Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering

07/21/2016
by   Peng Li, et al.
0

While question answering (QA) with neural network, i.e. neural QA, has achieved promising results in recent years, lacking of large scale real-word QA dataset is still a challenge for developing and evaluating neural QA system. To alleviate this problem, we propose a large scale human annotated real-world QA dataset WebQA with more than 42k questions and 556k evidences. As existing neural QA methods resolve QA either as sequence generation or classification/ranking problem, they face challenges of expensive softmax computation, unseen answers handling or separate candidate answer generation component. In this work, we cast neural QA as a sequence labeling problem and propose an end-to-end sequence labeling model, which overcomes all the above challenges. Experimental results on WebQA show that our model outperforms the baselines significantly with an F1 score of 74.69 the performance drops only 3.72 F1 points with more challenging character-based input.

READ FULL TEXT
research
01/16/2021

Transformer-Based Models for Question Answering on COVID19

In response to the Kaggle's COVID-19 Open Research Dataset (CORD-19) cha...
research
01/05/2021

End-to-End Video Question-Answer Generation with Generator-Pretester Network

We study a novel task, Video Question-Answer Generation (VQAG), for chal...
research
05/21/2023

Evaluating Open Question Answering Evaluation

This study focuses on the evaluation of Open Question Answering (Open-QA...
research
03/06/2020

Practical Annotation Strategies for Question Answering Datasets

Annotating datasets for question answering (QA) tasks is very costly, as...
research
08/03/2023

RealCQA: Scientific Chart Question Answering as a Test-bed for First-Order Logic

We present a comprehensive study of chart visual question-answering(QA) ...
research
04/21/2018

Generative Stock Question Answering

We study the problem of stock related question answering (StockQA): auto...
research
09/08/2017

Globally Normalized Reader

Rapid progress has been made towards question answering (QA) systems tha...

Please sign up or login with your details

Forgot password? Click here to reset