Data-Driven Parametric Text Normalization: Rapidly Scaling Finite-State Transduction Verbalizers to New Languages.
Sandy RitchieEoin MahonKim HeiligensteinNikos BampounisDaan van EschChristian SchallhartJonas Fromseier MortensenBenoît BrardPublished in: SLTU/CCURL@LREC (2020)
Keyphrases
- finite state
- data driven
- finite state transducers
- markov chain
- context free
- markov decision processes
- multi lingual
- model checking
- english text
- text summarization
- arabic language
- text mining
- transition systems
- language independent
- information retrieval
- optimal policy
- web documents
- action sets
- average cost
- partially observable markov decision processes
- vector quantizer
- cross lingual
- edit distance
- text documents
- state space