I am studying the following paper for understanding next-word prediction using n-gram & trie: - http://nlp.cs.berkeley.edu/pubs/Pauls-Klein_2011_LM_paper.pdf Before this, I did some brief study on what are n-grams. And, I know trie data structure. The issue is - the algorithm in paper is not so intuitive to understand. Anyone can provide some better/intuitive explanation of this algorithm, or some similar Language Model Implementation. I am new to this site, so if this question structure is inappropriate to this site, please guide. Thanks in advance.

  • 1
    $\begingroup$ are you trying to build something in particular or just understand the field? it is better to start with what are called "surveys" in the scientific literature [when they are available].... $\endgroup$ – vzn Nov 26 '13 at 19:43
  • $\begingroup$ Thanks vzn. "Surveys" look good to start with. I am now trying to understand the correct way to do a scientific "survey". About my study, right now, I am trying to understand the field. $\endgroup$ – superuser Nov 27 '13 at 10:15

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.