Zobrazeno 1 - 10
of 70
pro vyhledávání: '"Sethy, Abhinav"'
Autor:
Hayati, Shirley Anugrah, Jung, Taehee, Bodding-Long, Tristan, Kar, Sudipta, Sethy, Abhinav, Kim, Joo-Kyung, Kang, Dongyeop
Fine-tuning large language models (LLMs) with a collection of large and diverse instructions has improved the model's generalization to different tasks, even for unseen tasks. However, most existing instruction datasets include only single instructio
Externí odkaz:
http://arxiv.org/abs/2402.11532
Autor:
Richardson, Chris, Zhang, Yao, Gillespie, Kellen, Kar, Sudipta, Singh, Arshdeep, Raeesy, Zeynab, Khan, Omar Zia, Sethy, Abhinav
Personalization, the ability to tailor a system to individual users, is an essential factor in user experience with natural language processing (NLP) systems. With the emergence of Large Language Models (LLMs), a key question is how to leverage these
Externí odkaz:
http://arxiv.org/abs/2310.20081
Autor:
Richardson, Christopher, Kar, Sudipta, Kumar, Anjishnu, Ramachandran, Anand, Khan, Omar Zia, Raeesy, Zeynab, Sethy, Abhinav
Open domain conversational agents can answer a broad range of targeted queries. However, the sequential nature of interaction with these systems makes knowledge exploration a lengthy task which burdens the user with asking a chain of well phrased que
Externí odkaz:
http://arxiv.org/abs/2302.10978
Autor:
Gillespie, Kellen, Konstantakopoulos, Ioannis C., Guo, Xingzhi, Vasudevan, Vishal Thanvantri, Sethy, Abhinav
Publikováno v:
2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020, pp. 7859-7863
User interactions with personal assistants like Alexa, Google Home and Siri are typically initiated by a wake term or wakeword. Several personal assistants feature "follow-up" modes that allow users to make additional interactions without the need of
Externí odkaz:
http://arxiv.org/abs/2010.01949
Autor:
Shakeri, Siamak, Sethy, Abhinav
Generating paraphrases that are lexically similar but semantically different is a challenging task. Paraphrases of this form can be used to augment data sets for various NLP tasks such as machine reading comprehension and question answering with non-
Externí odkaz:
http://arxiv.org/abs/1911.11952
Autor:
Li, Alexander Hanbo, Sethy, Abhinav
Most recent neural semi-supervised learning algorithms rely on adding small perturbation to either the input vectors or their representations. These methods have been successful on computer vision tasks as the images form a continuous manifold, but a
Externí odkaz:
http://arxiv.org/abs/1911.11756
Complex deep learning models now achieve state of the art performance for many document retrieval tasks. The best models process the query or claim jointly with the document. However for fast scalable search it is desirable to have document embedding
Externí odkaz:
http://arxiv.org/abs/1911.11065
Autor:
Li, Alexander Hanbo, Sethy, Abhinav
Neural network models have been very successful at achieving high accuracy on natural language inference (NLI) tasks. However, as demonstrated in recent literature, when tested on some simple adversarial examples, most of the models suffer a signific
Externí odkaz:
http://arxiv.org/abs/1909.00102
Autor:
Powers, Thomas, Fakoor, Rasool, Shakeri, Siamak, Sethy, Abhinav, Kainth, Amanjit, Mohamed, Abdel-rahman, Sarikaya, Ruhi
Optimal selection of a subset of items from a given set is a hard problem that requires combinatorial optimization. In this paper, we propose a subset selection algorithm that is trainable with gradient-based methods yet achieves near-optimal perform
Externí odkaz:
http://arxiv.org/abs/1810.12464
Language models (LMs) based on Long Short Term Memory (LSTM) have shown good gains in many automatic speech recognition tasks. In this paper, we extend an LSTM by adding highway networks inside an LSTM and use the resulting Highway LSTM (HW-LSTM) mod
Externí odkaz:
http://arxiv.org/abs/1709.06436