Papers by Alexis Conneau

11 papers
Multilingual Speech Translation from Efficient Finetuning of Pretrained Models (2021.acl-long)

Copied to clipboard

Challenge: Recent advances in text pretraining and finetuning have improved multitasking applications significantly.
Approach: They propose a minimalistic LNA finetuning approach to build multilingual speech-to-text translation using a pretrained speech encoder and text decoder.
Outcome: The proposed approach surpasses the cascaded ST benchmark for 36 translation directions on the large-scale multilingual ST benchmark CoVoST 2.
Self-training Improves Pre-training for Natural Language Understanding (2021.naacl-main)

Copied to clipboard

Challenge: Unsupervised pretraining has led to improvements in natural language understanding . a data augmentation method can be used to generate labels for unlabeled examples .
Approach: They propose a semi-supervised method which uses unlabeled data to retrieve sentences from a database of billions of unlabed sentences crawled from the web.
Outcome: The proposed method improves on standard text classification benchmarks by 2.6% and knowledge distillation by few shots.
Learning Visually Grounded Sentence Representations (N18-1)

Copied to clipboard

Challenge: Unsupervised sentence representation models suffer from the grounding problem because of lack of association between symbols and external information.
Approach: They train a sentence encoder to predict image features of a caption and use them as sentence representations.
Outcome: The proposed model improves on word embeddings and word representations on standard benchmarks.
Unsupervised Cross-lingual Representation Learning at Scale (2020.acl-main)

Copied to clipboard

Challenge: Pretraining multilingual language models at scale leads to performance gains for cross-lingual transfer tasks.
Approach: They present a transformer-based multilingual masked language model pre-trained on 100 languages . they show that pretraining multilingual models at scale leads to significant performance gains .
Outcome: The proposed model outperforms multilingual BERT (mBERT) on cross-lingual benchmarks.
Emerging Cross-lingual Structure in Pretrained Language Models (2020.acl-main)

Copied to clipboard

Challenge: Recent work has shown that multilingual pretraining works, but is unable to measure these effects.
Approach: They propose to use multilingual masked language modeling to train a model on concatenated text from multiple languages to find universal latent symmetries in embedding spaces.
Outcome: The proposed models can be trained on concatenated text from multiple languages without shared vocabulary or domain similarity.
What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties (P18-1)

Copied to clipboard

Challenge: a lack of understanding of the properties of sentence embeddings is limiting the use of the techniques.
Approach: They propose 10 probing tasks designed to capture simple linguistic features of sentences . they use three different encoders to train embeddings in eight different ways .
Outcome: The proposed tasks capture key linguistic features of sentences, but they are difficult to infer from them.
CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data (2020.lrec-1)

Copied to clipboard

Challenge: Pre-training text representations have led to significant improvements in many areas of natural language processing.
Approach: They propose a pipeline to extract monolingual datasets from Common Crawl . pipeline follows data processing introduced in fastText that deduplicates documents .
Outcome: The proposed pipeline performs standard document deduplication and language identification similar to the pipeline introduced in fastText and a filtering step to select documents close to high quality corpora like Wikipedia.
Phrase-Based & Neural Unsupervised Machine Translation (D18-1)

Copied to clipboard

Challenge: Recent advances in machine translation have reported near human-level performance on several languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences.
Approach: They propose two models that leverage a careful initialization of the parameters and denoising effect of language models.
Outcome: The proposed models outperform the current methods on English-French and German-English benchmarks while being simpler and having fewer hyper-parameters.
XNLI: Evaluating Cross-lingual Sentence Representations (D18-1)

Copied to clipboard

Challenge: State-of-the-art natural language processing systems rely on annotated data to learn competent models.
Approach: They extend the development and test sets of the Multi-Genre Natural Language Inference Corpus to 14 languages, including Swahili and Urdu.
Outcome: The proposed evaluation set extends the development and test sets of the Multi-Genre Natural Language Inference Corpus (MultiNLI) to 14 languages including low-resource languages such as Swahili and Urdu.
SentEval: An Evaluation Toolkit for Universal Sentence Representations (L18-1)

Copied to clipboard

Challenge: a toolkit for evaluating the quality of universal sentence representations is available for download and preprocessing . word embeddings are not trained to perform well on one specific task, but their value lies in their transferability . evaluation of general-purpose word and sentence embeddables has been problematic .
Approach: They propose a toolkit to evaluate the quality of universal sentence representations.
Outcome: The proposed toolkit includes scripts to download and preprocess datasets and an easy interface to evaluate sentence encoders.
Toward Joint Language Modeling for Speech Units and Text (2023.findings-emnlp)

Copied to clipboard

Challenge: Speech and text are two major forms of human language and little effort has been made to model them together.
Approach: They propose to combine speech and text models to create mixed speech-text data by using different tokenizers and automatic metrics to evaluate how well the model mixes speech and texts.
Outcome: The proposed model improves over a speech-only baseline and shows zero-shot cross-modal transferability.

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