Search Results for author: Sajjadur Rahman

Found 7 papers, 1 papers with code

Towards integrated, interactive, and extensible text data analytics with Leam

no code implementations NAACL (DaSH) 2021 Peter Griggs, Cagatay Demiralp, Sajjadur Rahman

From tweets to product reviews, text is ubiquitous on the web and often contains valuable information for both enterprises and consumers.

Low-resource Entity Set Expansion: A Comprehensive Study on User-generated Text

1 code implementation Findings (NAACL) 2022 Yutong Shao, Nikita Bhutani, Sajjadur Rahman, Estevam Hruschka

Entity set expansion (ESE) aims at obtaining a more complete set of entities given a textual corpus and a seed set of entities of a concept.

MEGAnno+: A Human-LLM Collaborative Annotation System

no code implementations28 Feb 2024 Hannah Kim, Kushan Mitra, Rafael Li Chen, Sajjadur Rahman, Dan Zhang

Large language models (LLMs) can label data faster and cheaper than humans for various NLP tasks.

Management

Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions

no code implementations2 Feb 2024 Pouya Pezeshkpour, Eser Kandogan, Nikita Bhutani, Sajjadur Rahman, Tom Mitchell, Estevam Hruschka

We present a formal definition of reasoning capacity and illustrate its utility in identifying limitations within each component of the system.

Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks

no code implementations9 Nov 2023 Aditi Mishra, Sajjadur Rahman, Hannah Kim, Kushan Mitra, Estevam Hruschka

We consider the task of generating knowledge-guided rationalization in natural language by using expert-written examples in a few-shot manner.

Multiple-choice World Knowledge

Towards Multifaceted Human-Centered AI

no code implementations9 Jan 2023 Sajjadur Rahman, Hannah Kim, Dan Zhang, Estevam Hruschka, Eser Kandogan

Human-centered AI workflows involve stakeholders with multiple roles interacting with each other and automated agents to accomplish diverse tasks.

Leam: An Interactive System for In-situ Visual Text Analysis

no code implementations8 Sep 2020 Sajjadur Rahman, Peter Griggs, Çağatay Demiralp

Text data analysis is an iterative, non-linear process with diverse workflows spanning multiple stages, from data cleaning to visualization.

Cannot find the paper you are looking for? You can Submit a new open access paper.