Siddharth Parekh

Hi! I’m Siddharth, a senior studying Computer Science at CMU. My current research interests lie in the intersection of natural language processing, machine learning, and game theory - towards building intelligent systems using language agents.

I’ve worked extensively with Professor Carolyn Rosé’s Document Understanding Group at CMU’s Language Technologies Institute - collaborating with Armineh Nourbakhsh on developing graph-based models for form processing, and robust evaluation metrics for document visual question answering.

Zooming out, I often find myself along the confluence of mathematics and computer science hoping to find innovative applications with strong theoretical foundations.

Feel free to reach out to me to chat about my research or any shared interests!

news

Sep 20, 2024	AliGATr got accepted to EMNLP 2024!

selected publications

AliGATr: Graph-based layout generation for form understanding

Armineh Nourbakhsh, Zhao Jin, Siddharth Parekh, and 2 more authors

In Findings of the Association for Computational Linguistics: EMNLP 2024, Nov 2024

Abs DOI

Forms constitute a large portion of layout-rich documents that convey information through key-value pairs. Form understanding involves two main tasks, namely, the identification of keys and values (a.k.a Key Information Extraction or KIE) and the association of keys to corresponding values (a.k.a. Relation Extraction or RE). State of the art models for form understanding often rely on training paradigms that yield poorly calibrated output probabilities and low performance on RE. In this paper, we present AliGATr, a graph-based model that uses a generative objective to represent complex grid-like layouts that are often found in forms. Using a grid-based graph topology, our model learns to generate the layout of each page token by token in a data efficient manner. Despite using 30% fewer parameters than the smallest SotA, AliGATr performs on par with or better than SotA models on the KIE and RE tasks against four datasets. We also show that AliGATr’s output probabilities are better calibrated and do not exhibit the over-confident distributions of other SotA models.