no code implementations • 16 Nov 2023 • Sagi Pendzel, Tomer Wullach, Amir Adler, Einat Minkov
In addition, we explore and compare the performance of the finetuned LLMs with zero-shot hate detection using a GPT-3. 5 model.
no code implementations • 16 Oct 2023 • Tomer Wullach, Shlomo E. Chazan
The challenges facing speech recognition systems, such as variations in pronunciations, adverse audio conditions, and the scarcity of labeled data, emphasize the necessity for a post-processing step that corrects recurring errors.
no code implementations • 27 Dec 2022 • Tomer Wullach, Shlomo E. Chazan
One prominent speech recognition decoding heuristic is beam search, which seeks the transcript with the greatest likelihood computed using the predicted distribution.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 21 Mar 2022 • Tomer Wullach, Shlomo E. Chazan
Recently proposed speech recognition systems are designed to predict using representations generated by their top layers, employing greedy decoding which isolates each timestep from the rest of the sequence.
1 code implementation • 11 Nov 2021 • Tomer Wullach, Amir Adler, Einat Minkov
Our results show that the proposed HyperNetworks achieve performance that is competitive, and better in some cases, than these pretrained language models, while being smaller by orders of magnitude.
no code implementations • Findings (EMNLP) 2021 • Tomer Wullach, Amir Adler, Einat Minkov
Automatic hate speech detection is hampered by the scarcity of labeled datasetd, leading to poor generalization.
1 code implementation • 13 May 2020 • Tomer Wullach, Amir Adler, Einat Minkov
Hate speech detection is a critical problem in social media platforms, being often accused for enabling the spread of hatred and igniting physical violence.