Skip to content

Wiki Langage

Thursday at 13:00 in 26-00/536 or online on this Big Blue Button instance while social distancing is recommended.

Future meetings

When Who What
2019-06-25 Bruno Few-sample BERT Fine-tuning
2019-07-02 Everyone 0.2 paper per minute

Past meetings

When Who What Details
2020-06-18 Étienne The Dynamic Embedded Topic Model paper
2020-03-26 Agnès GAN for Language Modeling Long Text Generation via Adversarial Training with Leaked Information, Self-Adversarial Learning with Comparative Discrimination for Text Generation
2020-03-12 Étienne Few-Shot Relation Classification Datasets Fewrel: A large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation, FewRel 2.0: Towards more challenging few-shot relation classification
2020-03-05 Clément LOLS (Locally Optimal Learning to Search) and Data-to-Text Learning to Search Better than Your Teacher, Imitation learning for language generation from unaligned data
2020-01-30 Bruno Bertology Literature - Hierarchy + analysis of attention
2020-01-23 Adrien Language Model Analysis (LAMA) Language Models as Knowledge Bases?, Negated LAMA: Birds cannot fly, BERT is Not a Knowledge Base (Yet): Factual Knowledge vs. Name-Based Reasoning in Unsupervised QA
2019-12-12 Everyone Birthday Cake image-5f819241-8bc1-499e-9a91-c9bac4dbee1c
Étienne Harris' Distributional Structure paper
2019-11-28 Agnès Suggestion de requêtes avec des transformers
2019-11-21 Adrien Chatbot for Information Retrieval
2019-11-14 Clara Professional Profile Extraction
2019-10-31 Étienne Matching the Blanks: Distributional Similarity for Relation Learning paper
Valentin Answering Complex Open-domain Questions Through Iterative Query Generation paper
2019-10-24 Étienne Latent Structure Models for Natural Language Processing ACL slides
2019-10-10 Adrien Adversarial Learning of Task-Oriented Neural Dialog Models paper
2019-07-12 Thomas Text summarization
2019-07-02 Étienne Tuto Attention is all you need encoder-decoder, attention, attention dot product, end-to-end memnet, attention is all you need
Bruno Tuto Contextualized Word Embeddings
Tuto Named Entity Recognition
2019-06-20 Étienne Tuto Tâches et métriques On Chomsky and the Two Cultures of Statistical Learning
Liste de tâches sur Wikipédia, BLEU sur Wikipédia
Le script standard de moses multi-bleu.perl
Bruno Tuto Word Embeddings (Bengio 2003) A Neural Probabilistic Language Model
(Collobert 2008) A unified architecture for natural language processing: Deep neural networks with multitask learning
word2vec, GloVe
Edouard Tuto Language model, LSTM et Subwords LSTM: A search space odyssey, Capacity and trainability in recurrent neural networks, The Unreasonable Effectiveness of Recurrent Neural Networks
Tips and tricks: On the State of the Art of Evaluation in Neural Language Models, Regularizing and Optimizing LSTM Language Models
Subwords: BPE (Wikipédia, implémentation), WordPiece (implémentation), Subword (implémentation)
2019-06-13 Adrien Document Expansion by Query Prediction paper
Edouard State of the Art LSTM Language Modeling On the State of the Art of Evaluation in Neural Language Models, Regularizing and Optimizing LSTM Language Models
2019-06-06 Adrien From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing paper
Jean-Yves Learning Embeddings into Entropic Wasserstein Spaces paper
Bruno Fair is Better than Sensational: Man is to Doctor as Woman is to Doctor paper
Knowledge-Augmented Language Model and Its Application to Unsupervised Named-Entity Recognition paper
2019-04-18 Étienne Non-monotonic Sequential Text Generation paper
Valentin Atention is not Explanation paper
2019-04-11 Adrien « Hé Manu, tu descends ? » : identification nommée du locuteur dans les dialogues paper
2019-03-28 Valentin Meta-Learning for Low-Resource Neural Machine Translation paper
2019-03-21 Eloi Super librairie d'évaluation de word embeddings github
2019-03-14 Charles Multiple Attribute Text Rewriting paper
Valentin Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering paper
2019-03-07 Eloi Do Neural Network Cross-Modal Mappings Really Bridge Modalities? paper
Adrien From Natural Language to Keyword Queries paper
Étienne Word Embeddings and PMI Factorization
2019-02-28 Aurelia Suivi et génération d'instructions
2019-02-21 Valentin Multi-style Generative Reading Comprehension paper
Edouard Variational Autoencoding of Textual Data Generating sentences from a continuous space, Improved variational autoencoders for text modeling using dilated convolutions
Jean-Yves Universal Transformers paper
2019-02-14 Thomas Question Answering & Question Generation
2019-02-07 Étienne Compressing Word Embeddings via Deep Compositional Code Learning paper
Bruno A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks paper
Patrick Word Translation without Parallel Data paper
Clara TransNets: Learning to Transform for Recommendation paper
2019-01-31 Bruno Lexical Overlap in Named Entity Recognition
2019-01-24 Étienne Unsupervised Relation Extraction
2019-01-17 Valentin Question Answering
2019-01-10 Clément Pointer Networks paper
2018-12-20 Patrick Unsupervised machine translation using monolingual corpora only paper
Étienne Attention is all you need encoder-decoder, attention, attention dot product, end-to-end memnet, attention is all you need
2018-12-06 Clara Réseaux Hiérarchiques Attentifs pour la Représentation de Carrières Professionnelles
2018-11-29 Étienne An overview of word representations word2vec, GloVe, fasttext, CoVe, ELMo, GPT, BERT