Paul Tardy

`run_summarization.py` isn't computing on GPU (but allocate memory)

15

Strange fact. I've been trying to train summarization with default parameters and default dataset. It turns out that the GPU is detected (`2017-06-01 17:57:05.548650: I tensorflow/core/common_runtime/gpu/gpu_device.cc:977] Creating TensorFlow device (/gpu:0)...

Hi, I slightly modified the checkpoint loading so that the decoding first look for a `best_model` in the `eval` directory for the decoding. This makes more sense to me, you...

Experimental n-gram exclusion from ROUGE calculation. **Not ready to merge**

About ROUGE scores

5

Hi, I used the `seq2seq/metrics/rouge.py` on my [repo](https://github.com/pltrdy/rouge) to add some features. I wanted to check my results, therefore I compared my script, with yours, and with [pyrouge (a wrapper...

Benchmarking

3

Hi, Would you be interested in benchmarking Python ROUGE wrappers? I worked on my own solution for ROUGE evaluation over files (using two files `f1`, `f2`, reading each line `l1_i...

Recommandation (unsupervised/low ressource text alignment)

1

Hey guys, Good work both on MatchZoo and this list! I would be interested in quick advices/pointers on something related: I'd like to match related parts of texts. More formally,...

Hi! Could you release your systems predictions with respect to the NYT dataset please (optionally also the trained model?)

Otherwise I get error than type `set` isn't JSON serializable, i.e. `TypeError: {'Business'} is not JSON serializable`

Hallucination on successive generation

7

Hi, I'm probably missing something about how ollama works or am I facing a kind of side effect. I use a super simple code to get 3 outputs given a...

Predictions on NYT dataset

1

Hi, I'd be interesting in your systems predictions on the NYT dataset for research (any published work would of course cite your paper). If you cannot share it because of...