Zobrazeno 1 - 10
of 2 362
pro vyhledávání: '"Kanojia, A."'
Despite excellent results on benchmarks over a small subset of languages, large language models struggle to process text from languages situated in `lower-resource' scenarios such as dialects/sociolects (national or social varieties of a language), C
Externí odkaz:
http://arxiv.org/abs/2409.12683
Novel view acoustic synthesis (NVAS) aims to render binaural audio at any target viewpoint, given a mono audio emitted by a sound source at a 3D scene. Existing methods have proposed NeRF-based implicit models to exploit visual cues as a condition fo
Externí odkaz:
http://arxiv.org/abs/2406.08920
Audio-Visual Segmentation (AVS) aims to identify, at the pixel level, the object in a visual scene that produces a given sound. Current AVS methods rely on costly fine-grained annotations of mask-audio pairs, making them impractical for scalability.
Externí odkaz:
http://arxiv.org/abs/2403.14203
Autor:
Delfani, Jaleh, Orasan, Constantin, Saadany, Hadeel, Temizoz, Ozlem, Taylor-Stilgoe, Eleanor, Kanojia, Diptesh, Braun, Sabine, Schouten, Barbara
This study explores the use of Google Translate (GT) for translating mental healthcare (MHealth) information and evaluates its accuracy, comprehensibility, and implications for multilingual healthcare communication through analysing GT output in the
Externí odkaz:
http://arxiv.org/abs/2402.04023
Autor:
Gala, Jay, Jayakumar, Thanmay, Husain, Jaavid Aktar, M, Aswanth Kumar, Khan, Mohammed Safi Ur Rahman, Kanojia, Diptesh, Puduppully, Ratish, Khapra, Mitesh M., Dabre, Raj, Murthy, Rudra, Kunchukuttan, Anoop
We announce the initial release of "Airavata," an instruction-tuned LLM for Hindi. Airavata was created by fine-tuning OpenHathi with diverse, instruction-tuning Hindi datasets to make it better suited for assistive tasks. Along with the model, we al
Externí odkaz:
http://arxiv.org/abs/2401.15006
Autor:
Joshi, Aditya, Dabre, Raj, Kanojia, Diptesh, Li, Zhuang, Zhan, Haolan, Haffari, Gholamreza, Dippold, Doris
State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets. This survey delves into an important attribute of these datasets: the dialect of a languag
Externí odkaz:
http://arxiv.org/abs/2401.05632
Automatic Post-Editing (APE) is the task of automatically identifying and correcting errors in the Machine Translation (MT) outputs. We propose a repair-filter-use methodology that uses an APE system to correct errors on the target side of the MT tra
Externí odkaz:
http://arxiv.org/abs/2312.11312
Quality Estimation (QE) systems are important in situations where it is necessary to assess the quality of translations, but there is no reference available. This paper describes the approach adopted by the SurreyAI team for addressing the Sentence-L
Externí odkaz:
http://arxiv.org/abs/2312.00525
Autor:
Lent, Heather, Tatariya, Kushal, Dabre, Raj, Chen, Yiyi, Fekete, Marcell, Ploeger, Esther, Zhou, Li, Armstrong, Ruth-Ann, Eijansantos, Abee, Malau, Catriona, Heje, Hans Erik, Lavrinovics, Ernests, Kanojia, Diptesh, Belony, Paul, Bollmann, Marcel, Grobol, Loïc, de Lhoneux, Miryam, Hershcovich, Daniel, DeGraff, Michel, Søgaard, Anders, Bjerva, Johannes
Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research.While the genealogical ties between Creoles and a number of highly-resourced languages imply a significant potential for transfer l
Externí odkaz:
http://arxiv.org/abs/2310.19567
Autor:
Bhosale, Swapnil, Chaudhuri, Abhra, Williams, Alex Lee Robert, Tiwari, Divyank, Dutta, Anjan, Zhu, Xiatian, Bhattacharyya, Pushpak, Kanojia, Diptesh
The introduction of the MUStARD dataset, and its emotion recognition extension MUStARD++, have identified sarcasm to be a multi-modal phenomenon -- expressed not only in natural language text, but also through manners of speech (like tonality and int
Externí odkaz:
http://arxiv.org/abs/2310.01430