Skip to content

Commit

Permalink
fix: add bib to codegen sound law induction page
Browse files Browse the repository at this point in the history
  • Loading branch information
kalvinchang authored Sep 11, 2024
1 parent 5eb21f4 commit ac9f4ab
Showing 1 changed file with 3 additions and 2 deletions.
5 changes: 3 additions & 2 deletions _projects/2_codegen.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,9 @@ description: Modeling phonological reconstruction as a code generation problem u
img: assets/img/basel-rathaus-proj.jpg
importance: 2
category: diachronic
related_publications: true
---

Since the Neogrammarians, when linguists write the phonological histories of languages, they essentially write programs (that convert protoforms into reflexes). From a computational perspective, this is an example of coding by example. In this project, we seek to answer the question: can we treat comparative reconstruction as a code-generation problem and solve it with LLMs?
Since the Neogrammarians, when linguists write the phonological histories of languages, they essentially write programs (that convert protoforms into reflexes). From a computational perspective, this is an example of "coding by example." In this project, we seek to answer the question: can we treat comparative reconstruction as a code-generation problem and solve it with LLMs?

We have made initial progress on this front, experimenting both with data sets where only one rule (sound law) was involved and sets with multiple sound laws {% cite naik2024largelanguagemodelscode %}. In the next year, we hope to extend this work to naturalistic data sets.
We have made initial progress on this front, experimenting both with data sets where only one rule (sound law) was involved and sets with multiple sound laws {% cite naik2024largelanguagemodelscode %}. In the next year, we hope to extend this work to naturalistic data sets.

0 comments on commit ac9f4ab

Please sign in to comment.