*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Allie McFadden
Communications Officer
allie.mcfadden@cc.gatech.edu
Summary Sentence: "The Natural Language Decathlon: Multitask Learning as Question Answering"
Full Summary: The Machine Learning Center at Georgia Tech (ML@GT) is excited to welcome Bryan McCann from Salesforce to campus for a ML@GT Talk.
Bryan McCannThe Machine Learning Center at Georgia Tech (ML@GT) is excited to welcome Bryan McCann from Salesforce to campus for a ML@GT Talk.
For scheduling information, contact Mark Riedl at riedl@cc.gatech.edu
Please RSVP by Tuesday, August 27th.
Title
The Natural Language Decathlon: Multitask Learning as Question Answering
Abstract
Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, dataset, and task.
We introduce the Natural Language Decathlon (decaNLP), a challenge that spans ten tasks:
question answering, machine translation, summarization, natural language inference, sentiment analysis, semantic role labeling, zero-shot relation extraction, goal-oriented dialogue, semantic parsing, and commonsense pronoun resolution. We cast all tasks as question answering over a context. Furthermore, we present a new Multitask Question Answering Network (MQAN) jointly learns all tasks in decaNLP without any task-specific modules or parameters in the multitask setting. MQAN shows improvements in transfer learning for machine translation and named entity recognition, domain adaptation for sentiment analysis and natural language inference, and zero-shot capabilities for text classification. We demonstrate that the MQAN's multi-pointer-generator decoder is key to this success and performance further improves with an anti-curriculum training strategy.
Though designed for decaNLP, MQAN also achieves state of the art results on the WikiSQL semantic parsing task in the single-task setting.
We release code for procuring and processing data, training and evaluating models, and reproducing all experiments for decaNLP.
Bio
Bryan McCann is a Senior Research Scientist at Salesforce. He focuses on transfer learning and multitask learning for natural language processing. Most recently, Bryan proposed the Natural Language Decathlon (decaNLP) and a Multitask Question Answering Network to tackle all ten tasks in decaNLP. Before decaNLP, he showed that the intermediate representations, or context vectors (CoVe), of machine translation systems carry information that aids learning in question answering and text classification systems.
Prior to working at Salesforce, Bryan studied at Stanford University, where he completed a B.S and M.S in Computer Science as well as a B.A in Philosophy.
