Corpus Linguistics Working Group

Spring 2021

University of Oregon, Linguistics Department

Spring 2021 Schedule

• Week 1: Getting Organized
• Week 2: Introduction to Part of Speech (POS) Tagging
  • Overview of how POS tagging works
  • Begin building a basic POS tagger
  • Access POS Tagging Tutorial 1 here
  • Note, if you need to brush up on your Python skills, check out this tutorial
• Weeks 3,4: Introduction to POS Tagging (pt. 2)
  • Building better feature sets
  • Building simple tagging algorithms
  • Access POS Tagging Tutorial 2 here
• Week 5: Introduction to POS Tagging (pt. 3)
  • Looking at accuracy (precision and recall)
  • Access POS Tagging Tutorial 3 here
• Week 6: POS Tagging with Machine Learning
  • Apply machine learning algorithms, Part 1: Decision Trees
• Week 7 (Kris, TBD): POS Tagging with Machine Learning (part 2)
  • Apply machine learning algorithms, Part 2: Random Forests and Maximum Entropy
• Week 8 (Kris, TBD): State of the Art POS Tagging with (simple) Neural Nets
  • Apply a Simple Neural Net
• Week 9 (Kris): Dealing with Languages other than English
  • Working .conllu datasets
• Week 10 (TBD): TBD

Winter 2021 Schedule

• Week 1 (Kris): Getting Organized
  • Homework:
  • Sign up for a Github account
  • Create a sample repository
  • Take a look at the markdown guidelines (I promise, it is super easy)
• Week 2 (Wesley): Prospects for a (Semi-)Automated Papuan Comparative Linguistics and Reconstruction (Hammarström, 2019)
• Week 3 (Masaki): A corpus-driven approach to formulaic language in English Multi-word patterns in speech and writing (Biber, 2009). Note, skim this article for background; Workshop will be extracting formulaic language beyond n-grams.
• Week 4 (Keegan): Galves et al. 2017: Annotating a Polysynthetic Language
• Week 5 (Cece): Corpora, Databases, and Internet Resources: Corpus Phonology with Speech Resources Using The Internet For Collecting Phonological Data Speech Manipulation, Synthesis, and Automatic Recognition in Laboratory Phonology Phonotactic Patterns in Lexical Corpora
• Week 6 (Shayleen): Corpus linguistics and language documentation: challenges for collaboration (Cox, 2011)
• Week 7 (Brittany): Annotating the ICE corpora pragmatically – preliminary issues & steps (Weisser, 2017)
• Week 8 (Ksenia): Distributional Semantics article (Boleda, 2019) + word2vec coding in class
• Week 9 (Min): Min will be leading us through a collexeme analysis. For more about collexeme analysis check out [Gries et al., 2005 - focus on study 2](https://github.com/kristopherkyle/Corpus-Linguistics-Working-Group/raw/main/docs/Gries Hampe Shonfeld 2005.pdf) and/or Hilpert, 2006 - shorter paper
• Week 10 (Sabine): Sabine will be discussing the calculation of syntactic complexity (and in particular, the use of TAASSC). Sabine will be referencing this article: Kyle & Crossley (2018)

Small Project for Weeks 7-10: Part of Speech (POS) Tagging

• Week 7 - Introduction to POS Tagging
• Week 8 - POS tagging: More features, more precise accuracy figures
• Week 9 - Applying machine learning algorithms to POS tagging

Resources (readings, code, etc.)

• Markdown Cheatsheet
• GitHub Pages Information
• More to be added as the term progresses