Reducing Sequence Length by Predicting Edit Operations with Large Language Models.
Masahiro KanekoNaoaki OkazakiPublished in: CoRR (2023)
Keyphrases
- edit operations
- language model
- edit distance
- finite alphabet
- language modeling
- approximate matching
- minimum cost
- document retrieval
- information retrieval
- retrieval model
- minimal cost
- n gram
- probabilistic model
- query expansion
- tree edit distance
- normalized edit distance
- test collection
- relevance model
- smoothing methods
- language models for information retrieval
- context sensitive
- graph matching
- string matching
- vector space model
- tree structured data
- approximate string matching
- similarity measure
- distance function
- subgraph isomorphism
- record linkage
- approximation algorithms
- distance measure