NSF PAR Search | NSF Public Access Repository

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

Wav2Gloss: Generating Interlinear Glossed Text from Speech

https://doi.org/10.18653/v1/2024.acl-long.34

He, Taiqi; Choi, Kwanghee; Tjuatja, Lindia; Robinson, Nathaniel; Shi, Jiatong; Watanabe, Shinji; Neubig, Graham; Mortensen, David; Levin, Lori (August 2024, Association for Computational Linguistics)

Full Text Available
GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text

https://doi.org/10.18653/v1/2024.emnlp-main.683

Ginn, Michael; Tjuatja, Lindia; He, Taiqi; Rice, Enora; Neubig, Graham; Palmer, Alexis; Levin, Lori (January 2024, Association for Computational Linguistics)

Full Text Available
SigMoreFun Submission to the SIGMORPHON Shared Task on Interlinear Glossing

https://doi.org/10.18653/v1/2023.sigmorphon-1.22

He, Taiqi; Tjuatja, Lindia; Robinson, Nathaniel; Watanabe, Shinji; Mortensen, David R.; Neubig, Graham; Levin, Lori (January 2023, Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology)

Full Text Available
Generalized Glossing Guidelines: An Explicit, Human- and Machine-Readable, Item-and-Process Convention for Morphological Annotation

https://doi.org/10.18653/v1/2023.sigmorphon-1.7

Mortensen, David R.; Gulsen, Ela; He, Taiqi; Robinson, Nathaniel; Amith, Jonathan; Tjuatja, Lindia; Levin, Lori (January 2023, Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology)

Full Text Available
Language Embeddings for Typology and Cross-lingual Transfer Learning

https://doi.org/10.18653/v1/2021.acl-long.560

Yu, Dian; He, Taiqi; Sagae, Kenji (January 2021, Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers))
null (Ed.)
Cross-lingual language tasks typically require a substantial amount of annotated data or parallel translation data. We explore whether language representations that capture relationships among languages can be learned and subsequently leveraged in cross-lingual tasks without the use of parallel data. We generate dense embeddings for 29 languages using a denoising autoencoder, and evaluate the embeddings using the World Atlas of Language Structures (WALS) and two extrinsic tasks in a zero-shot setting: cross-lingual dependency parsing and cross-lingual natural language inference.
more » « less
Full Text Available

Search for: All records