1 / 11

Semantic Entailment

Semantic Entailment. Nathaniel Story Ginger Buckbee Greg Lorge Billy Dean . What is it?. Given sentence A, can you infer sentence B?. Challenges. Paraphrasing Negation Pre-Suppositions World Knowledge Juiciness . Paraphrasing Example. “There is a cat on the table.”

pegeen
Télécharger la présentation

Semantic Entailment

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. Semantic Entailment Nathaniel Story Ginger Buckbee Greg Lorge Billy Dean

  2. What is it? Given sentence A, can you infer sentence B?

  3. Challenges • Paraphrasing • Negation • Pre-Suppositions • World Knowledge • Juiciness

  4. Paraphrasing Example • “There is a cat on the table.” • “A cat is on the table.” • Different structurally, but infers same meaning

  5. Negation • “I am lazy” • “I am not lazy” • “I’m not unhappy” (Double negation) • “I’m happy” • “It’s not unnecessary” • “It’s necessary”

  6. Pre-Suppositions • “Bob doesn’t think it’s raining” • “Bob doesn’t know it’s raining” • Conversational Pragmatics • Contextual knowledge

  7. World Knowledge • “Japan is the only country that currently has an emperor.” • “Columbia doesn’t have an emperor.” • First sentence entails second, but you need to know that Columbia is a country.

  8. Approach • Tools: • Stemmer • Parser from Dan Bikel’s site • MALLET (maxEnt classifier) • Wordnet (synset) • Focusing on Comparable Document task • Start with simple features like word matching, synonym matching • Add in more complicated functions like phrase structure comparisons • Test the system out, see how it works. Continue adding features to improve performance.

  9. Data • Recognizing Textual Entailment Challenge (RTE) training data set • Training set is labeled • Best data set as was used in the European Competition

  10. Evaluation • International Competition • Best ≈ 60% accuracy • Strive for >52% accuracy • Comparing against annotated test set • Improvement: Print out incorrect ones, then look for mistakes.

  11. The End Questions?

More Related