no code implementations • 30 Sep 2021 • Angeline Yasodhara, Azin Asgarian, Diego Huang, Parinaz Sobhani
The recent increase in the deployment of machine learning models in critical domains such as healthcare, criminal justice, and finance has highlighted the need for trustworthy methods that can explain these models to stakeholders.
no code implementations • EMNLP (sustainlp) 2021 • Zilun Peng, Akshay Budhkar, Ilana Tuil, Jason Levy, Parinaz Sobhani, Raphael Cohen, Jumana Nassour
Using a teacher-student approach, we distilled the knowledge from the original wav2vec 2. 0 model into a student model, which is 2 times faster and 4. 8 times smaller than the original model.
no code implementations • 3 Dec 2018 • Azin Asgarian, Parinaz Sobhani, Ji Chao Zhang, Madalin Mihailescu, Ariel Sibilia, Ahmed Bilal Ashraf, Babak Taati
Transfer learning can help overcome this issue by transferring the knowledge from readily available datasets (source) to a new dataset (target).
no code implementations • 12 Nov 2018 • Sophia Collet, Robert Dadashi, Zahi N. Karam, Chang Liu, Parinaz Sobhani, Yevgeniy Vahlis, Ji Chao Zhang
In this work, two approaches for private model aggregation are proposed that enable the transfer of knowledge from existing models trained on other companies' datasets to a new company with limited labeled data while protecting each client company's underlying individual sensitive information.
no code implementations • EACL 2017 • Parinaz Sobhani, Diana Inkpen, Xiaodan Zhu
Current models for stance classification often treat each target independently, but in many applications, there exist natural dependencies among targets, e. g., stance towards two or more politicians in an election or towards several brands of the same product.
no code implementations • 5 May 2016 • Saif M. Mohammad, Parinaz Sobhani, Svetlana Kiritchenko
However, a person may express the same stance towards a target by using negative or positive language.
no code implementations • LREC 2016 • Saif Mohammad, Svetlana Kiritchenko, Parinaz Sobhani, Xiaodan Zhu, Colin Cherry
Apart from stance, the tweets are also annotated for whether the target of interest is the target of opinion in the tweet.
no code implementations • 16 Mar 2015 • Xiaodan Zhu, Parinaz Sobhani, Hongyu Guo
The chain-structured long short-term memory (LSTM) has showed to be effective in a wide range of problems such as speech recognition and machine translation.