Following procedural texts written in natural languages is challenging. ...
In this work, we propose Masked Noun-Phrase Prediction (MNPP), a pre-tra...
Decompilation is the procedure of transforming binary programs into a
hi...
Recent work on unsupervised question answering has shown that models can...
A recent work has shown that transformers are able to "reason" with fact...
Methodologies for training VQA models assume the availability of dataset...
While progress has been made on the visual question answering leaderboar...
The aim of all Question Answering (QA) systems is to be able to generali...
Open Domain Question Answering requires systems to retrieve external
kno...
Captioning is a crucial and challenging task for video understanding. In...
Question answering (QA) in natural language (NL) has been an important a...
Logical connectives and their implications on the meaning of a natural
l...
In this work, we try to perform Named Entity Recognition (NER) with exte...
In this work we describe the system from Natural Language Processing gro...
DARPA and Allen AI have proposed a collection of datasets to encourage
r...
Open book question answering is a type of natural language based QA (NLQ...