siyuanwangw / lreasoner Goto Github PK

Hi, thanks for your great contribution first!

I'm trying to pre-process the data by myself to extract the constituents. It seems that the version for the package allennlp is not provided in requirements.txt so I installed the laster version with allennlp == 2.4.0 and transformers == 4.5.1. And following error occured while initializing the parser:

Traceback (most recent call last):
  File "extract_logical_expressions_v2.py", line 9, in <module>
    predictor = Predictor.from_path("https://storage.googleapis.com/allennlp-public-models/elmo-constituency-parser-2020.02.10.tar.gz")
    File "/home/jiaofangkai/anaconda3/envs/torch1.8-py3.8/lib/python3.8/site-packages/allennlp/predictors/predictor.py", line 362, in from_path
    load_archive(archive_path, cuda_device=cuda_device, overrides=overrides),
  File "/home/jiaofangkai/anaconda3/envs/torch1.8-py3.8/lib/python3.8/site-packages/allennlp/models/archival.py", line 204, in load_archive
    dataset_reader, validation_dataset_reader = _load_dataset_readers(
  File "/home/jiaofangkai/anaconda3/envs/torch1.8-py3.8/lib/python3.8/site-packages/allennlp/models/archival.py", line 230, in _load_dataset_readers
    dataset_reader = DatasetReader.from_params(
  File "/home/jiaofangkai/anaconda3/envs/torch1.8-py3.8/lib/python3.8/site-packages/allennlp/common/from_params.py", line 570, in from_params
    choice = params.pop_choice(
  File "/home/jiaofangkai/anaconda3/envs/torch1.8-py3.8/lib/python3.8/site-packages/allennlp/common/params.py", line 352, in pop_choice
    raise ConfigurationError(message)
allennlp.common.checks.ConfigurationError: ptb_trees not in acceptable choices for dataset_reader.type: ['babi', 'conll2003', 'interleaving', 'multitask', 'multitask_shim', 'sequence_tagging', 'sharded', 'text_classification_json']. You should either use the --include-package flag to make sure the correct module is loaded, or use a fully qualified class name in your config file like {"model": "my_module.models.MyModel"} to have it imported automatically.

Could you please provide the version for allennlp or release the pre-processed constituents files?

Thank you very much!

Hi,

I am interested in your methods. Have you provided the code for the ensemble methods?

Kind regardes,
Qiming

请问正样例的构造哪里可以看到？或者正样例的是如何构造的？

Hi, I have found the paper From LSAT: The Progress and Challenges of Complex Reasoning, where the results on LogiQA are also reported.

Would you love to share the pre-processed constituent files?
If I choose to pre-process them by myself, can I change the file format of LogiQA into that of ReClor and run the same procedure directly?

Thanks for you help very much!

Best.

感谢您提出的精彩的工作！
运行python extract_logical_expressions_v2.py之后可以获取扩充的文本，但是要如何得到中间提取的逻辑表达式呢？
感谢！

Hi, I found that the data in reclor-data/test.json is indeed part of the original validation set and as a result, the prediction results can not be submitted to the leaderboard. Will you fix this problem?

代码中使用了4卡，每个卡Batch size=2, 共batch size=8。那每张卡的型号是什么，显存是多少？

您好，很好的工作，想了解一下，就是我看了文章以后知道，模型在训练的时候是用logical data augmentation对问题的option进行扩增，想问一下您在测试集上测试的时候是不是也是做了扩增以后完成的测试，还是直接把测试集输入到模型进行测试？非常感谢！

您好，我想问一下关于训练模型用到的具体的包的版本。我看到requirements.txt文件里有写，但是比如pandas和numpy的版本没有给全，还有requirements.txt里其他包的版本希望也能标注一下，非常感谢！

这是我目前的环境安装的包，python3.8
Package Version

aiohttp 3.7.4.post0
allennlp 2.1.0
allennlp-models 2.1.0
argon2-cffi 21.1.0
async-timeout 3.0.1
atomicwrites 1.4.0
attrs 21.2.0
backcall 0.2.0
backports.csv 1.0.7
base58 2.1.0
beautifulsoup4 4.10.0
bleach 4.1.0
blis 0.7.4
boto3 1.18.55
botocore 1.21.55
cachetools 4.2.4
catalogue 2.0.5
certifi 2021.5.30
cffi 1.14.6
chardet 4.0.0
charset-normalizer 2.0.4
checklist 0.0.11
cheroot 8.5.2
CherryPy 18.6.1
click 7.1.2
colorama 0.4.4
configparser 5.0.2
conllu 4.4
cryptography 35.0.0
cymem 2.0.5
datasets 1.12.1
debugpy 1.5.0
decorator 5.1.0
defusedxml 0.7.1
dill 0.3.4
docker-pycreds 0.4.0
en-core-web-sm 3.0.0
entrypoints 0.3
fairscale 0.4.0
feedparser 6.0.8
filelock 3.0.12
fsspec 2021.10.0
ftfy 6.0.3
future 0.18.2
gitdb 4.0.7
GitPython 3.1.24
google-api-core 2.1.0
google-auth 2.2.1
google-cloud-core 2.1.0
google-cloud-storage 1.42.3
google-crc32c 1.3.0
google-resumable-media 2.0.3
googleapis-common-protos 1.53.0
h5py 3.4.0
huggingface-hub 0.0.18
idna 3.2
iniconfig 1.1.1
ipykernel 6.4.1
ipython 7.28.0
ipython-genutils 0.2.0
ipywidgets 7.6.5
iso-639 0.4.5
jaraco.classes 3.2.1
jaraco.collections 3.4.0
jaraco.functools 3.3.0
jaraco.text 3.5.1
jedi 0.18.0
Jinja2 3.0.1
jmespath 0.10.0
joblib 1.0.1
jsonpickle 2.0.0
jsonschema 4.0.1
jupyter 1.0.0
jupyter-client 7.0.6
jupyter-console 6.4.0
jupyter-core 4.8.1
jupyterlab-pygments 0.1.2
jupyterlab-widgets 1.0.2
lmdb 1.2.1
lxml 4.6.3
MarkupSafe 2.0.1
matplotlib-inline 0.1.3
mistune 0.8.4
more-itertools 8.10.0
multidict 5.2.0
multiprocess 0.70.12.2
munch 2.5.0
murmurhash 1.0.5
nbclient 0.5.4
nbconvert 6.2.0
nbformat 5.1.3
nest-asyncio 1.5.1
nltk 3.6.2
notebook 6.4.4
numpy 1.17.5
overrides 3.1.0
packaging 21.0
pandas 1.1.0
pandocfilters 1.5.0
parso 0.8.2
pathtools 0.1.2
pathy 0.6.0
patternfork-nosql 3.6
pdfminer.six 20201018
pickleshare 0.7.5
Pillow 8.3.2
pip 21.2.4
pluggy 1.0.0
portend 2.7.1
preshed 3.0.5
prometheus-client 0.11.0
promise 2.3
prompt-toolkit 3.0.20
protobuf 3.18.1
psutil 5.8.0
py 1.10.0
py-rouge 1.1
pyarrow 5.0.0
pyasn1 0.4.8
pyasn1-modules 0.2.8
pycparser 2.20
pydantic 1.8.2
Pygments 2.10.0
pyparsing 2.4.7
pyrsistent 0.18.0
pytest 6.2.5
python-dateutil 2.8.2
python-docx 0.8.11
pytz 2021.1
pywin32 301
pywinpty 1.1.4
PyYAML 5.4.1
pyzmq 22.3.0
qtconsole 5.1.1
QtPy 1.11.2
regex 2021.8.3
requests 2.26.0
rsa 4.7.2
ruamel.yaml 0.17.16
ruamel.yaml.clib 0.2.6
s3transfer 0.5.0
sacremoses 0.0.45
scikit-learn 1.0
scipy 1.7.1
Send2Trash 1.8.0
sentencepiece 0.1.96
sentry-sdk 1.4.3
setuptools 41.2.0
sgmllib3k 1.0.0
shortuuid 1.0.1
six 1.16.0
smart-open 5.1.0
smmap 4.0.0
sortedcontainers 2.4.0
soupsieve 2.2.1
spacy 3.0.7
spacy-legacy 3.0.8
sqlitedict 1.7.0
srsly 2.4.1
subprocess32 3.5.4
tempora 4.1.1
tensorboardX 2.4
termcolor 1.1.0
terminado 0.12.1
testpath 0.5.0
thinc 8.0.8
threadpoolctl 3.0.0
tokenizers 0.10.3
toml 0.10.2
torch 1.7.1
torchvision 0.8.2+cpu
tornado 6.1
tqdm 4.62.1
traitlets 5.1.0
transformers 4.3.3
typer 0.3.2
typing-extensions 3.10.0.0
urllib3 1.26.6
wandb 0.12.4
wasabi 0.8.2
wcwidth 0.2.5
webencodings 0.5.1
widgetsnbextension 3.5.1
word2number 1.1
xxhash 2.0.2
yarl 1.6.3
yaspin 2.1.0
zc.lockfile 2.0

有一个问题是每次换numpy版本的时候都会重新下载这个文件，不知道为什么，每次要下载很久。

When I run the scipt, I get the error as follows:

FileNotFoundError: [Errno 2] No such file or directory: '../reclor-data/train_extended_context_cp_v5.npy'

“train_extended_context_cp_v5.npy” seems to be missing in reclor-data.