Semantics of a sentence is defined with much less ambiguity than semanti...
We propose a new kind of embedding for natural language text that deeply...
Transformer language models provide superior accuracy over previous mode...
We propose a simple and practical method of named entity linking (NEL), ...
Factual consistency is one of important summary evaluation dimensions,
e...
We present Namesakes, a dataset of ambiguously named entities obtained f...
The creation of a large summarization quality dataset is a considerable,...
Evaluating large summarization corpora using humans has proven to be
exp...
We propose a new reference-free summary quality evaluation measure, with...
The goal of a summary is to concisely state the most important informati...
Normally, summary quality measures are compared with quality scores prod...
The prevalence of ambiguous acronyms make scientific documents harder to...
We explore the sensitivity of a document summary quality estimator, BLAN...
We present an approach to generating topics using a model trained only f...
We present BLANC, a new approach to the automatic estimation of document...
We propose a novel method for generating titles for unstructured text
do...
We propose a novel method for generating titles for unstructured text
do...