probml / probml/dynamax

add support for normalizing flow emission model for HMM

Open
#274 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

help wanted
Dominant language
Python
Stars
1k
Forks
114
Avg merge
19h 14m
Merged PRs (30d)
1

Description

Then try to replicate this cool application, where they did unsupervised POS discovery from penn treebank text corpus, using fixed word embeddings as the observaiton sequence.

J. He, G. Neubig, and T. Berg-Kirkpatrick, “Unsupervised Learning of Syntactic Structure with Invertible Neural Projections,” in EMNLP, 2018 [Online]. Available: http://arxiv.org/abs/1808.09111

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the cited EMNLP 2018 paper and the existing HMM emission-model interfaces. The issue names no files or tests; done would mean supporting a normalizing-flow emission model and reproducing the paper's unsupervised POS discovery experiment on Penn Treebank text with fixed word embeddings.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.