Shubham Agarwal

GC overhead limit when mining wikipedia and extracting anchor text

2

Hi I am following the steps provided [here](https://github.com/yahoo/FEL/blob/master/src/main/java/com/yahoo/semsearch/fastlinking/io/README.md) to train my model. I have pre-processed the datapack. But when I am trying to "Build Data Structures and extract anchor text",...

Thank you for providing the code. We were trying out to mine wikipedia using [this shell script](https://github.com/yahoo/FEL/blob/d6050b26cd7e6beb9ba0714e6461b392973014f6/src/main/bash/mine-datapack.sh) for our entity linker using the dump for 2018/05/01. We were able to...

Is beam search working fine?

4

Is your beam search bug free? I tried to use your decoder in a seq2seq model and getting some weird results when beam width>1. (BLEU falls from 40 to 4)....

Handling special characters for character seq2seq model

3

I was trying to train the model for the character level seq2seq model. My source and target file (both in utf-8 encoding) contains special characters such as the pound symbol....

Backtracking in beam search

6

Compared to OpenNMT, why do we need this [block](https://github.com/IBM/pytorch-seq2seq/blob/master/seq2seq/models/TopKDecoder.py#L257) which handles the dropped sequences that see EOS earlier. (This is not there in their beam search implementation.) They are also...

Hi, I am using boto mturk api for crowdsourcing. Is it possible to filter and identify qualifying AMT workers using very small test cases before they start the actual HIT?...

Bounding box coordinates

1

Hi @kdexd , Is it possible to release the bounding box information (co-ordinates/labels) of the detectron features to actually map these features to the original images. Thanks.

Shared memory issues with parallelization

5

Hi @kdexd I am running into all kinds of shared memory errors after this commit 9c1ee36b85c2c63d554471cac2825cf0b9cf2efd https://github.com/pytorch/pytorch/issues/8976 https://github.com/pytorch/pytorch/issues/973 I guess this parallelization is not stable; sometimes it run while sometimes...

Beam search backtracking

2

Hi, Thank you providing this code. Could you explain your code for backtracking in beam search. In particular how do you handle the dropped sequences that have seen EOS earlier...

data_utils.py List index out of range

12

While creating train-roto-ptrs.txt using ptrs mode, I am getting this index error: ``` Traceback (most recent call last): File "data_utils.py", line 859, in make_pointerfi(args.output_fi, inp_file=args.input_path, content_plan_inp=args.train_content_plan) File "data_utils.py", line 593,...