@article{buckman-neubig-2018-neural,
    title = "Neural Lattice Language Models",
    author = "Buckman, Jacob  and
      Neubig, Graham",
    editor = "Lee, Lillian  and
      Johnson, Mark  and
      Toutanova, Kristina  and
      Roark, Brian",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "6",
    year = "2018",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/Q18-1036/",
    doi = "10.1162/tacl_a_00036",
    pages = "529--541",
    abstract = "In this work, we propose a new language modeling paradigm that has the ability to perform both prediction and moderation of information flow at multiple granularities: neural lattice language models. These models construct a lattice of possible paths through a sentence and marginalize across this lattice to calculate sequence probabilities or optimize parameters. This approach allows us to seamlessly incorporate linguistic intuitions {---} including polysemy and the existence of multiword lexical items {---} into our language model. Experiments on multiple language modeling tasks show that English neural lattice language models that utilize polysemous embeddings are able to improve perplexity by 9.95{\%} relative to a word-level baseline, and that a Chinese model that handles multi-character tokens is able to improve perplexity by 20.94{\%} relative to a character-level baseline."
}