Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Making Neural QA as Simple as Possible but not Simpler

About

Recent development of large-scale question answering (QA) datasets triggered a substantial amount of research into end-to-end neural architectures for QA. Increasingly complex systems have been conceived without comparison to simpler neural baseline systems that would justify their complexity. In this work, we propose a simple heuristic that guides the development of neural baseline systems for the extractive QA task. We find that there are two ingredients necessary for building a high-performing neural QA system: first, the awareness of question words while processing the context and second, a composition function that goes beyond simple bag-of-words modeling, such as recurrent neural networks. Our results show that FastQA, a system that meets these two requirements, can achieve very competitive performance compared with existing models. We argue that this surprising finding puts results of previous systems and the complexity of recent QA datasets into perspective.

Dirk Weissenborn, Georg Wiese, Laura Seiffe• 2017

Related benchmarks

TaskDatasetResultRank
Question AnsweringSQuAD v1.1 (dev)
F1 Score78.5
375
Question AnsweringSQuAD v1.1 (test)
F1 Score78.9
260
Question AnsweringNewsQA (dev)
F1 Score56.4
101
Question AnsweringSQuAD (dev)
F178.5
74
Question AnsweringNewsQA (test)
F156.1
31
Generative Question AnsweringMsMARCO (test)
ROUGE Score33.7
18
Generative Question AnsweringMsMARCO (dev)
ROUGE Score34.4
11
Machine Reading ComprehensionMS-MARCO (test)
ROUGE-L33.67
9
Showing 8 of 8 rows

Other info

Follow for update