-
BoolQ 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 build …
-
hi, thanks for your work
Is the code available now?
or does its dataset need any special processing skills?
-
## 프로젝트 개요
- 프로젝트 목표 : 내가 NLP 알못일 때 만든, 엉성한 Kochat을 개선해보자.
- 프로젝트 기간 : 딱히 정한 것은 없음. 2021년 내내 개발하지 않을까 싶음.. (퇴근하고 짬짬이)
- 프로젝트 멤버 : 일단 내가 주축. 하고싶은 사람 있으면 찾아볼 예정. (8명 이내가 적당할 듯?)
- 라이브러리 : 아마 pytorch…
-
# 🌟 New model addition
## Model description
Thanks for the awesome work!
[DialogRPT](https://github.com/golsun/DialogRPT) (Dialog Ranking Pretrained Transformers) is a set of GPT-2 based dial…
-
* https://arxiv.org/abs/2010.07174
* Blackbox NLP Workshop at EMNLP 2020
見たことのないシーケンスの長さへの外挿は、言語のニューラル生成モデルにとっての課題である。
この研究では、見落とされがちなモデル化の決定である、特別なEOS（End-of-sequence）語彙項目の使用による生成プロセスの終了予測の長さ外挿の…
e4exp updated
3 years ago
-
Hi, I am really interesting in your work, could you plz also release your code about models for the experiments( I want to know if you change original model for this new setting, how do you organize y…
-
Every time I run agent by `python ./python/craftassist/craftassist_agent.py`, it prompts me to download the models and datasets. Even after I downloaded them, when I type instructions it says models a…
-
Hi, I'm trying to run your code on a new dataset when after running the format_data.py, AMIE cannot find any rules for one of the graphs. Then, when I ran the train.py, it reported the following error…
-
In the paper, you also report results for B-AON, which simply replaces the LSTM of AON with the pre-trained BERT model as Sentence Encoder. Do you directly extract the BERT embeddings for sentences an…
-
## The problem
When running the code below, the result of the tokenizer is somewhat strange. Some weird characters seem to be introduced by the tokenization which leads to the fact that following tas…