no code implementations • 21 Jul 2022 • Prabhat Agarwal, Manisha Srivastava, Vishwakarma Singh, Charles Rosenberg
Users' complex behavior can be well represented by a heterogeneous graph rich with node and edge attributes.
no code implementations • NAACL 2021 • Manisha Srivastava, Yichao Lu, Riley Peschon, Chenyang Li
In this work, we present a method for training retrieval-based dialogue systems using a small amount of high-quality, annotated data and a larger, unlabeled dataset.
no code implementations • NAACL 2019 • Yichao Lu, Manisha Srivastava, Jared Kramer, Heba Elfardy, Andrea Kahn, Song Wang, Vikas Bhardwaj
To test our models, a customer service agent handles live contacts and at each turn we present the top four model responses and allow the agent to select (and optionally edit) one of the suggestions or to type their own.
no code implementations • IJCNLP 2017 • Heba Elfardy, Manisha Srivastava, Wei Xiao, Jared Kramer, Tarun Agarwal
The ability to automatically and accurately process customer feedback is a necessity in the private sector.
no code implementations • 10 Jul 2014 • Ramasubramanian Sundararajan, Hima Patel, Manisha Srivastava
This document describes a novel learning algorithm that classifies "bags" of instances rather than individual instances.