AI/ML

Relation Module for Non-answerable Prediction on Question Answering. (arXiv:1910.10843v1 [cs.CL])

Machine reading comprehension(MRC) has attracted significant amounts of
research attention recently, due to an increase of challenging reading
comprehension datasets. In this paper, we aim to improve a MRC model’s ability
to determine whether a question has an answer in a given context (e.g. the
recently proposed SQuAD 2.0 task). Our solution is a relation module that is
adaptable to any MRC model. The relation module consists of both semantic
extraction and relational information. We first extract high level semantics as
objects from both question and context with multi-head self-attentive pooling.
These semantic objects are then passed to a relation network, which generates
relationship scores for each object pair in a sentence. These scores are used
to determine whether a question is non-answerable. We test the relation module
on the SQuAD 2.0 dataset using both BiDAF and BERT models as baseline readers.
We obtain 1.8% gain of F1 on top of the BiDAF reader, and 1.0% on top of the
BERT base model. These results show the effectiveness of our relation module on
MRC

Source link




Related posts

Complex-valued unsupervised convolutional neural networks for sleep stage classification.

Newsemia

Aberrant intra and inter network resting state functional connectivity in thyrotoxicosis.

Newsemia

Thousands of AI researches agree to never build lethal autonomous weapons…

Newsemia

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More

Privacy & Cookies Policy