Search

Your search keyword '"Narasimhan, Karthik"' showing total 4 results
Start Over Author "Narasimhan, Karthik" Publisher association for computational linguistics (acl)
4 results on '"Narasimhan, Karthik"'

1. Quantifying learning-style adaptation in effectiveness of LLM teaching

Author

Deshpande, Ameet, Hwang, EunJeong, Murahari, Vishvak, Park, Joon Sung, Yang, Diyi, Sabharwal, Ashish, Narasimhan, Karthik, Kalyan, Ashwin, Weijers, Ruben, De Castilho, Gabrielle Fidelis, Godbout, Jean François, Rabbany, Reihaneh, Pelrine, Kellin, Deshpande, Ameet, Hwang, EunJeong, Murahari, Vishvak, Park, Joon Sung, Yang, Diyi, Sabharwal, Ashish, Narasimhan, Karthik, Kalyan, Ashwin, Weijers, Ruben, De Castilho, Gabrielle Fidelis, Godbout, Jean François, Rabbany, Reihaneh, and Pelrine, Kellin

Published
2024

2. LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models

Author

Deshpande, Ameet, Hwang, EunJeong, Murahari, Vishvak, Park, Joon Sung, Yang, Diyi, Sabharwal, Ashish, Narasimhan, Karthik, Kalyan, Ashwin, Frisch, Ivar, Giulianelli, Mario, Deshpande, Ameet, Hwang, EunJeong, Murahari, Vishvak, Park, Joon Sung, Yang, Diyi, Sabharwal, Ashish, Narasimhan, Karthik, Kalyan, Ashwin, Frisch, Ivar, and Giulianelli, Mario

Published
2024

3. Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge

Author

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Locascio, Nicholas (Nicholas J.), Narasimhan, Karthik Rajagopal, De Leon, Eduardo, Kushman, Nate, Barzilay, Regina, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Locascio, Nicholas (Nicholas J.), Narasimhan, Karthik Rajagopal, De Leon, Eduardo, Kushman, Nate, and Barzilay, Regina

Abstract

This paper explores the task of translating natural language queries into regular expressions which embody their meaning. In contrast to prior work, the proposed neural model does not utilize domain-specific crafting, learning to translate directly from a parallel corpus. To fully explore the potential of neural models, we propose a methodology for collecting a large corpus of regular expression, natural language pairs. Our resulting model achieves a performance gain of 19.6% over previous state-of-the-art models.

Published
2020

4. Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning

Author

Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Narasimhan, Karthik Rajagopal, Yala, Adam, Barzilay, Regina, Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Narasimhan, Karthik Rajagopal, Yala, Adam, and Barzilay, Regina

Abstract

Most successful information extraction systems operate with access to a large collection of documents. In this work, we explore the task of acquiring and incorporating external evidence to improve extraction accuracy in domains where the amount of training data is scarce. This process entails issuing search queries, extraction from new sources and reconciliation of extracted values, which are repeated until sufficient evidence is collected. We approach the problem using a reinforcement learning framework where our model learns to select optimal actions based on contextual information. We employ a deep Qnetwork, trained to optimize a reward function that reflects extraction accuracy while penalizing extra effort. Our experiments on two databases--of shooting incidents, and food adulteration cases--demonstrate that our system significantly outperforms traditional extractors and a competitive meta-classifier baseline., Google (Firm) (Google Research Faculty Award)

Published
2016

Catalog

Books, media, physical & digital resources
See catalog results