Charles Elkan


2018

pdf bib
What we need to learn if we want to do and not just talk
Rashmi Gangadharaiah | Balakrishnan Narayanaswamy | Charles Elkan
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)

In task-oriented dialog, agents need to generate both fluent natural language responses and correct external actions like database queries and updates. Our paper makes the first attempt at evaluating state of the art models on a large real world task with human users. We show that methods that achieve state of the art performance on synthetic datasets, perform poorly in real world dialog tasks. We propose a hybrid model, where nearest neighbor is used to generate fluent responses and Seq2Seq type models ensure dialogue coherency and generate accurate external actions. The hybrid model on the customer support data achieves a 78% relative improvement in fluency, and a 200% improvement in accuracy of external calls.

2014

pdf bib
Learning to Re-rank for Interactive Problem Resolution and Query Refinement
Rashmi Gangadharaiah | Balakrishnan Narayanaswamy | Charles Elkan
Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)

2010

pdf bib
Conditional Random Fields for Word Hyphenation
Nikolaos Trogkanis | Charles Elkan
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics