Papers by Phillippe Langlais

12 papers
End-to-End Self-Debiasing Framework for Robust NLU Training (2021.findings-acl)

Copied to clipboard

Challenge: Existing models incorporate dataset biases leading to strong performance on in-distribution test sets but poor performance on out-of-distortion (OOD) tests.
Approach: They propose a debiasing framework where the shallow representations of the main model are used to derive a bias model and both models are trained simultaneously.
Outcome: The proposed framework outperforms existing approaches on three well-studied NLU tasks while still delivering high in-distribution performance.
Contextualized Word Representations from Distant Supervision with and for NER (D19-55)

Copied to clipboard

Challenge: Existing word embeddings for named entity recognition are stacked with traditional ones for downstream tasks.
Approach: They propose a special type of contextualized word representation that is learned from distant supervision annotations and dedicated to named entity recognition.
Outcome: The proposed representation surpasses the existing representations and is complementary to existing embeddings.
SEDAR: a Large Scale French-English Financial Domain Parallel Corpus (2020.lrec-1)

Copied to clipboard

Challenge: Existing approaches for neural machine translation use small amount of data or monolingual data.
Approach: They describe acquisition, preprocessing and characteristics of a large English-French parallel corpus for the financial domain.
Outcome: The proposed corpus contains 8.6 million high quality sentence pairs . the first release of the corpus is available on github.
Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging (2022.findings-emnlp)

Copied to clipboard

Challenge: Recent studies show that the flatness of the local minimum correlates well with better generalization.
Approach: They propose to use a method encouraging convergence to a flatter minimum to fine-tune PLMs.
Outcome: The proposed method outperforms state-of-the-art methods on NLP tasks without extra computation cost.
Human or Neural Translation? (2020.coling-main)

Copied to clipboard

Challenge: a recent study shows that deep neural models have improved machine translation . identifying machine translation is still feasible, but is not yet known.
Approach: They train and apply deep neural models to distinguish between human and machine translations . they use a monolingual and bilingual task to train and train 18 classifiers based on their results .
Outcome: The proposed model improves the ability to distinguish between human and machine translations at the sentence level.
HardEval: Focusing on Challenging Tokens to Assess Robustness of NER (2020.lrec-1)

Copied to clipboard

Challenge: Named entity recognition (NER) systems are often evaluated on human annotations . a new evaluation method focuses on subsets of tokens that represent specific sources of errors .
Approach: They propose a method that focuses on subsets of tokens that represent specific sources of errors.
Outcome: The proposed evaluation method focuses on subsets of tokens that represent specific sources of errors.
Robust Lexical Features for Improved Neural Network Named-Entity Recognition (C18-1)

Copied to clipboard

Challenge: Named-Entity Recognition (NER) uses word embeddings to extend, rather than replace, hand-crafted features.
Approach: They propose to embed words and entity types into a low-dimensional vector space and compute a feature vector representing each word offline.
Outcome: The proposed representations outperform existing models and achieve state-of-the-art performance.
Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing (2022.emnlp-main)

Copied to clipboard

Challenge: Existing pre-trained language models are not well-explored and are not reproducible in the literature.
Approach: They propose to improve existing Arabic language pre-trained language models using a more methodical approach.
Outcome: The proposed models outperform existing models on ALUE, a leaderboard-powered benchmark for Arabic NLU and NLG tasks.
CILDA: Contrastive Data Augmentation Using Intermediate Layer Knowledge Distillation (2022.coling-1)

Copied to clipboard

Challenge: Knowledge distillation (KD) is an efficient framework for compressing large-scale pre-trained language models.
Approach: They propose a data augmentation technique tailored for knowledge distillation based on contrastive loss to improve masked adversarial data augmented by intermediate layer matching.
Outcome: The proposed technique outperforms state-of-the-art methods on the GLUE benchmark and in an out-of domain evaluation.
LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for regularizing deep neural networks rely on weight decay, dropout, batch/layer normalization to converge faster and generalize.
Approach: They propose a framework for training with label regularization which includes conventional LS but can also model instance-specific variants.
Outcome: The proposed approach consistently yields better results than conventional regularization on seven machine translation and three image classification tasks while maintaining training efficiency.
Part-Of-Speech Sensitivity of Routers in Mixture of Experts Models (2025.coling-main)

Copied to clipboard

Challenge: a study examines the behavior of routers in Mixture of Experts (MoE) models . experts with similar linguistic traits are often routed to the same expert regardless of context .
Approach: They investigate how tokens are routed based on their linguistic features . they aim to explore whether experts specialize in processing tokens with similar linguistic traits .
Outcome: The proposed model-integrated routers are based on Mixture of Experts (MoE) models . the results show that expert specialization is high for POS categories .
Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora (2020.coling-main)

Copied to clipboard

Challenge: Narrow specialized comparable corpora are small in size, making it difficult to build efficient models to acquire translation equivalents.
Approach: They propose to use Tf-Idf and cross entropy to improve bilingual lexicon induction from specialized comparable corpora by a factor of 10 .
Outcome: The proposed methods improve bilingual lexicon induction by a large margin.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations