Zobrazeno 1 - 10
of 289
pro vyhledávání: '"Robinson, Nathaniel"'
Autor:
Naik, Atharva, Zhang, Kexun, Robinson, Nathaniel, Mysore, Aravind, Marr, Clayton, Byrnes, Hong Sng Rebecca, Cai, Anna, Chang, Kalvin, Mortensen, David
Historical linguists have long written a kind of incompletely formalized ''program'' that converts reconstructed words in an ancestor language into words in one of its attested descendants that consist of a series of ordered string rewrite functions
Externí odkaz:
http://arxiv.org/abs/2406.12725
Autor:
Robinson, Nathaniel R., Dabre, Raj, Shurtz, Ammon, Dent, Rasul, Onesi, Onenamiyi, Monroc, Claire Bizon, Grobol, Loïc, Muhammad, Hasan, Garg, Ashi, Etori, Naome A., Tiyyala, Vijay Murari, Samuel, Olanrewaju, Stutzman, Matthew Dean, Odoom, Bismarck Bamfo, Khudanpur, Sanjeev, Richardson, Stephen D., Murray, Kenton
A majority of language technologies are tailored for a small number of high-resource languages, while relatively many low-resource languages are neglected. One such group, Creole languages, have long been marginalized in academic study, though their
Externí odkaz:
http://arxiv.org/abs/2405.05376
Autor:
He, Taiqi, Choi, Kwanghee, Tjuatja, Lindia, Robinson, Nathaniel R., Shi, Jiatong, Watanabe, Shinji, Neubig, Graham, Mortensen, David R., Levin, Lori
Thousands of the world's languages are in danger of extinction--a tremendous threat to cultural identities and human language diversity. Interlinear Glossed Text (IGT) is a form of linguistic annotation that can support documentation and resource cre
Externí odkaz:
http://arxiv.org/abs/2403.13169
Autor:
Chang, Kalvin, Robinson, Nathaniel R., Cai, Anna, Chen, Ting, Zhang, Annie, Mortensen, David R.
We describe a set of new methods to partially automate linguistic phylogenetic inference given (1) cognate sets with their respective protoforms and sound laws, (2) a mapping from phones to their articulatory features and (3) a typological database o
Externí odkaz:
http://arxiv.org/abs/2402.01582
Large language models (LLMs) implicitly learn to perform a range of language tasks, including machine translation (MT). Previous studies explore aspects of LLMs' MT capabilities. However, there exist a wide variety of languages for which recent LLM M
Externí odkaz:
http://arxiv.org/abs/2309.07423
Autor:
Zouhar, Vilém, Chang, Kalvin, Cui, Chenxuan, Carlson, Nathaniel, Robinson, Nathaniel, Sachan, Mrinmaya, Mortensen, David
Mapping words into a fixed-dimensional vector space is the backbone of modern NLP. While most word embedding methods successfully encode semantic information, they overlook phonetic information that is crucial for many tasks. We develop three methods
Externí odkaz:
http://arxiv.org/abs/2304.02541
Multilingual transfer techniques often improve low-resource machine translation (MT). Many of these techniques are applied without considering data characteristics. We show in the context of Haitian-to-English translation that transfer effectiveness
Externí odkaz:
http://arxiv.org/abs/2209.06295
Developing Automatic Speech Recognition (ASR) for low-resource languages is a challenge due to the small amount of transcribed audio data. For many such languages, audio and text are available separately, but not audio with transcriptions. Using text
Externí odkaz:
http://arxiv.org/abs/2207.09889
Autor:
Robinson, Nathaniel James
Breast cancer (BC) is the most commonly diagnosed cancer, and the most prevalent cause of cancer-related mortality, in women worldwide. Importantly, approximately 90% of BC-associated deaths are attributable to metastasis, which stems from a paucity
Autor:
Moreno-Martinez, Alvaro, Maneta, Marco, Camps-Valls, Gustau, Martino, Luca, Robinson, Nathaniel, Allred, Brady, Running, Steven W
Publikováno v:
IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium
Products derived from a single multispectral sensor are hampered by a limited spatial, spectral or temporal resolutions. Image fusion in general and downscaling/blending in particular allow to combine different multiresolution datasets. We present he
Externí odkaz:
http://arxiv.org/abs/2012.07987