

提供机构：

Jianyu Zheng

创建时间：

2023-04-29

Constituency Parsing Task Dataset

句法分析

自然语言处理

The Constituency Parsing Task Dataset contains the dataset used for the Constituency Parsing Task (http://www.evalita.it/2009/tasks/parsing) organised as part of the EVALITA 2009 evaluation campaign (

DataCite Commons2022-06-01 更新100

Treebank-2

自然语言处理

句法分析

Original release was included in LDC Catalog No. LDC93T1 Original Treebank Release This release contains over 1.6 million words of hand-pa

DataCite Commons2021-07-01 更新80

Dataset 6 - Representação Sintática das sentenças dos Dispositivos das Normas Legislativas Federais

法律文本分析

句法分析

Contém o resultado da análise sintática de cada dispositivo do dataset 4 realizada por processamento de linguagem natural por meio da Google Natural Language Processing API.

Figshare2018-02-26 更新30

A Syntactic Analysis Of The Co-Occurrence Of Stative And Passive In Kiswahili

句法分析

斯瓦希里语

This study concerns the co-occurrence of stative and passive in Kiswahili. The co-occurrence is only possible with an intervening applicative suffix and in the order st-appl-pass. There are two readin

DataCite Commons2024-05-17 更新90

SolshineMisfit/nla-qwen2.5-7b-L20-results-famous-ads

模型可解释性

广告分析

该数据集名为著名广告标语——NLA激活分析（Qwen2.5-7B，第20层），旨在探究语言模型在读取著名广告标语时的内部表示。它使用自然语言自编码器（NLA）将Qwen2.5-7B-Instruct模型在第20层最后一个token的残差流激活解码为自然语言描述。数据集包含约146条著名广告标语（源自维基百科，附有品牌、年份和上下文信息），每条标语都对应一个由AV生成的英文解释（描述模型对该标语的表

Hugging Face2026-05-27 更新70

Three syntactic probing tasks for hidden states

资源简介：

相关数据集