Overview

Reading

Marcus et al. (1993) on building the first large-scale constituency treebank: the Penn Treebank.

How can we search a treebank for a particular configuration? We’ll answer that question from the ground up. First, we’ll build classes for representing trees and treebanks. Then we’ll use those classes to search the annotations rather than only the words.

References

Marcus, Mitchell P., Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. “Building a Large Annotated Corpus of English: The Penn Treebank.” Computational Linguistics (Cambridge, MA) 19 (2): 313–30. https://aclanthology.org/J93-2004.

---
title: Overview
bibliography: ../references.bib
---

::: {.callout-tip}
## Reading

@marcus_building_1993 on building the first large-scale constituency treebank: the [Penn Treebank](https://catalog.ldc.upenn.edu/LDC99T42).
:::

How can we search a treebank for a particular configuration? We'll answer that question from the ground up. First, we'll build classes for representing trees and treebanks. Then we'll use those classes to search the annotations rather than only the words.