Lorenzo Flores (Lj)

Lorenzo Flores (Lj)

Excited by NLP and good coffee, proudly Filipino

Hello!

And thank you for stopping by!

I am Lorenzo Flores, an MSc thesis student at MILA (Montreal Institute for Learning Algorithms) and McGill University, with Professor Jackie Cheung.

Previously, I worked with Prof. Arman Cohan on summarization and simplification. I completed a joint BS/MA in statistics at Yale University, where I worked with Prof. Dragomir Radev and Linyong Nan (LILY Lab) on NLP for tabular data.

I am interested in making NLP and machine learning work when data is scarce, and am excited to see its applications in low-resource scenarios (especially in the Philippines)!

Before coming to Montreal, I was a data scientist at McKinsey and Company (QuantumBlack) in New York, and interned with Elicit as a machine learning engineer!

Selected Publications

Improving Factuality & Accuracy of Language Models

  • Lorenzo Flores and Arman Cohan. On the Benefits of Fine-Grained Loss Truncation: A Case Study on Factuality in Summarization, EACL 2024 [Paper, Video, Code]
  • Lorenzo Flores, Heyuan Huang, Kejian Shi, Sophie Chheang, and Arman Cohan. 2023. Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decoding, EMNLP 2023 Findings [Paper, Video, Code, Demo]
  • Linyong Nan, Lorenzo Flores, Yilun Zhao, Yixin Liu, Luke Benson, Weijin Zou, and Dragomir Radev. 2022. R2D2: Robust Data-to-Text with Replacement Detection, EMNLP 2022 [Paper]
  • Lorenzo Flores, Yiding Hao. 2022. Adversarial Benchmark for Fake News Classification. AAAI 2022 AdvML Workshop [Paper, Code]

Low Resource Applications

  • Lorenzo Flores, Dragomir Radev. 2022. Look Ma, Only 400 Samples! Revisiting the Effectiveness of Automatic N-Gram Rule Generation for Spelling Normalization in Filipino, EMNLP 2022 SustaiNLP Workshop [Paper, Video, Code]

  • Chiara Ledesma, Oshean Lee Garonita, Lorenzo Flores, Isabelle Tingzon, and Danielle Dalisay. 2020. Interpretable Poverty Mapping using Social Media Data, Satellite Images, and Geospatial Information, ML4D Workshop, NeurIPS 2020, Best Workshop Paper Award [Paper]

ML Projects I’m Working On (!)

  • LossLibrary: a repository that consolidates loss functions from NLP literature and helps users integrate it into training [Here!]

Other Projects (!)

  • CPG Lookup: a lookup tool for Philippine clinical practice guidelines using semantic search [Here!]