Leveraging ParsBERT and Pretrained mT5 for Persian Abstractive Text Summarization

Farahani, Mehrdad; Gharachorloo, Mohammad; Manthouri, Mohammad

doi:10.1109/csicc52343.2021.9420563

Cited by 20 publications

(10 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For any given embedding space, an object is created which provides a wide range of functions. NER ARMAN (Poostchi et al, 2018) NER PEYMA (Shahshahani et al, 2018) NER FarsTail (Amirkhani et al, 2020) Textual Entailment FaSpell 9 Spell Checking PersianNews (Farahani et al, 2020) Text Classification PerDT Universal Dependency PnSummary (Farahani et al, 2021) Text Summarization SnappfoodSentiment (Farahani et al, 2020) Sentiment Classification TEP (Pilevar et al, 2011) Text Translation(eng-fa) WikipediaCorpus Corpus PersianTweets (Khojasteh et al, 2020) Corpus The details of the corresponding embeddings can be shown with get embedding info(<EMBEDDING>). Several functions are present in DadmaTools that can be used for word embeddings, such as finding top nearest neighbours, finding similarity scores between two given words, or getting sentence embedding of a text.…”

Section: Embedding Modulementioning

confidence: 99%

DadmaTools: Natural Language Processing Toolkit for Persian Language

Etezadi¹,

Karrabi²,

Zare³

et al. 2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

We introduce DadmaTools, an open-source Python Natural Language Processing toolkit for the Persian language. The toolkit is a neural pipeline based on spaCy for several text processing tasks, including normalization, tokenization, lemmatization, part-of-speech, dependency parsing, constituency parsing, chunking, and ezafe detecting. DadmaTools relies on fine-tuning of ParsBERT using the PerDT dataset for most of the tasks. Dataset module and embedding module are included in Dad-maTools that support different Persian datasets, embeddings, and commonly used functions for them. Our evaluations show that DadmaTools can attain state-of-the-art performance on multiple NLP tasks. The source code is freely available at https://github.com/Dadmatech/ DadmaTools.

show abstract

Section: Embedding Modulementioning

confidence: 99%

DadmaTools: Natural Language Processing Toolkit for Persian Language

Etezadi¹,

Karrabi²,

Zare³

et al. 2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…PersianNER 8 NER ARMAN (Poostchi et al, 2018) NER PEYMA (Shahshahani et al, 2018) NER FarsTail (Amirkhani et al, 2020) Textual Entailment FaSpell 9 Spell Checking PersianNews (Farahani et al, 2020) Text Classification PerDT Universal Dependency PnSummary (Farahani et al, 2021) Text Summarization SnappfoodSentiment (Farahani et al, 2020) Sentiment Classification TEP (Pilevar et al, 2011) Text Translation(eng-fa) WikipediaCorpus Corpus PersianTweets (Khojasteh et al, 2020) Corpus…”

Section: Appendixmentioning

confidence: 99%

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations

2022

View full text Add to dashboard Cite

Textless spoken language processing research aims to extend the applicability of standard NLP toolset onto spoken language and languages with few or no textual resources. In this paper, we introduce textless-lib, a PyTorch-based library aimed to facilitate research in this research area. We describe the building blocks that the library provides and demonstrate its usability by discuss three different use-case examples: (i) speaker probing, (ii) speech resynthesis and compression, and (iii) speech continuation. We believe that textless-lib substantially simplifies research the textless setting and will be handful not only for speech researchers but also for the NLP community at large. The code, documentation, and pre-trained models are available at https://github.com/ facebookresearch/textlesslib/.

show abstract

“…The mT5 can be successfully applied in a multilingual context and the models can achieve outstanding results in a number of reference tasks and the applicability of the framework can be extended to other areas as well. Pre-trained mT5 has been applied to successfully generate abstractive text summaries in a range of languages, including Persian (Farahani, Gharachorloo & Manthouri 2020), Arabic Fuad &Al-Yahya (2022), andStankevi cius &Lukoševi cius (2021). Since mT5 includes Hungarian language as well, we could apply the mT5 small model for summary generation in our research.…”

Section: T5 Mt5mentioning

confidence: 99%

Neural text summarization for Hungarian

Yang

2022

ALing

View full text Add to dashboard Cite

One of the most important NLP tasks for the industry today is to produce an extract from longer text documents. This task is one of the hottest topics for the researchers and they have created some solutions for English. There are two types of the text summarization called extractive and abstractive. The goal of the first task is to find the relevant sentences from the text, while the second one should generate the extraction based on the original text. In this research I have built the first solutions for Hungarian text summarization systems both for extractive and abstractive subtasks. Different kinds of neural transformer-based methods were used and evaluated. I present in this publication the first Hungarian abstractive summarization tool based on mBART and mT5 models, which gained state-of-the-art results.

show abstract

Leveraging ParsBERT and Pretrained mT5 for Persian Abstractive Text Summarization

Cited by 20 publications

References 13 publications

DadmaTools: Natural Language Processing Toolkit for Persian Language

DadmaTools: Natural Language Processing Toolkit for Persian Language

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations

Neural text summarization for Hungarian

Contact Info

Product

Resources

About