1 / 9

Natural Language Processing for the Web

Natural Language Processing for the Web. Prof. Kathleen McKeown 722 CEPSR, 939-7118 Office Hours: Wed, 1-2; Tues 4-5 TA: Yves Petinot 719 CEPSR, 939-7116 Office Hours: Thurs 12-1, 8-9. Today.

hamlet
Télécharger la présentation

Natural Language Processing for the Web

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Natural Language Processing for the Web Prof. Kathleen McKeown 722 CEPSR, 939-7118 Office Hours: Wed, 1-2; Tues 4-5 TA: Yves Petinot 719 CEPSR, 939-7116 Office Hours: Thurs 12-1, 8-9

  2. Today • Next week: Invited Speaker SandaHarabagiu, Need 2 Discussants, location 414 CEPSR. This is not a class to miss! • Open Domain Question Answering (Lauren) • Natural language based reformulation resource and web exploitation for question answering (Kathy) • Improving QA Accuracy by Question Inversion (Vikas) • A Classification Approach to QA in Discussion Boards (Kenny) • Discussants: William, Shrenik

  3. When QA is difficult • When the answer string does not use the same words as the question string: • Who discovered America? • Columbus discovered America • Columbus Day celebrates the Italian Navigator who first landed in the New World on Oct. 12, 1942.

  4. Proposed Solution • Paraphrase Templates • How did Mahatma Gandhi die? • Mahatma Gandhi died <how> • Mahatma Gandhi died of <what> • Mahatma Gandhi died from <what> • Mahatma Gandhi’s death from <what> • Mahatma Gandhi drowned • Mahatma Gandhi suffocated • Mahatma Gandhi froze to death • <who> killed Mahatma Gandhi • <who> assassinated Mahatma Gandhi • Mahatma Gandhi was killed

  5. Use • In IR to find documents more likely to contain answer • To rank sentences within documents that are returned by IR

  6. Reformulations • Hand-built or manual generalizations of automatically produced paraphrases • Specify type of relation to original • Number of reformulations: 1-30, ave: 3.24

  7. Other Reformulation Types • Lexical: • Buy/sell: John sold the laptop to Mary = Mary bought the laptop from John • Syntactic: • How deep is Crater Lake? • Crater Lake has a depth of <what distance> • Inference • Reformulation Chains • Where did Bill Gates go to college? • Bill Gates was a student at <which college>? • Bill Gates dropped out of <which college>? • Bill Gates was a <which college> dropout? • Text: Bill Gates was a Harvard dropout.

  8. But…. Their Web IR System • Preserve quoted terms and quote the smallest NPs: • “What is the longest river in the United States?” -> “longest river” and “United States” • Expand the query using Wordnet Synonyms • “What is the length of the border between Ukraine and Russia?” -> (“length” or “distance”) and (“border” or “surround”) and (“Ukraine” or “Ukrainia”) and (“Russia” or “Soviet Union”) and (“between” or “betwixt”) • Using Contexrefomulations, add quoted reformulations of the question’s declarative form • “What is an atom?” -> “is an atom”, “an atom is” “an atom is one of”

  9. Evaluation

More Related