Persian Ezafe Recognition Using Transformers and Its Role in Part-Of-Speech Tagging

Doostmohammadi, Ehsan; Nassajian, Minoo; Rahimi, Adel

doi:10.18653/v1/2020.findings-emnlp.86

Cited by 2 publications

(2 citation statements)

References 30 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a research by Doostmohammadi et al, they have exploited Transformer-based, BERT, and XLMRoBERTa methods, and achieved the best results, with respect to the previous works [58]. In another research accomplished by Ansari et al, they tackled the problem of Ezafe recognition using ParsBert transformer.…”

Section: Ezafe Recognition Using Transformersmentioning

confidence: 99%

Persian Ezafe Recognition Using Neural Approaches

Asghari,

Faili

2024

jist

View full text Add to dashboard Cite

Persian Ezafe Recognition aims to automatically identify the occurrences of Ezafe (short vowel /e/) which should be pronounced but usually is not orthographically represented. This task is similar to the task of diacritization and vowel restoration in Arabic. Ezafe recognition can be used in spelling disambiguation in Text to Speech Systems (TTS) and various other language processing tasks such as syntactic parsing and semantic role labeling. In this paper, we propose two neural approaches for the automatic recognition of Ezafe markers in Persian texts. We have tackled the Ezafe recognition task by using a Neural Sequence Labeling method and a Neural Machine Translation (NMT) approach as well. Some syntactic features are proposed to be exploited in the neural models. We have used various combinations of lexical features such as word forms, Part of Speech Tags, and ending letter of the words to be applied to the models. These features were statistically derived using a large annotated Persian text corpus and were optimized by a forward selection method. In order to evaluate the performance of our approaches, we examined nine baseline models including state-of-the-art approaches for recognition of Ezafe markers in Persian text. Our experiments on Persian Ezafe recognition based on neural approaches employing some optimized features into the models show that they can drastically improve the results of the baselines. They can also achieve better results than the Conditional Random Field method as the best-performing baseline. On the other hand, although the results of the NMT approach show a better performance compared to other baseline approaches, it cannot achieve better performance than the Neural Sequence Labeling method. The best achieved F1measure based on neural sequence labeling is 96.29%

show abstract

Section: Ezafe Recognition Using Transformersmentioning

confidence: 99%

Persian Ezafe Recognition Using Neural Approaches

Asghari,

Faili

2024

jist

View full text Add to dashboard Cite

show abstract

“…Using transformers library (Wolf et al, 2020), we fine-tune different pretrained transformer-based models for the task of chunking because earlier works have shown their superior ability to perform well on shallow parsing tasks (Tran et al, 2020;Doostmohammadi et al, 2020;Li et al, 2021). The word embeddings are obtained by taking an unweighted average of all its subword embeddings.…”

Section: Modelmentioning

confidence: 99%

IndIE: A Multilingual Open Information Extraction Tool For Indic Languages

Mishra,

Singh,

Shah

et al. 2023

Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings)

View full text Add to dashboard Cite

Open Information Extraction (OIE) is the process of extracting informative facts from opendomain natural language text. A multilingual OIE tool, IndIE, has been proposed, which performs chunking, creates a Merged-phrase Dependency Tree (MDT), and generates triples using hand-crafted rules. It is observed that fine-tuned transformer-based chunker outperforms other traditional methods of chunking. A benchmark called Hindi-BenchIE has also been developed for automatically evaluating Hindi triples. The developed OIE tool, IndIE, has been automatically evaluated on the goldentriples of 112 Hindi sentences. Compared to other multilingual methods, the IndIE method generates more meaningful triples with 0.51 F1-score. It is observed that IndIE generates more fine-grained triples than other methods. It is conjectured that IndIE has the ability to generate meaningful triples for Urdu, Tamil, and Telugu sentences as well because the developed chunker is shown to generalize across various natural languages, and the triple generation rules are based on dependency relations that are common to the aforementioned Indic languages.Triple generator algorithm from Merged-phrase Dependency Tree (MDT)Head, T ail ← FIND_HEAD(M DT, t) , t 5:Rel ← x where (x ∈ t.children ∧ x.dep_rel = 'cop') 6: else 7: Head, T ail ← FIND_HEAD(M DT, t) , FIND_TAIL(M DT, t) 8: Rel ← t + x where (x ∈ t.children ∧ x.dep_rel = 'cop') 9: end if 10: else if 'advcl' == t.dep_rel then 11:Head ← q.T ail + q.Rel where (q ∈ Q ∧ t.parent ∈ q) 12:Rel, T ail ← t , FIND_TAIL(M DT, t) 13: else if 'acl' == t.dep_rel then 14:Head ← t.closest_phrase(q.T ail, q.Head) where (q ∈ Q ∧ t.parent ∈ q)

show abstract

Persian Ezafe Recognition Using Transformers and Its Role in Part-Of-Speech Tagging

Cited by 2 publications

References 30 publications

Persian Ezafe Recognition Using Neural Approaches

Persian Ezafe Recognition Using Neural Approaches

IndIE: A Multilingual Open Information Extraction Tool For Indic Languages

Contact Info

Product

Resources

About