Diego Garcia-Olano


2023

pdf
Using Captum to Explain Generative Language Models
Vivek Miglani | Aobo Yang | Aram Markosyan | Diego Garcia-Olano | Narine Kokhlikyan
Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)

Captum is a comprehensive library for model explainability in PyTorch, offering a range of methods from the interpretability literature to enhance users’ understanding of PyTorch models. In this paper, we introduce new features in Captum that are specifically designed to analyze the behavior of generative language models. We provide an overview of the available functionalities and example applications of their potential for understanding learned associations within generative language models.

2022

pdf
Intermediate Entity-based Sparse Interpretable Representation Learning
Diego Garcia-Olano | Yasumasa Onoe | Joydeep Ghosh | Byron Wallace
Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

Interpretable entity representations (IERs) are sparse embeddings that are “human-readable” in that dimensions correspond to fine-grained entity types and values are predicted probabilities that a given entity is of the corresponding type. These methods perform well in zero-shot and low supervision settings. Compared to standard dense neural embeddings, such interpretable representations may permit analysis and debugging. However, while fine-tuning sparse, interpretable representations improves accuracy on downstream tasks, it destroys the semantics of the dimensions which were enforced in pre-training. Can we maintain the interpretable semantics afforded by IERs while improving predictive performance on downstream tasks? Toward this end, we propose Intermediate enTity-based Sparse Interpretable Representation Learning (ItsIRL). ItsIRL realizes improved performance over prior IERs on biomedical tasks, while maintaining “interpretability” generally and their ability to support model debugging specifically. The latter is enabled in part by the ability to perform “counterfactual” fine-grained entity type manipulation, which we explore in this work. Finally, we propose a method to construct entity type based class prototypes for revealing global semantic properties of classes learned by our model. Code for pre-training and experiments will be made publicly available.

2021

pdf
Biomedical Interpretable Entity Representations
Diego Garcia-Olano | Yasumasa Onoe | Ioana Baldini | Joydeep Ghosh | Byron Wallace | Kush Varshney
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

2019

pdf
Learning Dense Representations for Entity Retrieval
Daniel Gillick | Sayali Kulkarni | Larry Lansing | Alessandro Presta | Jason Baldridge | Eugene Ie | Diego Garcia-Olano
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

We show that it is feasible to perform entity linking by training a dual encoder (two-tower) model that encodes mentions and entities in the same dense vector space, where candidate entities are retrieved by approximate nearest neighbor search. Unlike prior work, this setup does not rely on an alias table followed by a re-ranker, and is thus the first fully learned entity retrieval model. We show that our dual encoder, trained using only anchor-text links in Wikipedia, outperforms discrete alias table and BM25 baselines, and is competitive with the best comparable results on the standard TACKBP-2010 dataset. In addition, it can retrieve candidates extremely fast, and generalizes well to a new dataset derived from Wikinews. On the modeling side, we demonstrate the dramatic value of an unsupervised negative mining algorithm for this task.