Linus Lin

icon indicating a website link https://pjlintw.github.io/ icon indicating an email [email protected]

icon company LLMs Lab, Virginia Tech icon location Virginia icon location researching efficient NLP, particularly module representation learning and data efficiency.

Results 2 issues of Linus Lin

Why using Glove in compressor instead of pretrained embeddings from LM prior

The compressor and reconstructor are using Glove as their embedding layer. I am curious about why did you use Glove instead of embedding from LM prior.

encoder state in `matching_encoder_utils.py`

4 comment

I read the paper "Leveraging Context Information for Natural Question Generation". Section 2.2 says: > Each encoder state hj is the concatenation of two bi-directional LSTM states (Section 3.2 also...