Yang An

请问tnews 1.1版本测试集有各个baseline的分数吗？

7

如题，请问几个tnews 1.1版本测试集相关的问题： 1. 有没有BERT-base, BERT-wwm-ext, ERNIE-base, RoBERTa-large, XLNet-mid, ALBERT-base, ALBERT-large, ALBERT-xlarge, ALBERT-xxlarge, ALBERT-tiny, RoBERTa-wwm-ext, RoBERTa-wwm-large这些对应baseline的测试集分数呢？ 2. 为什么测试集需要从1.0更新到1.1呢？我观察到1.0测试集分数普遍高于1.1，这个主要是因为什么呢 3. 1.1版本测试集sample没有了keyword，这个是什么考虑呢 @brightmart 希望主办方能够麻烦解答，十分感谢！

VQA finetune: test annotation file test-dev2015_qla_mrcnn.json and test2015_qla_mrcnn.json are missing

4

Hi, thank you for releasing the great work! I am working on the VQA task. May I ask where can I find the annotation file `test2015_qla_mrcnn.json` and `test-dev2015_qla_mrcnn.json` to make...

Add unconstrained training for VQA, which does not need a pre-defined candidate answer set for both finetuning and inference. In this case, evaluation inference mode must be `beamsearch` rather than...

## 推荐项目 - 项目地址：https://github.com/OFA-Sys/Chinese-CLIP - 类别：Python - 项目标题：OpenAI CLIP模型中文预训练版本，几行代码实现中文图文特征&图文检索 - 项目描述：大家好我们是达摩院OFA-Sys团队，欢迎在github试用我们的Chinese-CLIP图文预训练模型项目（https://github.com/OFA-Sys/Chinese-CLIP ），该项目是OpenAI CLIP模型的中文版本。我们使用大量互联网图文信息进行预训练（~2亿中文原生图文数据），提供了多个规模的预训练模型和技术报告，使对机器学习感兴趣的初学者，能几行代码完成中文图文特征提取和图文检索。在近期多个图文检索评测比赛（“兴智杯”全国人工智能创新应用大赛、天池电商多模态图文检索挑战赛）上，基于Chinese-CLIP的模型都取得榜首成绩！**希望大家多多试用 & 多多star！** - 亮点：我们实现的中文版本CLIP在多个公开数据集上取得杰出的效果，基本超出市面同类型baseline图文表征和检索模型。上手门槛非常低，几行代码就可以完成中文图文特征提取和图文检索，打比赛做项目都非常给力，持续保持更新和维护当中！ - 示例代码： ```python import torch from PIL import Image import cn_clip.clip as clip...

Hope to get access to the source code

9

Hello. I am very interested in question generation and I think this paper tackles an important issue on this task. Your release of generated QA dataset is helpful for inspecting...

Would you release the multi-task fine-tuning codes for ViL-BERT?

4

Hi, I have read your new paper "12-in-1: Multi-Task Vision and Language Representation Learning" on Arxiv, which utilizes multi-task fine-tuning to boost the performance of Vil-BERT. May I ask whether...