Unsupervised Learning of Morphological Forests

Jiaming Luo, Karthik Narasimhan, Regina Barzilay


Abstract
This paper focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary. This formulation enables us to capture edge-wise properties reflecting single-step morphological derivations, along with global distributional properties of the entire forest. These global properties constrain the size of the affix set and encourage formation of tight morphological families. The resulting objective is solved using Integer Linear Programming (ILP) paired with contrastive estimation. We train the model by alternating between optimizing the local log-linear model and the global ILP objective. We evaluate our system on three tasks: root detection, clustering of morphological families, and segmentation. Our experiments demonstrate that our model yields consistent gains in all three tasks compared with the best published results.
Anthology ID:
Q17-1025
Volume:
Transactions of the Association for Computational Linguistics, Volume 5
Month:
Year:
2017
Address:
Cambridge, MA
Editors:
Lillian Lee, Mark Johnson, Kristina Toutanova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
353–364
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/Q17-1025/
DOI:
10.1162/tacl_a_00066
Bibkey:
Cite (ACL):
Jiaming Luo, Karthik Narasimhan, and Regina Barzilay. 2017. Unsupervised Learning of Morphological Forests. Transactions of the Association for Computational Linguistics, 5:353–364.
Cite (Informal):
Unsupervised Learning of Morphological Forests (Luo et al., TACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/Q17-1025.pdf
Video:
 https://preview.aclanthology.org/build-pipeline-with-new-library/Q17-1025.mp4