Nelson Liu's Blog

nlp

Software Archaeology: Re-generating the CoNLL 2000 Chunking Data

I've been using the data from the CoNLL 2000 shared task on syntactic chunking for some ongoing work, but the original dataset is tiny by modern standards. The train set...

Extracting last timestep outputs from PyTorch RNNs

Here's some code I've been using to extract the last hidden states from an RNN with variable length input....

Some work I liked at ACL 2017

I was fortunate to attend ACL 2017 last week in Vancouver. There was a lot of great work on a variety of topics, and I'll quickly mention some papers/talks/...

Paraphrase Identification Models in Tensorflow

I've been loosely hacking on the Quora Question Pairs dataset in my free time to get some more experience working with vanilla Tensorflow for NLP in a practical setting. Yesterday,...