Improving Span-based Question Answering Systems with Coarsely Labeled Data

11/05/2018
by   Hao Cheng, et al.
0

We study approaches to improve fine-grained short answer Question Answering models by integrating coarse-grained data annotated for paragraph-level relevance and show that coarsely annotated data can bring significant performance gains. Experiments demonstrate that the standard multi-task learning approach of sharing representations is not the most effective way to leverage coarse-grained annotations. Instead, we can explicitly model the latent fine-grained short answer variables and optimize the marginal log-likelihood directly or use a newly proposed posterior distillation learning objective. Since these latent-variable methods have explicit access to the relationship between the fine and coarse tasks, they result in significantly larger improvements from coarse supervision.

READ FULL TEXT
research
08/12/2020

Fine-Grained Relevance Annotations for Multi-Task Document Ranking and Question Answering

There are many existing retrieval and question answering datasets. Howev...
research
10/19/2022

MuGER^2: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering

Hybrid question answering (HQA) aims to answer questions over heterogene...
research
09/14/2021

Semantic Answer Type Prediction using BERT: IAI at the ISWC SMART Task 2020

This paper summarizes our participation in the SMART Task of the ISWC 20...
research
03/09/2023

Toward Unsupervised Realistic Visual Question Answering

The problem of realistic VQA (RVQA), where a model has to reject unanswe...
research
08/22/2021

Efficient Algorithms for Learning from Coarse Labels

For many learning problems one may not have access to fine grained label...
research
08/31/2020

Classifier Combination Approach for Question Classification for Bengali Question Answering System

Question classification (QC) is a prime constituent of automated questio...
research
11/03/2022

Exploring explicit coarse-grained structure in artificial neural networks

We propose to employ the hierarchical coarse-grained structure in the ar...

Please sign up or login with your details

Forgot password? Click here to reset