Structured Complex Task Decomposition (SCTD) is the problem of breaking ...
Automated reasoning with unstructured natural text is a key requirement ...
Standard empirical risk minimization (ERM) training can produce deep neu...
Language models (LMs) pretrained on large corpora of text from the web h...
Remarkable progress has been made on automated reasoning with knowledge
...
Representative selection (RS) is the problem of finding a small subset o...
Interactive recommender systems (RSs) allow users to express intent,
pre...
Many Question-Answering (QA) datasets contain unanswerable questions, bu...
Pretrained Language Models (LMs) have been shown to possess significant
...
Most current NLP systems have little knowledge about quantitative attrib...