@deep_spin

Deep structured prediction in NLP. ERC project coordinated by @andre_t_martins. Instituto de Telecomunicações.

 Lisbon, Portugal
deep-spin.github.io/
Joined August 2018
  • Tweets23
  • Following72
  • Followers348
5Media
Our group is headed to #acl2019nlp! Come chat at our posters and presentations listed in the attached image. More info in thread 👇👇 [1/11]
1
4
1
30
Adaptively Sparse Transformers @emnlp2019 +Gonçalo Correia, André Martins α-entmax attention α=1: softmax, α=2: sparsemax, continuous in between. twist: we learn α for each head, w gradients! Some heads become dense, some sparse. arxiv.org/abs/1909.00015 github.com/deep-spin/entmax
2
31
1
111
Joint Learning of Named Entity Recognition and Entity Linking Pedro Henrique Martins, Zita Marinho, André Martins arxiv.org/abs/1907.08243 Tue 30, SRW, Posters 2 10:30–12:10 [5/11]
2
4
(forgot to tag @pedrohenmartins!)
BERT-based Encoder-Decoder for Automatic Post-Editing WMT APE shared task winner! António Lopes, Amin Farajian, Gonçalo M Correia, Jonay Trénous, André Martins arxiv.org/abs/1905.13068 Fri 2, WMT APE 11:00–12:30 [10/11]

Unbabel's Submission to the WMT2019 APE Shared Task:...

This paper describes Unbabel's submission to the WMT2019 APE Shared Task for the English-German language pair. Following the recent rise of large, powerful, pre-trained models, we adapt the BERT...

arxiv.org
1
2
Unbabel's Participation in the WMT'19 Translation Quality Estimation Shared Task WMT QE s. t. winner! Fábio Kepler, Jonay Trénous, Marcos Treviso, Miguel Vera, António Góis, Amin Farajian, António Lopes, André Martins arxiv.org/abs/1907.10352 Fri 2, WMT APE 11:00–12:30 [11/11]
3
The Variational Inference Tutorial tour stopped by our lab! Thank you @wilkeraziz for a fantastic tutorial and a visit full of exciting discussion!
1
9
Slides and plenty of useful resources at vitutorial.github.io/

About

vitutorial.github.io
A nice write-up of the challenges of lemmatization by DeepSPINner Erick! Multilingual examples reveal different complexities hard to imagine if focusing on English.
Erick Fonseca@Erick40412 Mar 2019
My overview of state-of-the-art lemmatization medium.com/@erickrfonseca/st…
2
DeepSPIN talks at #emnlp2018 ! - Thu, 11:00AM, talk @ Blackbox NLP Interpretable Structure Induction via Sparse Attention. Peters/Niculae/Martins. - Fri, 3:36PM, main conf talk @ ML(3B) Towards Dynamic Computation Graphs via Sparse Latent Structure. Niculae/Martins/Cardie.
1
7
Towards Dynamic Computation Graphs via Sparse Latent Structure: #emnlp2018 + André @clairecardie - marginalize over structured latent vars w/ SparseMAP - CG a function of discrete structure - eg latent dependency TreeLSTM pdf arxiv.org/abs/1809.00653 code github.com/vene/sparsemap/tr… – at Lisbon, Portugal
1
44
108
"Structure Back in Play, Translation Wants More Context" DeepSPINner André Martins writes on the @Unbabel R&D blog his notes from this year's #icml2018 and #ACL2018: medium.com/unbabel/icml-acl0…

ICML+ACL'18: Structure Back in Play, Translation Wants More Context

Thoughts on this year's International Conference in Machine Learning and Annual Conference of the Association for Computational…

medium.com
3
16
DeepSPIN will be at #emnlp2018! 1) SparseMAP for latent dynamic computation graphs; @vnfrombucharest, André Martins and @clairecardie; 2) Discussing the interpretability of sparse/structured attention; @bpopuw, @vnfrombucharest, Martins at #BlackboxNLP. (preprints soon) -->
1
1
15
1) "Towards dynamic computation graphs via sparse latent structure": @vnfrombucharest, André Martins, @clairecardie - marginalize over structured latent variables with SparseMAP - computation graph conditions globally on discrete structure - e.g: latent dependency TreeLSTM
1
2
10
2) #BlackboxNLP Interpretable structure induction via sparse attention: @bpopuw, @vnfrombucharest, André Martins We discuss the interpretability angle of recent & ongoing work on sparse, structured and constrained attention: sparsemax, fusedmax, constrained sparsemax, SparseMAP
5
Load more