jurafsky&martin_3rdEd_17 (1).pdf

Sequences of question terms the length of the longest

Info icon This preview shows pages 408–409. Sign up to view the full content.

View Full Document Right Arrow Icon
Sequences of question terms: The length of the longest sequence of question terms that occurs in the candidate answer. An alternative approach to answer extraction, used solely in Web search, is based on N-gram tiling , sometimes called the redundancy-based approach ( Brill N-gram tiling et al. 2002 , Lin 2007 ). This simplified method begins with the snippets returned from the Web search engine, produced by a reformulated query. In the first step, N-gram mining , every unigram, bigram, and trigram occurring in the snippet is ex- N-gram mining tracted and weighted. The weight is a function of the number of snippets in which the N -gram occurred, and the weight of the query reformulation pattern that re- turned it. In the N-gram filtering step, N -grams are scored by how well they match N-gram filtering the predicted answer type. These scores are computed by hand-written filters built for each answer type. Finally, an N-gram tiling algorithm concatenates overlapping N -gram fragments into longer answers. A standard greedy method is to start with the highest-scoring candidate and try to tile each other candidate with this candidate. The best-scoring concatenation is added to the set of candidates, the lower-scoring candidate is removed, and the process continues until a single answer is built. For any of these answer-extraction methods, the exact answer phrase can just be presented to the user by itself, or, more helpfully, accompanied by enough passage information to provide helpful context. 27.2 Knowledge-based Question Answering While an enormous amount of information is encoded in the vast amount of text on the web, information obviously also exists in more structured forms. We use the term knowledge-based question answering for the idea of answering a natural language question by mapping it to a query over a structured database. Like the text- based paradigm for question answering, this approach dates back to the earliest days of natural language processing, with systems like BASEBALL (Green et al., 1961) that answered questions from a structured database of baseball games and stats. Systems for mapping from a text string to any logical form are called semantic parsers (???). Semantic parsers for question answering usually map either to some version of predicate calculus or a query language like SQL or SPARQL, as in the examples in Fig. 27.7 . Question Logical form When was Ada Lovelace born? birth-year (Ada Lovelace, ?x) What states border Texas? l x.state(x) ^ borders(x,texas) What is the largest state argmax( l x . state ( x ) , l x . size ( x ) ) How many people survived the sinking of the Titanic (count (!fb:event.disaster.survivors fb:en.sinking of the titanic)) Figure 27.7 Sample logical forms produced by a semantic parser for question answering. These range from simple relations like birth-year , or relations normalized to databases like Freebase, to full predicate calculus.
Image of page 408

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 409
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern