Papers by Pascal Vincent

7 papers
Flow Matching for Conditional Text Generation in a Few Sampling Steps (2024.eacl-short)

Copied to clipboard

Challenge: Current diffusion models face multiple drawbacks including slow sampling, noise schedule sensitivity, and misalignment between training and sampling stages.
Approach: They propose a method which leverages flow matching for conditional text generation.
Outcome: The proposed method can generate text in a few steps by training with a novel anchor loss, alleviating the need for expensive hyperparameter optimization of the noise schedule prevalent in diffusion models.
Chop and Change: Anaphora Resolution in Instructional Cooking Videos (2022.findings-aacl)

Copied to clipboard

Challenge: temporally evolving entities present challenges for anaphora resolution tasks . recipes provide rich source for referring expressions of transformed entities .
Approach: They propose to use annotations to annotate recipes for anaphora resolution task . they propose to employ temporal features to improve anamorphic resolution .
Outcome: The proposed annotation scheme improves the performance of the anaphora resolution task.
MMAR: Multilingual and Multimodal Anaphora Resolution in Instructional Videos (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to multilingual anaphora resolution include images and video inputs.
Approach: They propose to include multimodal information in the form of images in anaphora resolution tasks.
Outcome: The proposed approach improves resolution by 10% for unseen languages.
Find-2-Find: Multitask Learning for Anaphora Resolution and Object Localization (2023.emnlp-main)

Copied to clipboard

Challenge: Existing systems require large number of accurate annotations, such as image-level labels and location-level labeling.
Approach: They propose a joint anaphora resolution and object localization dataset targeting visual-linguistic ambiguity.
Outcome: The proposed framework improves visual-linguistic alignment and object localization with one joint model compared to a strong single-task baseline.
Auto-Encoding Dictionary Definitions into Consistent Word Embeddings (D18-1)

Copied to clipboard

Challenge: Monolingual dictionaries are widespread and semantically rich resources.
Approach: They propose a model that learns to compute word embeddings by processing dictionary definitions and trying to reconstruct them.
Outcome: The proposed model shows strong performance when trained exclusively on dictionary data and generalizes in one shot.
The Emergence of Argument Structure in Artificial Languages (2022.tacl-1)

Copied to clipboard

Challenge: a new study shows that natural languages are shaped by cognitive and sociocultural factors.
Approach: They propose a setup where agents talk about a variable number of entities that can be partially observed by the listener.
Outcome: The proposed setup shows that awareness of object structure yields a more natural sentence organization.
Do sequence-to-sequence VAEs learn global features of sentences? (2020.emnlp-main)

Copied to clipboard

Challenge: Autoregressive language models are often trained without explicit conditioning labels . authors question claim that latent vectors can capture global features in unsupervised manner .
Approach: They propose to use a sequence-to-sequence architecture to learn latent variables . they find that VAEs are prone to memorizing the first words and sentence length .
Outcome: The proposed model is prone to memorizing the first words and sentence length, the authors show . et al., 2016: a new model learns latent variables that are more global, more predictive of topic or topic labels . authors question this claim, say it is a waste of time and money .

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