Topic change and local perplexity in spoken legal dialogue
2002Vol. 2, pp. 721–724
Abstract
The notion of local perplexity of a corpus (over a range of language models) is examined. The local behaviour of perplexity (over several court transcripts) is also examined to determine if there is there any correspondence between local variations in perplexity and some event in the dialogue, such as topic change.
Related Papers
- Combination of Recurrent Neural Networks and Factored Language Models for Code-Switching Language Modeling(2013)
- → Improved topic-dependent language modeling using information retrieval techniques(1999)55 cited
- → Verifying the long-range dependency of RNN language models(2016)2 cited
- → Attention-based Persian Language Modeling(2022)
- → Building Personalized Language Models Through Language Model Interpolation(2023)