no code implementations • 16 Dec 2023 • Raviteja Anantha, Bortik Bandyopadhyay, Anirudh Kashi, Sayantan Mahinder, Andrew W Hill, Srinivas Chappidi
Large language models (LLMs) are increasingly employed for complex multi-step planning tasks, where the tool retrieval (TR) step is crucial for achieving successful outcomes.
no code implementations • 9 Dec 2023 • Raviteja Anantha, Tharun Bethi, Danil Vodianik, Srinivas Chappidi
To address this limitation, we propose Context Tuning for RAG, which employs a smart context retrieval system to fetch relevant information that improves both tool retrieval and plan generation.
no code implementations • 1 Mar 2023 • Raviteja Anantha, Kriti Bhasin, Daniela de la Parra Aguilar, Prabal Vashisht, Becci Williamson, Srinivas Chappidi
In this work, we present a highly-precise, PDA-compatible pronunciation learning framework for the task of TTS mispronunciation detection and correction.
no code implementations • dialdoc (ACL) 2022 • Greyson Gerhard-Young, Raviteja Anantha, Srinivas Chappidi, Björn Hoffmeister
Recent work building open-domain chatbots has demonstrated that increasing model size improves performance.
2 code implementations • NAACL 2021 • Raviteja Anantha, Svitlana Vakulenko, Zhucheng Tu, Shayne Longpre, Stephen Pulman, Srinivas Chappidi
We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 80K question-answer pairs.
no code implementations • 4 May 2020 • Raviteja Anantha, Stephen Pulman, Srinivas Chappidi
We present a generic and flexible Reinforcement Learning (RL) based meta-learning framework for the problem of few-shot learning.
no code implementations • 30 Apr 2020 • Raviteja Anantha, Srinivas Chappidi, William Dawoodi
Voice Assistants aim to fulfill user requests by choosing the best intent from multiple options generated by its Automated Speech Recognition and Natural Language Understanding sub-systems.