1 code implementation • dialdoc (ACL) 2022 • Sayed Hesam Alavian, Ali Satvaty, Sadra Sabouri, Ehsaneddin Asgari, Hossein Sameti
Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative answers based on users’ needs.
2 code implementations • 7 Apr 2024 • Pouya Fallah, Soroush Gooran, Mohammad Jafarinasab, Pouya Sadeghi, Reza Farnia, Amirreza Tarabkhah, Zainab Sadat Taghavi, Hossein Sameti
Language models, particularly generative models, are susceptible to hallucinations, generating outputs that contradict factual knowledge or the source text.
2 code implementations • 7 Dec 2023 • Hamed Hematian Hemati, Atousa Toghyani, Atena Souri, Sayed Hesam Alavian, Hossein Sameti, Hamid Beigy
Our models include baseline models and pre-trained models, which are leveraged to boost the performance of the model.
no code implementations • 20 Aug 2023 • Zeinab Sadat Taghavi, Soroush Gooran, Seyed Arshan Dalili, Hamidreza Amirzadeh, Mohammad Jalal Nematbakhsh, Hossein Sameti
In this paper, we introduce a novel Artificial Intelligence (AI) system inspired by the philosophical and psychoanalytical concept of imagination as a ``Re-construction of Experiences".
1 code implementation • 21 Jul 2023 • Zeinab Sadat Taghavi, Ali Satvaty, Hossein Sameti
Speech Emotion Recognition (SER) is a challenging task.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 21 Apr 2023 • Leila Khalatbari, Yejin Bang, Dan Su, Willy Chung, Saeed Ghadimi, Hossein Sameti, Pascale Fung
Our approach differs from the standard contrastive learning framework in that it automatically obtains positive and negative signals from the safe and unsafe language distributions that have been learned beforehand.
1 code implementation • 29 Aug 2022 • Sadra Sabouri, Elnaz Rahmati, Soroush Gooran, Hossein Sameti
We propose naab, the biggest cleaned and ready-to-use open-source textual corpus in Farsi.
no code implementations • 2 Aug 2022 • Mahdi Rezaei, Negar Nayeri, Saeed Farzi, Hossein Sameti
In this paper, we investigate the application of end-to-end and multi-module frameworks for G2P conversion for the Persian language.
no code implementations • 25 Sep 2020 • Ehsan Doostmohammadi, Mohammad Hadi Bokaei, Hossein Sameti
Since previous studies on Persian keyword or keyphrase extraction have not published their data, the field suffers from the lack of a human extracted keyphrase dataset.
1 code implementation • 25 Sep 2020 • Ehsan Doostmohammadi, Mohammad Hadi Bokaei, Hossein Sameti
Keyphrases are a very short summary of an input text and provide the main subjects discussed in the text.
1 code implementation • SEMEVAL 2019 • Ehsan Doostmohammadi, Hossein Sameti, Ali Saffar
This paper presents the models submitted by Ghmerti team for subtasks A and B of the OffensEval shared task at SemEval 2019.
no code implementations • 12 Jan 2020 • Elham Seifossadat, Hossein Sameti
This article presents a stochastic corpus-based model for generating natural language text.
no code implementations • 13 Jul 2019 • Nooshin Maghsoodi, Hossein Sameti, Hossein Zeinali, Themos~Stafylakis
By making use of the natural partition of input features into digits, we train digit-specific i-vector extractors on top of each HMM and we extract well-localized i-vectors, each modelling merely the phonetic content corresponding to a single digit.
no code implementations • 28 Sep 2018 • Hossein Zeinali, Lukas Burget, Hossein Sameti, Jan Cernocky
The task of spoken pass-phrase verification is to decide whether a test utterance contains the same phrase as given enrollment utterances.
no code implementations • Interspeech 2018 2018 • Hossein Hadian, Hossein Sameti, Daniel Povey, Sanjeev Khudanpur
We present our work on end-to-end training of acoustic models using the lattice-free maximum mutual information (LF-MMI) objective function in the context of hidden Markov models.
Ranked #1 on Speech Recognition on Switchboard (300hr)