no code implementations • 10 Apr 2024 • Yu Ying Chiu, Liwei Jiang, Maria Antoniak, Chan Young Park, Shuyue Stella Li, Mehar Bhatia, Sahithya Ravi, Yulia Tsvetkov, Vered Shwartz, Yejin Choi
Our study reveals that CulturalTeaming's various modes of AI assistance support annotators in creating cultural questions, that modern LLMs fail at, in a gamified manner.
no code implementations • 19 Mar 2024 • Maksym Taranukhin, Sahithya Ravi, Gabor Lukacs, Evangelos Milios, Vered Shwartz
Recognizing this demand, we present a chatbot to assist passengers and educate them about their rights.
no code implementations • 28 Feb 2024 • Sahithya Ravi, Patrick Huber, Akshat Shrivastava, Aditya Sagar, Ahmed Aly, Vered Shwartz, Arash Einolghozati
The emergence of Large Language Models (LLMs) has brought to light promising language generation capabilities, particularly in performing tasks like complex reasoning and creative writing.
1 code implementation • 3 Nov 2023 • Wenkai Chen, Sahithya Ravi, Vered Shwartz
One of the major limitations of the basic score is that it treats all words as equally important.
1 code implementation • 24 May 2023 • Sahithya Ravi, Raymond Ng, Vered Shwartz
We propose COMET-M (Multi-Event), an event-centric commonsense model capable of generating commonsense inferences for a target event within a complex sentence.
1 code implementation • 20 Feb 2023 • Sahithya Ravi, Chris Tanner, Raymond Ng, Vered Shwartz
Event coreference models cluster event mentions pertaining to the same real-world event.
1 code implementation • 24 Oct 2022 • Sahithya Ravi, Aditya Chinchure, Leonid Sigal, Renjie Liao, Vered Shwartz
In contrast to previous methods which inject knowledge from static knowledge bases, we investigate the incorporation of contextualized knowledge using Commonsense Transformer (COMET), an existing knowledge model trained on human-curated knowledge bases.
Ranked #8 on Visual Question Answering (VQA) on A-OKVQA (DA VQA Score metric)
no code implementations • 30 Nov 2020 • Sahithya Ravi, Samaneh Khoshrou, Mykola Pechenizkiy
In the light of the COVID-19 pandemic, deep learning methods have been widely investigated in detecting COVID-19 from chest X-rays.
1 code implementation • 6 Nov 2019 • Matthias Feurer, Jan N. van Rijn, Arlind Kadra, Pieter Gijsbers, Neeratyoy Mallik, Sahithya Ravi, Andreas Müller, Joaquin Vanschoren, Frank Hutter
It also provides functionality to conduct machine learning experiments, upload the results to OpenML, and reproduce results which are stored on OpenML.
no code implementations • 19 Feb 2019 • Sahithya Ravi, Pouria Zand, Mohieddine El Soussi, Majid Nabi
The resource allocation and link adaptation in NS-3 are modified to comply with the new features of NB-IoT.
Networking and Internet Architecture