An Automated Question-Answering Framework Based on Evolution Algorithm

01/26/2022
by   Sinan Tan, et al.
0

Building a deep learning model for a Question-Answering (QA) task requires a lot of human effort, it may need several months to carefully tune various model architectures and find a best one. It's even harder to find different excellent models for multiple datasets. Recent works show that the best model structure is related to the dataset used, and one single model cannot adapt to all tasks. In this paper, we propose an automated Question-Answering framework, which could automatically adjust network architecture for multiple datasets. Our framework is based on an innovative evolution algorithm, which is stable and suitable for multiple dataset scenario. The evolution algorithm for search combine prior knowledge into initial population and use a performance estimator to avoid inefficient mutation by predicting the performance of candidate model architecture. The prior knowledge used in initial population could improve the final result of the evolution algorithm. The performance estimator could quickly filter out models with bad performance in population as the number of trials increases, to speed up the convergence. Our framework achieves 78.9 EM and 86.1 F1 on SQuAD 1.1, 69.9 EM and 72.5 F1 on SQuAD 2.0. On NewsQA dataset, the found model achieves 47.0 EM and 62.9 F1.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/30/2019

Ensembling Strategies for Answering Natural Questions

Many of the top question answering systems today utilize ensembling to i...
research
01/01/2021

Reader-Guided Passage Reranking for Open-Domain Question Answering

Current open-domain question answering (QA) systems often follow a Retri...
research
09/24/2019

Technical report on Conversational Question Answering

Conversational Question Answering is a challenging task since it require...
research
10/29/2020

Less is More: Data-Efficient Complex Question Answering over Knowledge Bases

Question answering is an effective method for obtaining information from...
research
12/14/2021

Few-shot Multi-hop Question Answering over Knowledge Base

Previous work on Chinese Knowledge Base Question Answering has been rest...
research
10/04/2020

When in Doubt, Ask: Generating Answerable and Unanswerable Questions, Unsupervised

Question Answering (QA) is key for making possible a robust communicatio...

Please sign up or login with your details

Forgot password? Click here to reset