Despite their impressive performance on diverse tasks, large language mo...
We introduce RoMQA, the first benchmark for robust, multi-evidence,
mult...
We present M2D2, a fine-grained, massively multi-domain corpus for study...
Recent work has shown that augmenting environments with language descrip...
Reinforcement learning (RL) agents are particularly hard to train when
r...
Existing work in language grounding typically study single environments....
Many types of text style transfer can be achieved with only small, preci...
We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing...
Obtaining policies that can generalise to new environments in reinforcem...
Conversational machine reading systems help users answer high-level ques...
Multi-hop Reading Comprehension (RC) requires reasoning and aggregation
...
End-to-end neural models have made significant progress in question
answ...
Neural models for question answering (QA) over documents have achieved
s...
Dialogue state tracking, which estimates user goals and requests given t...
Traditional models for question answering optimize using cross entropy l...
A significant amount of the world's knowledge is stored in relational
da...
Several deep learning models have been proposed for question answering.
...
Most tasks in natural language processing can be cast into question answ...