Papers by Sujay Khandagale
Towards Unsupervised Morphological Analysis of Polysynthetic Languages (2022.aacl-short)
Copied to clipboard
Sujay Khandagale, Yoann Léveillé, Samuel Miller, Derek Pham, Ramy Eskander, Cass Lowry, Richard Compton, Judith Klavans, Maria Polinsky, Smaranda Muresan
| Challenge: | Polysynthetic languages are low-resource, lacking large scale annotated datasets needed to build and/or evaluate computational models. |
| Approach: | They propose to use linguistic priors to help with morphological segmentation and part-of-speech tagging tasks for Adyghe and Inuktitut . |
| Outcome: | The proposed methods improve morphological segmentation and part-of-speech tagging tasks on Adyghe and Inuktitut. |
Minimally-Supervised Morphological Segmentation using Adaptor Grammars with Linguistic Priors (2021.findings-acl)
Copied to clipboard
Ramy Eskander, Cass Lowry, Sujay Khandagale, Francesca Callejas, Judith Klavans, Maria Polinsky, Smaranda Muresan
| Challenge: | Unsupervised morphological segmentation is an essential subtask in many natural language processing applications. |
| Approach: | They introduce two types of priors: grammar definition and linguist-provided affixes . they show that priors boost morphological segmentation performance in a minimally-supervised manner . |
| Outcome: | The proposed priors achieve 8.9% and 34.2% error reductions over the state-of-the-art unsupervised system. |
Unsupervised Stem-based Cross-lingual Part-of-Speech Tagging for Morphologically Rich Low-Resource Languages (2022.naacl-main)
Copied to clipboard
| Challenge: | Low-resource languages lack annotated data even for basic syntactic information such as parts of speech. |
| Approach: | They propose an unsupervised cross-lingual approach for POS tagging for low-resource languages of rich morphology . they further investigate morpheme-level alignment and projection and use of linguistic priors for morphological segmentation . |
| Outcome: | The proposed approach outperforms the word-based approach and outperfies word-driven approaches. |