data2text

data2text copied to clipboard

Thanks for your sharing. In model training, there shows 'ppl' (I guess). What's more , there are other metrics in evaluation, such as RG, CO and CS. So which one...

JianyuZhao7

Hi, thanks for the awesome code and paper and datasets! I got this problem when I run the extractor.lua: /usr/bin/luajit: /usr/share/lua/5.1/torch/File.lua:351: cuda runtime error (2) : out of memory at...

LTlitong

CUDNN_STATUS_BAD_PARAM problem when running extractor.lua for training convolutional extraction model

1

Hi~Need some help here. When training convolution IE model using extractor.lua, I met _Error in CuDNN: CUDNN_STATUS_BAD_PARAM (cudnnSetConvolutionNdDescriptor)_

LarryLee-BD

Possible PyTorch version of the code?

1

Hi, thanks for the awesome code and paper and datasets! Since there has been a trend of increasing PyTorch usage in NLP areas, and OpenNMT also has a pytorch version,...

frankxu2004

A bug regarding text numbers in data_utils.py

1

In line 134 and 136, it should be `and annoying_number_word(sent, i)` rather than `and not annoying_number_word(sent, i)`, since the function returns True if it's not saying three-point related stuff.

frankxu2004

[Here](https://github.com/harvardnlp/data2text/blob/203281f20f8c6ce67ed1f2b28cd3a8fcb09a94ac/data_utils.py#L372) you're getting `num_to_keep` based on the number of examples not labeled as NONE (`len(trlabels)-len(none_idxs)`); however, according to the comment above you should use the number of examples labeled as...

wwt17

Here are several issues I find in the rule-based entity/number extraction functions in `data_utils.py`. I'm still working on the dataset and will probably update more once I observe them. These...

wwt17