Zobrazeno 1 - 10
of 2 087
pro vyhledávání: '"Khanuja, A."'
Beyond conventional paradigms of translating speech and text, recently, there has been interest in automated transcreation of images to facilitate localization of visual content across different cultures. Attempts to define this as a formal Machine L
Externí odkaz:
http://arxiv.org/abs/2412.13717
Autor:
Chandra, Mohit, Sriraman, Siddharth, Verma, Gaurav, Khanuja, Harneet Singh, Campayo, Jose Suarez, Li, Zihang, Birnbaum, Michael L., De Choudhury, Munmun
Adverse Drug Reactions (ADRs) from psychiatric medications are the leading cause of hospitalizations among mental health patients. With healthcare systems and online communities facing limitations in resolving ADR-related issues, Large Language Model
Externí odkaz:
http://arxiv.org/abs/2410.19155
Autor:
Yue, Xiang, Song, Yueqi, Asai, Akari, Kim, Seungone, Nyandwi, Jean de Dieu, Khanuja, Simran, Kantharuban, Anjali, Sutawika, Lintang, Ramamoorthy, Sathyanarayanan, Neubig, Graham
Despite recent advances in multimodal large language models (MLLMs), their development has predominantly focused on English- and western-centric datasets and tasks, leaving most of the world's languages and diverse cultural contexts underrepresented.
Externí odkaz:
http://arxiv.org/abs/2410.16153
Autor:
Li, Baiqi, Lin, Zhiqiu, Peng, Wenxuan, Nyandwi, Jean de Dieu, Jiang, Daniel, Ma, Zixian, Khanuja, Simran, Krishna, Ranjay, Neubig, Graham, Ramanan, Deva
Vision-language models (VLMs) have made significant progress in recent visual-question-answering (VQA) benchmarks that evaluate complex visio-linguistic reasoning. However, are these models truly effective? In this work, we show that VLMs still strug
Externí odkaz:
http://arxiv.org/abs/2410.14669
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
Autor:
Annapureddy Sai Krishna, Jyotsna Agarwal, Samiksha Khanuja, Sandeep Kumar, Adam Khan, Khairat Mohammad Butt
Publikováno v:
Indian Journal of Anaesthesia, Vol 68, Iss 9, Pp 795-800 (2024)
Background and Aims: One major limitation of the spinal block remains the inability to extend the duration of the block intraoperatively unless planned before with spinal or epidural catheters and/or intrathecal additives. This study was designed to
Externí odkaz:
https://doaj.org/article/acb7f4f093ee4d57a5ed8b74c0f7a51d
