introduction to natural language syntax and parsing l95
play

Introduction to Natural Language Syntax and Parsing: L95 Lecture 2 - PowerPoint PPT Presentation

Introduction to Natural Language Syntax and Parsing: L95 Introduction to Natural Language Syntax and Parsing: L95 Lecture 2 Ann Copestake (standing in for Simone Teufel) Department of Computer Science and Technology University of Cambridge


  1. Introduction to Natural Language Syntax and Parsing: L95 Introduction to Natural Language Syntax and Parsing: L95 Lecture 2 Ann Copestake (standing in for Simone Teufel) Department of Computer Science and Technology University of Cambridge October 2019

  2. Introduction to Natural Language Syntax and Parsing: L95 POS tag: N, V, A, Det, P , Num, ? Eliud Kipchoge has become the first athlete to run a marathon in under two hours, beating the mark by 20 seconds. The Kenyan, 34, covered the 26.2 miles (42.2km) in one hour 59 minutes 40 seconds in the Ineos 1:59 Challenge in Vienna, Austria on Saturday.

  3. Introduction to Natural Language Syntax and Parsing: L95 Polysemy Time flies like an arrow. Fruit flies like a banana. Kim gave her dog biscuits. POS tag sequence is often the same for ambiguous sentences: The bank is 200 metres away. I saw a man with a telescope. Note: I saw wood. VBD vs VBP in PTB tagging scheme.

  4. Introduction to Natural Language Syntax and Parsing: L95 Polysemy Time flies like an arrow. Fruit flies like a banana. Kim gave her dog biscuits. POS tag sequence is often the same for ambiguous sentences: The bank is 200 metres away. I saw a man with a telescope. Note: I saw wood. VBD vs VBP in PTB tagging scheme.

  5. Introduction to Natural Language Syntax and Parsing: L95 Polysemy Time flies like an arrow. Fruit flies like a banana. Kim gave her dog biscuits. POS tag sequence is often the same for ambiguous sentences: The bank is 200 metres away. I saw a man with a telescope. Note: I saw wood. VBD vs VBP in PTB tagging scheme.

  6. Introduction to Natural Language Syntax and Parsing: L95 Polysemy Time flies like an arrow. Fruit flies like a banana. Kim gave her dog biscuits. POS tag sequence is often the same for ambiguous sentences: The bank is 200 metres away. I saw a man with a telescope. Note: I saw wood. VBD vs VBP in PTB tagging scheme.

  7. Introduction to Natural Language Syntax and Parsing: L95 Polysemy Time flies like an arrow. Fruit flies like a banana. Kim gave her dog biscuits. POS tag sequence is often the same for ambiguous sentences: The bank is 200 metres away. I saw a man with a telescope. Note: I saw wood. VBD vs VBP in PTB tagging scheme.

  8. Introduction to Natural Language Syntax and Parsing: L95 Idioms Mostly idioms have normal syntax: We have hit a brick wall. The cat is out of the bag. But there are exceptions: They are well off. PTB tagging guidelines say that off is RP (particle), but impossible to give good tags on a word-by-word basis. well off , better off etc behave like adjectives if considered as single units: The better off inhabitants of the village protested against the tax rise.

  9. Introduction to Natural Language Syntax and Parsing: L95 Particle vs preposition The man up the ladder fell. Kim ran up the stairs. Kim ran up a large bill. Kim slipped up. Kim washed up the dishes. Kim washes the dishes up. NB: PTB guidelines say that to is always tagged TO.

  10. Introduction to Natural Language Syntax and Parsing: L95 Particle vs preposition The man up the ladder fell. Kim ran up the stairs. Kim ran up a large bill. Kim slipped up. Kim washed up the dishes. Kim washes the dishes up. NB: PTB guidelines say that to is always tagged TO.

  11. Introduction to Natural Language Syntax and Parsing: L95 Particle vs preposition The man up the ladder fell. Kim ran up the stairs. Kim ran up a large bill. Kim slipped up. Kim washed up the dishes. Kim washes the dishes up. NB: PTB guidelines say that to is always tagged TO.

  12. Introduction to Natural Language Syntax and Parsing: L95 Particle vs preposition The man up the ladder fell. Kim ran up the stairs. Kim ran up a large bill. Kim slipped up. Kim washed up the dishes. Kim washes the dishes up. NB: PTB guidelines say that to is always tagged TO.

  13. Introduction to Natural Language Syntax and Parsing: L95 Particle vs preposition The man up the ladder fell. Kim ran up the stairs. Kim ran up a large bill. Kim slipped up. Kim washed up the dishes. Kim washes the dishes up. NB: PTB guidelines say that to is always tagged TO.

  14. Introduction to Natural Language Syntax and Parsing: L95 Particle vs preposition The man up the ladder fell. Kim ran up the stairs. Kim ran up a large bill. Kim slipped up. Kim washed up the dishes. Kim washes the dishes up. NB: PTB guidelines say that to is always tagged TO.

  15. Introduction to Natural Language Syntax and Parsing: L95 Particle vs preposition The man up the ladder fell. Kim ran up the stairs. Kim ran up a large bill. Kim slipped up. Kim washed up the dishes. Kim washes the dishes up. NB: PTB guidelines say that to is always tagged TO.

  16. Introduction to Natural Language Syntax and Parsing: L95 Tokenization ◮ Usually for English, words are separated by spaces. ◮ Standard PTB tokenization: split off possessive ’s, put spaces round punctuation in general. ◮ But formulae etc: buta-1,3-diene ◮ Need to think about this for the exercises!

  17. Introduction to Natural Language Syntax and Parsing: L95 To do ◮ Read Section 5.1–5.6 in ‘introduction to linguistics’ and attempt exercises 1–3 in section 5.9 (note: this material is dense). ◮ Next lecture is on Thursday ◮ Logic worksheet ◮ Assignment 1: deadline October 21 (remember to write notes on problematic cases).

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend