What BERT Based Language Model Learns in Spoken Transcripts: An Empirical Study.
Ayush KumarMukuntha Narayanan SundararamanJithendra VepaPublished in: BlackboxNLP@EMNLP (2021)
Keyphrases
- language model
- speech recognition
- automatic speech recognition
- word clouds
- spoken documents
- word error rate
- language modeling
- broadcast news
- document retrieval
- n gram
- information retrieval
- test collection
- retrieval model
- language modelling
- speech signal
- context sensitive
- spoken document retrieval
- probabilistic model
- query expansion
- statistical language models
- speech transcripts
- language model for information retrieval
- vector space model
- mixture model
- pseudo relevance feedback
- handwriting recognition
- document ranking
- retrieval effectiveness
- relevance model
- translation model
- statistical machine translation
- query terms
- pseudo feedback
- text categorization
- information retrieval systems
- ad hoc information retrieval
- hidden markov models
- feature selection