Grouping Language Model Boundary Words to Speed K-Best Extraction from Hypergraphs

@inproceedings{Heafield2013GroupingLM,
  title={Grouping Language Model Boundary Words to Speed K-Best Extraction from Hypergraphs},
  author={Kenneth Heafield and Philipp Koehn and Alon Lavie},
  booktitle={HLT-NAACL},
  year={2013}
}
We propose a new algorithm to approximately extract top-scoring hypotheses from a hypergraph when the score includes an N–gram language model. In the popular cube pruning algorithm, every hypothesis is annotated with boundary words and permitted to recombine only if all boundary words are equal. However, many hypotheses share some, but not all, boundary words. We use these common boundary words to group hypotheses and do so recursively, resulting in a tree of hypotheses. This tree forms the… CONTINUE READING
Highly Cited
This paper has 26 citations. REVIEW CITATIONS