id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_pomvj2ifwrbwjdcmiw5ube5dge	Felix Hill	Learning to Understand Phrases by Embedding the Dictionary	2016	14	.pdf	application/pdf	8620	774	54	Neural language embedding models can be effectively trained to map dictionary definitions (phrases) to (lexical) representations of the words defined by those definitions. On both tasks, neural language embedding models trained on definitions from a handful of freely-available lexical resources perform as well or better than The results highlight the effectiveness of both neural embedding architectures and definitionbased training for developing models that understand phrases and sentences. on only a handful of dictionaries identifies novel definitions and concept descriptions comparably or better than commercial systems, which rely on significant task-specific engineering and access to much input definition phrase sc defining word c to a location close to the the pre-trained embedding vc of To compile a bank of dictionary definitions for training the model, we started with all words in the target embedding space. As with the reverse dictionary experiments, candidates are extracted from models by inputting definitions and returning words corresponding to the	./cache/work_pomvj2ifwrbwjdcmiw5ube5dge.pdf	./txt/work_pomvj2ifwrbwjdcmiw5ube5dge.txt