Papers by Nithya Govindarajan

GenGO

Omakase Read Later

Search

Papers by Nithya Govindarajan

ACL

P19-3

Microsoft Icecaps
Intelligent Conversation Engine
Pre-trained Systems
modular component-based architecture
upgraded language model decoding features
multitask learning
conversational tasks
response generation
knowledge grounding
fine-tuning

2019

Dialogue Systems & Conversational Agents

1 papers

Microsoft Icecaps: An Open-Source Toolkit for Conversation Modeling (P19-3)

Copied to clipboard

Vighnesh Leonardo Shiv, Chris Quirk, Anshuman Suri, Xiang Gao, Khuram Shahid, Nithya Govindarajan, Yizhe Zhang, Jianfeng Gao, Michel Galley, Chris Brockett, Tulasi Menon, Bill Dolan

Dialogue Systems & Conversational Agents

Challenge:	upcoming open-source natural language processing repository aims to train conversational agents for multi-turn situations.
Approach:	They present the Intelligent Conversation Engine: Code and Pre-trained Systems (ICECAPS) the framework wraps TensorFlow functionality in a modular component-based architecture.
Outcome:	The Intelligent Conversation Engine: Code and Pre-trained Systems (ICECAPS) is an open-source natural language processing repository.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations