Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Khanuja, Simran"'
Given the rise of multimedia content, human translators increasingly focus on culturally adapting not only words but also other modalities such as images to convey the same meaning. While several applications stand to benefit from this, machine trans
Externí odkaz:
http://arxiv.org/abs/2404.01247
NLP models today strive for supporting multiple languages and modalities, improving accessibility for diverse users. In this paper, we evaluate their multilingual, multimodal capabilities by testing on a visual reasoning task. We observe that proprie
Externí odkaz:
http://arxiv.org/abs/2403.01404
We consider the task of optimally fine-tuning pre-trained multilingual models, given small amounts of unlabelled target data and an annotation budget. In this paper, we introduce DEMUX, a framework that prescribes the exact data-points to label from
Externí odkaz:
http://arxiv.org/abs/2311.06379
Autor:
Kabra, Anubha, Liu, Emmy, Khanuja, Simran, Aji, Alham Fikri, Winata, Genta Indra, Cahyawijaya, Samuel, Aremu, Anuoluwapo, Ogayo, Perez, Neubig, Graham
Figurative language permeates human communication, but at the same time is relatively understudied in NLP. Datasets have been created in English to accelerate progress towards measuring and improving figurative language processing in language models
Externí odkaz:
http://arxiv.org/abs/2305.16171
Autor:
Song, Yueqi, Cui, Catherine, Khanuja, Simran, Liu, Pengfei, Faisal, Fahim, Ostapenko, Alissa, Winata, Genta Indra, Aji, Alham Fikri, Cahyawijaya, Samuel, Tsvetkov, Yulia, Anastasopoulos, Antonios, Neubig, Graham
Despite the major advances in NLP, significant disparities in NLP system performance across languages still exist. Arguably, these are due to uneven resource allocation and sub-optimal incentives to work on less resourced languages. To track and furt
Externí odkaz:
http://arxiv.org/abs/2305.14716
In order for NLP technology to be widely applicable, fair, and useful, it needs to serve a diverse set of speakers across the world's languages, be equitable, i.e., not unduly biased towards any particular language, and be inclusive of all users, par
Externí odkaz:
http://arxiv.org/abs/2205.12676
Autor:
Conneau, Alexis, Ma, Min, Khanuja, Simran, Zhang, Yu, Axelrod, Vera, Dalmia, Siddharth, Riesa, Jason, Rivera, Clara, Bapna, Ankur
We introduce FLEURS, the Few-shot Learning Evaluation of Universal Representations of Speech benchmark. FLEURS is an n-way parallel speech dataset in 102 languages built on top of the machine translation FLoRes-101 benchmark, with approximately 12 ho
Externí odkaz:
http://arxiv.org/abs/2205.12446
Autor:
Conneau, Alexis, Bapna, Ankur, Zhang, Yu, Ma, Min, von Platen, Patrick, Lozhkov, Anton, Cherry, Colin, Jia, Ye, Rivera, Clara, Kale, Mihir, Van Esch, Daan, Axelrod, Vera, Khanuja, Simran, Clark, Jonathan H., Firat, Orhan, Auli, Michael, Ruder, Sebastian, Riesa, Jason, Johnson, Melvin
We introduce XTREME-S, a new benchmark to evaluate universal cross-lingual speech representations in many languages. XTREME-S covers four task families: speech recognition, classification, speech-to-text translation and retrieval. Covering 102 langua
Externí odkaz:
http://arxiv.org/abs/2203.10752
Autor:
Bapna, Ankur, Cherry, Colin, Zhang, Yu, Jia, Ye, Johnson, Melvin, Cheng, Yong, Khanuja, Simran, Riesa, Jason, Conneau, Alexis
We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unlabeled speech and text in multiple languages. mSLAM combines w2v-BERT p
Externí odkaz:
http://arxiv.org/abs/2202.01374
Pre-trained multilingual language models (LMs) have achieved state-of-the-art results in cross-lingual transfer, but they often lead to an inequitable representation of languages due to limited capacity, skewed pre-training data, and sub-optimal voca
Externí odkaz:
http://arxiv.org/abs/2106.02834