id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_fkn6grwf7be5hmmu5cqetl6dzm	Aaron Jaech	Low-Rank RNN Adaptation for Context-Aware Language Modeling	2018	122	.pdf	application/pdf	31085	3142	67	In our experiments on several different datasets and multiple types of context, the increased adaptation of the recurrent layer is always helpful, as measured by perplexity, the 6.3 Context-specificity of hotel class versus FactorCell rank and perplexity in generated reviews using the models learned on the TripAdvisor data. If statistical language models can be made to mimic this contextual adaptability, then they will be useful in a wider range of applications, including speech recognition, domains, contexts, and model and vocabulary sizes confirms that adapting the recurrent layer Chapter 6 deals with the use of language model adaptation for context-specific text adaptation method, model fine-tuning, does not require the use of a context embedding. For neural language model adaptation, context information is typically represented as an Low-rank RNN adaptation for context-aware language modeling. Low-rank RNN adaptation for context-aware language modeling. Low-rank RNN adaptation for context-aware language modeling.	./cache/work_fkn6grwf7be5hmmu5cqetl6dzm.pdf	./txt/work_fkn6grwf7be5hmmu5cqetl6dzm.txt