A software for inferring morphological rules from linguistically annotated data
Project description
README
What is this repository for?
- This repo hosts a version of MOM sofware, originally developed by David Wax in 2014.
- It was later significantly changed by Olga Zamaraeva.
- It is part of the AGGREGATION project
- The software helps infer morphological position classes (slots) from interlinearized data.
What to cite if I use MOM for my research?
- Wax, David Allen. Automated grammar engineering for verbal morphology. Diss. 2014.
- Zamaraeva, Olga. Inferring Morphotactics from Interlinear Glossed Text: Combining Clustering and Precision Grammars. SIGMORPHON 2016 (2016): 141.
How do I get set up?
-
Please see the Wiki. Most of the info is there, some may be outdated.
-
There are dependencies; you should be able to easily install them by pip, but you may need to manually install Graphviz.
-
You will need a config file. Please see a sample eng_config under config_files, ass well as documented_config for comments.
-
You will need some files, particularly files containing what the program will treat as gloss grams and POS tags. See mom/util/collect_tags_xigt.py
-
For morphosyntactic features, the program relies on FeatDict.py. mom/util/collect_tags_xigt.py will report if it finds grams that are not yet mapped to anything in FeatDict.py. Please enter them there manually, all lowercased, to whichever dictionary you think they should belong.
Who do I talk to?
- Please contact Emily M. Bender about the AGGREGATION project and ask who is currently working on MOM.
- You can also contact olga.zamaraeva@ (geeeeemail), who may or may not be able to help you at this point (she will try).
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file matrix-odin-morphology-0.0.1.tar.gz
.
File metadata
- Download URL: matrix-odin-morphology-0.0.1.tar.gz
- Upload date:
- Size: 48.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/4.6.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.61.2 CPython/3.9.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7f8efd476431047b8241c588767804ef89cebd95d2f9458bc3cf075e6741f361 |
|
MD5 | 941860bce288a0babb654d3d91a7db08 |
|
BLAKE2b-256 | 321563443b7b0921cbce4174eb525ef9d4712d925ece9591db8bca9a4ae64d6b |
File details
Details for the file matrix_odin_morphology-0.0.1-py3-none-any.whl
.
File metadata
- Download URL: matrix_odin_morphology-0.0.1-py3-none-any.whl
- Upload date:
- Size: 48.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/4.6.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.61.2 CPython/3.9.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | f81643ec6df2c2705407b383953113c020ef56d4057ca00ed3e36ef432dd112d |
|
MD5 | 33b84c64c713f2bcb6636ceef4866c4a |
|
BLAKE2b-256 | 5d8389103199ba5036f8ea3ea7645e0e7ed26fc5c5c3ff6646bb4d5b700c3abe |