Song Duong

About Me

I am a 3rd year Ph.D. student at Criteo and CNRS-ISIR, Sorbonne University, under the direction of Patrick Gallinari and Alberto Lumbreras.

My PhD research revolves around the design of models that can generate text from structured data, such as tables or knowledge graphs. Lately, I have worked on the development of efficient architectures. I currently work on LLMs and their applications to various NLP tasks.

Research Interests

Natural Language Processing: large language models, efficient architectures, data-to-text generation.

News

[Mar. 2024] Our paper ‘LOCOST’ is honored with the Best Paper Award.
[Feb. 2024] Our paper ‘LOCOST’ is accepted and selected for an oral presentation at EACL 2024.
[July. 2023] Attending virtually the OxML 2023 summer school.
[Feb. 2023] Our paper on learning from multiple sources is accepted at AISTATS 2023.
[Jan. 2023] Attending virtually the ALPS 2023 winter school.

Publications

EACL

LOCOST: State-Space Models for Long Document Abstractive Summarization

Florian Le Bronnec*, Song Duong*, Mathieu Ravaut, Alexandre Allauzen, Nancy F. Chen, Vincent Guigue, Alberto Lumbreras, Laure Soulier, Patrick Gallinari (*equal contribution)

18th Conference of the European Chapter of the Association for Computational Linguistics, (EACL), 2024.

PDF Code BibTex Best Paper Award

AISTATS

Learning from Multiple Sources for Data-to-Text and Text-to-Data

Song Duong, Alberto Lumbreras, Mike Gartrell, Patrick Gallinari

26th International Conference on Artificial Intelligence and Statistics, (AISTATS), 2023.

PDF Code BibTex

About Me

Research Interests

News

Publications

Services

Conference Reviewers