Homepage
Close
Menu

Site Navigation

  • Home
  • Archive(TODO)
    • By Day
    • By Month
  • About(TODO)
  • Stats
Close
by seb_ruder on 2020-01-28 (UTC).

The other dimension here is monolingual vs multilingual models. I think monolingual models in low-resource languages currently have an edge e.g. as seen in our MultiFiT paper.

— Sebastian Ruder (@seb_ruder) January 28, 2020
nlpresearchthought
by Thom_Wolf on 2020-01-28 (UTC).

I feel like good-old LSTM (or QRNN) are usually better for text classification indeed.

Note that for those who want to give a try at text classification with pretrained Bert models, you can give a look at the experimental section of this paper https://t.co/w4MWPTB79u

— Thomas Wolf (@Thom_Wolf) January 28, 2020
nlpthought
by Smerity on 2020-01-28 (UTC).

Even my continued fiddling with the SHA-RNN model shows there's a _lot_ to be studied and explored. I haven't published new incremental progress but you can tie the RNN across the 4 layers to substantially decrease total params yet get nearly equivalent perplexity results.

— Smerity (@Smerity) January 28, 2020
nlpresearchthought

Tags

learning tutorial misc nlp rstats gan ethics research dataviz survey python tool security kaggle video thought bayesian humour tensorflow w_code bias dataset pytorch cv tip application javascript forecast swift golang rl jax julia gnn causal surey diffusion
© Copyright Philosophy 2018 Site Template by Colorlib