We present Vārta, a large-scale multilingual dataset for headline
genera...
In this work, we introduce IndicXTREME, a benchmark consisting of nine
d...
Semantic parsing allows humans to leverage vast knowledge resources thro...
This work introduces Itihasa, a large-scale translation dataset containi...
Model-agnostic meta-learning (MAML) has been recently put forth as a str...
Professional summaries are written with document-level information, such...
Coreference resolution and semantic role labeling are NLP tasks that cap...
Image captioning models are usually evaluated on their ability to descri...
Unresolved coreference is a bottleneck for relation extraction, and
high...
Coreference and many forms of ellipsis are similar to reading comprehens...
Although the vast majority of knowledge bases KBs are heavily biased tow...
Although the vast majority of knowledge bases KBs are heavily biased tow...
Humans do not make inferences over texts, but over models of what texts ...
Deep learning is one of the fastest growing technologies in computer sci...
Fooling deep neural networks with adversarial input have exposed a
signi...
We propose DuoRC, a novel dataset for Reading Comprehension (RC) that
mo...
For a given software bug report, identifying an appropriate developer wh...
Question answering is one of the primary challenges of natural language
...
Mobile app distribution platforms such as Google Play Store allow users ...
Cross-modal data retrieval has been the basis of various creative tasks
...
Traditional software engineering programming paradigms are mostly object...
Since the advent of computers, many tasks which required humans to spend...