no code implementations • MMMPIE (COLING) 2022 • Ehsan Doostmohammadi, Marco Kuhlmann
The results show that the smaller model benefits from video grounding in predicting highly imageable words, while the results for the larger model seem harder to interpret. of lack of grounding, e. g., addressing issues like models’ insufficient commonsense knowledge.
no code implementations • 16 Feb 2024 • Ehsan Doostmohammadi, Oskar Holmström, Marco Kuhlmann
Work on instruction-tuned Large Language Models (LLMs) has used automatic methods based on text overlap and LLM judgments as cost-effective alternatives to human evaluation.
1 code implementation • 25 May 2023 • Ehsan Doostmohammadi, Tobias Norlund, Marco Kuhlmann, Richard Johansson
Inspired by this, we replace the semantic retrieval in Retro with a surface-level method based on BM25, obtaining a significant reduction in perplexity.
no code implementations • 23 Feb 2023 • Tobias Norlund, Ehsan Doostmohammadi, Richard Johansson, Marco Kuhlmann
Recent work on the Retrieval-Enhanced Transformer (RETRO) model has shown that off-loading memory from trainable weights to a retrieval database can significantly improve language modeling and match the performance of non-retrieval models that are an order of magnitude larger in size.
no code implementations • 15 Apr 2021 • Nasrin Taghizadeh, Ehsan Doostmohammadi, Elham Seifossadat, Hamid R. Rabiee, Maedeh S. Tahaei
We have released Sina-BERT, a language model pre-trained on BERT (Devlin et al., 2018) to address the lack of a high-quality Persian language model in the medical domain.
no code implementations • COLING 2020 • Ehsan Doostmohammadi, Minoo Nassajian, Adel Rahimi
Words are properly segmented in the Persian writing system; in practice, however, these writing rules are often neglected, resulting in single words being written disjointedly and multiple words written without any white spaces between them.
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.
no code implementations • WS 2019 • Ehsan Doostmohammadi, Minoo Nassajian
Identification of the languages written using cuneiform symbols is a difficult task due to the lack of resources and the problem of tokenization.
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.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Ehsan Doostmohammadi, Minoo Nassajian, Adel Rahimi
Ezafe is a grammatical particle in some Iranian languages that links two words together.