We present a human-in-the-loop dashboard tailored to diagnosing potentia...
We introduce a novel dependency parser, the hexatagger, that constructs
...
Recently, there has been a growing interest in the development of
gradie...
We show that most structured prediction problems can be solved in linear...
Large language models are able to learn new tasks in context, where they...
There have been many proposals to reduce constituency parsing to tagging...
Probing has become a go-to methodology for interpreting and analyzing de...
Beam search is the default decoding strategy for many sequence generatio...