-
### Author Pages
https://aclanthology.org/people/c/chen-zhang/
### Type of Author Metadata Correction
- [X] The author page wrongly conflates different people with the same name.
- [ ] This author …
-
在用reading_comprehension模型进行预测时（按照官方文档操作），遇到如下错误：
Traceback (most recent call last):
File "run.py", line 652, in
predict(logger, args)
File "run.py", line 575, in predict
exe, args.lo…
-
实验环境：python3.5 paddlepaddle-gpu==1.0.0.post87 ubuntu16.04 GPU 使用 两个1080Ti
执行 `sh run.sh --train --pass_num 10` 时， 在执行到`2018-12-17 11:15:38,728 - brc - INFO - Training the model...
` 时 报错如下
```bash…
-
First off, the OS family tree is just awesome! I really appreciate the sisyphean work behind those comparisons and presentations.
By this issue, I'm suggesting a minor improvement to the family tre…
-
MultiRC is one of the tasks of the [SuperGLUE](https://super.gluebenchmark.com) benchmark. The task is to re-trace the steps of Facebook's RoBERTa paper (https://arxiv.org/pdf/1907.11692.pdf) and buil…
-
## Description
When using the ReadAloud function in a Reading System, or when a screen reader is being used, text citations in the text can be disruptive to reading comprehension. The same disrup…
-
## 一言でいうと
複数根拠文にまたがる推論が必要な質問(日光は日本にある/日光には猿がいる=日本に猿がいる、等)について、一度に回答せず一つ一つの質問に分解して答えるという手法。個別質問への分解は少量のアノテーションで学習し(400件)、入力文を元にどの個別質問の回答が正答かを予測する。
。質問/回答が、人間のものである点が特徴(Bing=検索エンジンへの入力なのでどこまで質問っぽいかは要確認)。回答はBingの検索結果から抜粋して作成。
### 論文リンク
https://arxiv.org/pdf/1611.09268v1.pdf
### 著者/所属機関
Tri Ng…
-
Hi all, the Bert paper discusses how to adopt this model for Question Answering/Reading Comprehension tasks like SQUAD where you just combine the passage and question into a single packed sequence and…
-
1. 약 61,860 개 영어의 SQuAD, MS MARCO 문서와 질문 쌍에 대해 특정한 문장을 넣을 경우, 문장에 대한 질문을 생성하는 Question Generation 모델.
2. Learning to Ask: Neural Question Generation for Reading Comprehension
3. Question Generation …