Publications (10)
The TechQA Dataset
Vittorio Castelli, Rishav Chakravarti, Saswati Dana +18
We introduce TechQA, a domain-adaptation question answering dataset for the technical support domain. The TechQA corpus highlights two real-world issues from the automated customer…
SPARTAN: Sparse Hierarchical Memory for Parameter-Efficient Transformers
Ameet Deshpande, Md Arafat Sultan, Anthony Ferritto +3
Fine-tuning pre-trained language models (PLMs) achieves impressive performance on a range of downstream tasks, and their sizes have consequently been getting bigger. Since a differ…
Ensembling Strategies for Answering Natural Questions
Anthony Ferritto, Lin Pan, Rishav Chakravarti +4
Many of the top question answering systems today utilize ensembling to improve their performance on tasks such as the Stanford Question Answering Dataset (SQuAD) and Natural Questi…
CFO: A Framework for Building Production NLP Systems
Rishav Chakravarti, Cezar Pendus, Andrzej Sakrajda +8
This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language…
Frustratingly Easy Natural Question Answering
Lin Pan, Rishav Chakravarti, Anthony Ferritto +5
Existing literature on Question Answering (QA) mostly focuses on algorithmic novelty, data augmentation, or increasingly large pre-trained language models like XLNet and RoBERTa. A…
GAAMA 2.0: An Integrated System that Answers Boolean and Extractive Questions
Scott McCarley, Mihaela Bornea, Sara Rosenthal +4
Recent machine reading comprehension datasets include extractive and boolean questions but current approaches do not offer integrated support for answering both question types. We…