Persian Sentences Research Articles

PAMR: Persian Abstract Meaning Representation Corpus

One of the most used and well-known semantic representation models is Abstract Meaning Representation (AMR). This representation has had numerous applications in natural language processing tasks in recent years. Currently, for English and Chinese languages, large annotated corpora are available. In addition, in some low-resource languages, related corpora have been generated with less size; although, until now, to the best of our knowledge, there is not any AMR corpus for the Persian/Farsi language. Therefore, the aim of this article is to create a Persian AMR (PAMR) corpus via translating English sentences and adjusting AMR guidelines and to solve the various challenges that are faced in this regard. The result of this research is a corpus, containing 1,020 Persian sentences and their related AMR that can be used in various natural language processing tasks. In this article, to investigate the feasibility of using the corpus, we have applied it to two natural language processing tasks: Sentiment Analysis and Text Summarization.

Determining Frequency Importance Function for Speech Intelligibility of Persian Monosyllabic Words and the List of Quick Speech in Noise in Persian Language

Background and Aim: The Frequency Importance Function (FIF) is the main component of the Speech Intelligibility Index (SII) for a certain language. The FIF indicates the relative importance of each frequency band as it contributes to speech intelligibility. This study was conducted to determine the FIF for the Persian monosyllabic words and the list of Quick Speech in Noise (QSIN) in Persian language. Methods: In this exploration study, 34 monolingual Persian-speaking subjects aged 25–40 years with normal hearing (17 males) were included. The FIF was evaluated for 100 monosyllabic words and 30 sentences of Persian QSIN under 180 different auditory conditions. The speech recognition scores were calculated and crossover frequencies were determined. Then, the relative transfer function was extracted and FIFs were calculated. Results: The findings showed that for monosyllabic word material, the FIF had three peaks at 178, 1787, and 4467 Hz and for Persian QSIN, the FIF had an initial peak at about 141 Hz followed by a peak at about 1800 Hz. According to the results, the frequency range 891–8913 Hz is very important for recognition of the Persian words. Moreover, the mean crossover frequencies for the Persian sentences was 1446 Hz. Conclusion: For monosyllabic word material in the Persian language, the FIF at 708–1778 Hz is very important for recognition of the Persian monosyllabic words. For sentence material in the Persian Language, the FIF at 708–4467 Hz has the highest importance for recognition of Persian sentences. Keywords: Frequency importance function; speech intelligibility index; monosyllabic word; quick speech in noise list; Persian language

Agree and the subjects of specificational clauses

AbstractThis article investigates agreement in Persian sentences with a specificational copular clause embedded under the epistemic modal tavānestan ‘can’. We argue that this structure is a raising structure. It exhibits agreement on both the embedded and modal verbs. Crucially, while the subject fails to control agreement in the embedded clause, it successfully controls agreement on the modal. We argue that the subject's failure to form an Agree relation in the embedded specificational clause is due to its defective feature structure, resulting in agreement with the lower noun phrase instead, this being an accessible goal as well. In the matrix clause, the lower noun phrase is inaccessible, due to the presence of an intervening domain boundary. This triggers probe reduction, a process that impoverishes the feature structure of the probe, expanding the set of possible goals to include the subject. We extend this analysis to subject agreement in simple specificational clauses in languages like English.

Classi cation of incomplete Persian sentences with ellipsis

Classi cation of incomplete Persian sentences with ellipsis

Presence or Absence of the Object Marker “Râ” in the Speech of Aphasic Patients With Agrammatic Broca’s Aphasia

Introduction: The aims and the importance of the study: Regarding the importance of the object marker “râ” as one of the components of Persian sentences and its little investigation in aphasic Persian speakers, we decided to study its usage in the speech of aphasic patients with agrammatic Broca’s aphasia to know whether aphasic Persian speakers use “râ” in comparison to normal Persian speakers. The agrammatic aphasics are known for not using function words (like the object marker “râ”). Materials and Methods: In this experimental-descriptive study, two groups were employed. In the first group, six Persian children with Broca’s aphasia participated as the experimental group. The general linguistic capabilities of these patients were evaluated with the Persian aphasic test by speech therapy specialists. In the second group, six Persian-speaking normal persons participated as the control group. Two similar tests were administered to the aphasic and control groups, inspired by Caplan et al. 's test, to know whether they use “râ”. As there was a difference between the two groups, 1-way ANOVA was utilized to see if this difference was statistically significant. To analyze linguistic data, the approaches of Garman, Saffran, Kolk, Friedman, and Dolfić and Fabijanić were applied. Results: While the control group produced “râ” in all cases, the aphasic group never used it. Conclusion: It seems that using content words (like “nouns and verbs”) may be more vital than using function words (like “râ”).

A Hidden Markov Model for Morphology of Compound Roles in Persian Text Part of Tagging

Nowadays, data mining has become significant given the popularity of social networks as well as the emergence of abbreviated words, foreign terms and emoticons in the Persian language. Meanwhile, numerous studies have been conducted to identify the type of words. On the one hand, identifying the role of each word in a sentence is far more important than identifying the type of word in the sentence. On the other hand, the spelling-grammatical similarity of Persian to Arabic has enabled the newly proposed method in this paper to be applied to Arabic. In this paper, we adopted the Hidden Markov Model (MHM) and Tri-gram tagging with the aim of identifying the morphology of composition roles in Persian sentences. Then, a comparison was made between the technique developed in this paper and the Hidden Markov Model, Uni-gram and Bi-gram tagging. The proposed method supports the results obtained by the word role identification through "independent" and "dependent" roles and several factors that have a contribution to the words roles in sentences. In fact, the simulation results show that the average success rates of independent composition roles with MHM and Tri-gram tagging were 20.56% and 17.67% compared to Uni-gram and Bi-gram methods, respectively. Regarding the dependent composition role, there were improvements by 24.67% and 32.62%, respectively.

Comparative analysis Case (Haal) in Arabic syntax and semantic equivalents role of grammar in Persian

Comparative analysis Case (Haal) in Arabic syntax and semantic equivalents role of grammar in Persian

The Efficacy of Two Teaching Methods on Minimizing the Grammatical Errors in Translating Persian Sentences into English

This study deals with spotting the grammatical errors committed by the Iranian students majoring in English translation while translating the Persian sentences into English and investigating the effect of two teaching methods, including Grammar-Translation Method (GTM) and Communicative Language Teaching Method (CLT), on minimizing these errors. For this purpose, the grammatical errors in the translation of thirty students were identified. These errors were analyzed and classified according to Keshavarz’s model of error analysis. The students were divided into two groups; the first group received the learning materials based on GTM, and in the second group CLT was applied. Afterward, a test which included English sentences extracted from Modern English 1 and 2 was designed based on the errors taken from the corpus compiled by the students’ translations. Then the frequency of the errors in both groups were analyzed by SPSS software to determine the significance of using these methods on minimizing the grammatical errors made by the students in their translations into English. To determine the level of significance, the probability value was calculated for raw errors, GTM and CLT errors. The analysis of Pearson correlation showed that both methods had their significance; however, the communicative method proved to be slightly more effective than the other. Undoubtedly, this does not mean to underestimate the efficacy of grammar translation method since it seems that it plays a complementary role in teaching environment, and achieving better pedagogical results cannot be prescribed on a single method.

Рассмотрение побудительных предложений в персидском языке

The main question in this article is the consideration of sentences with incentive meaning in Persian. The article addresses the following issues: the concept of an incentive offer, means of expressing motivation in Persian and structure of incentive sentences in Persian. The novelty of the work is which examines incentive proposals in detail in Persian and describes the syntactic resources of named sentences in Persian and will find their possible equivalents in Russian. The object of work is syntactic and semantic properties of incentive sentences. The method of comparative analysis of examples and their translations is used to describe such sentences. As an example, the authors cite Persian sentences, including impulse meaning and this is the subject of research. The materials in our work are the works of Iranian and Russian linguists and grammarians working on this issue. The composition of the work is: introduction, main body, conclusion and bibliography. The article starts with an introduction and ends with a conclusion in which the authors summarize what have been said. The article is intended for students of the Persian language and for linguists who interested in the grammar of the Persian language.

An investigation into the use of Catford's shifts in translating short stories: translating english grammatical sentences into persian in focus

The present study investigated the use of Catford's shifts in the Persian translation. To achieve the research objectives, the researcher used a qualitative research design to examine Catford’s Translation Shifts category (1965). The research corpus was 50 English sentences of Introductory Steps to Understanding book and its Persian translation by 100 elementary EFL learners. The findings showed that shift structure, unit shift, class shift, and in-system shifts were used by learners. Also, the most shift used by learners was a structural shift. The findings achieved in this study indicated the applicability of shifts in translating grammatical sentences in Persian. Due to the complexity and variety of languages and their structure, the role of translation is very important. The researcher tried to prove that although education in the SL can be practical, finding equivalences for the grammatical sentences will complete it.

The effect of using the native language as a pedagogic intervention on Iranian EFL learners' complexity of English oral productions

The present study aims at investigating the effect of using the native language as a pedagogic intervention on the complexity of Iranian EFL learners' English oral productions. A sample of 39 male and female adult English learners of B1 and B2 CEFR proficiency levels was recruited to participate in this study. They were placed into two intact classes (i.e., as already determined by the institution’s authorities) and each class was randomly chosen to serve as either the experimental (EG) or the control (CG) group. Improving the learners’ speaking ability was the focus of both groups while only the EG was asked to orally produce the equivalents of Persian sentences presented to them. In order to measure the lexical and grammatical complexity of oral productions of the learners, two parallel speaking tests of IELTS 10, in the form of two oral interviews, were used as pre- and post-test oral interviews. A MANCOVA test was run to compare the performance of the two groups in terms of their lexical and grammatical complexity after the treatment. Results indicated that the EG's lexical and grammatical complexity improved as compared to the CG, and the improvement in both of these variables was statistically significant.

Application of Quantum Natural Language Processing for Language Translation

In this paper, we develop compositional vector-based semantics of positive transitive sentences using quantum natural language processing (Q-NLP) to compare the parametrized quantum circuits of two synonymous simple sentences in English and Persian. We propose a protocol based on quantum long short-term memory (Q-LSTM) for Q-NLP to perform various tasks in general but specifically for translating a sentence from English to Persian. Then, we generalize our method to use quantum circuits of sentences as an input for the Q-LSTM cell. This enables us to translate sentences in different languages. Our work paves the way toward representing quantum neural machine translation, which may demonstrate quadratic speedup and converge faster or reaches a better accuracy over classical methods.

Infinitive Interrogative Sentences in Russian and Persian: Modal Meanings of Potentiality and Efficiency

The article is a study of infinitive interrogative sentences bearing meanings of potentiality and efficiency in Russian and the means to render those in Persian. Both for Russian and Persian, such interrogative syntactic constructions and the relevant range of meanings are typical. As is known, in Russian infinitive is a verbal form though in a sentence it can combine the noun-and-verb functions, while in Persian, infinitive functions as a noun. As a rule, so-called Russian indefinite verbal form reflects various subjective and objective modal meanings, in particular, those of potentiality and efficiency which differs in Persian rather to reflect modal meanings of desirability, possibility, necessity, the must, inevitability, doubt, motive, etc. In relevant contexts the combination of modal meanings of desirability and possibility forms the potentiality meaning which is expressed by various linguistic means to form sentences: intonation, lexical and grammatical units, semantical components; other contexts of using such linguistic means to combine modal meanings of desirability and motive reveal the meaning of efficiency. The meanings themselves are not characteristic of Persian infinitive primarily due to their grammatical properties and belong to nouns therefore in Persian the mentioned above meanings and senses could be reflected by other linguistic means as well. The task of the study is to tackle the question of what are the means and manner they might make linguistic analogy to transmit semantics of potentiality and efficiency in Persian, while they are expressed in Russian infinitive interrogative sentences and rhetorical questions.The article treats infinitive interrogative sentences and rhetorical questions with infinitive as a predicate to render the semantics of potentiality and efficiency on the drama texts by M.Yu. Lermontov and A.P. Chekhov and the epic novel by A.N. Tolstoy. In course of comparative study, the translations into Persian of those texts were involved to find out similarities and differences of linguistic means used to reflect and reveal the semantics of infinitive interrogative sentences.

STRUKTUR KALIMAT BAHASA ARAB DAN BAHASA PERSIA

This paper describes the differences between Arabic and Persian sentence structure to help beginner Persian learners, especially those with Arabic language knowledge. This is a library research using linguistic approach and contrastive analysis to compare both sentence structre to predict difficulties that might appear in learning Persian. The differences of both languages, i.e. : 1) there ara two formulas of Arabic sentence structure: a) subject + predicate, and b) predicate + subject or predicate + subject + object. While in Persian the formula is subject + predicate or subject + object + predicate; 2) negative sentences of both languages use negative particle, but Arabic has various ones and most of them change the i’rab; 3) Arabic passive sentences follows the wazn فعل (past) and يفعل (present), while in Persian uses ending of شدن after the past verbs; 4) Arabic imperatives are formed by adding hamzah wasal replacing the huruf mudara’ah, while in Persian by adding بــ before the root of present verbs; 5) fi’l nahyi in Arabic are formed by adding lam an-nahiyah before majzum present verbs, while in Persian by adding نــ before root of present verbs.

Achieving the best defuzzifier in terminology of Persian sentences through classified fuzzy method

Fuzzy logic is a multi-valued concept, whose emergence in software sciences has eliminated 0 and 1 computations, putting them within an infinite space of [0,1]. This characteristic of fuzzy logic has resolved ambiguity in numerous previous problems. The sentence roles in Persian language were specified based on the fuzzy logic’s capability to resolve ambiguity. For that purpose, we first obtained the best classification for each defuzzifier, based on which a classified fuzzy was implemented. Nonetheless, the fuzzy system used in this research was classified based on statistical computations. To achieve the best classification, five defuzzification methods (Mean Of Max, Max Of Membership, Largest Of Max, Smallest Of Max, and Central Average) competed in 16 roles each in five classes (different matrices). Finally, Mean of Max with a success rate of 64% proved to be a defuzzifier delivering the best output among 5 different defuzzification methods.

A Combination of Frequent Pattern Mining and Graph Traversal Approaches for Aspect Elicitation in Customer Reviews

Due to the remarkable increase in e-commerce transactions, people try to have an appropriate choice of purchase through considering other people's reflected experience in product's or service's reviews. Automatic analysis of such corpus requires enhanced developed algorithms based on natural language processing and opinion mining. Moreover, the linguistic differences make extending existing algorithms from one language to another challenging and in some cases impossible. Opinion mining focuses on different subjects of review analysis such as spam detection, aspect elicitation and polarity allocation. In this article, we focus on detection of explicit aspect and propose a methodology to overcome some difficult and problematic aspect compounds in the form of multi- words format in Persian language. Our approach proposes the construction of a directed weighted graph (ADG structure) based on some yielded information from FP-Growth frequent pattern identification algorithm on our corpus of Persian sentence. Traversing some special paths within the ADG graph according to our developed rules could lead us to the extraction of problematic multi-word aspects. We utilize Neo4j NoSQL graph database environment and its Cypher query language in order to create the ADG graph and access the desired paths that reflects our developed rules on the ADG structure which lead us to extract the multi-word aspects. The evaluation of our methodology with the existing approaches on the issue of aspect derivation in Persian language including ELDA, SAM, an MMI-based and an LRT-based algorithms indicates the robustness of our approach.

Persian Verb and Sentence Production Protocol (PVSP) and its efficacy on Persian-speaking agrammatic non-fluent persons with aphasia

ABSTRACT Background: The semantic/syntactic representation of the verb is directly correspondent with the information required for generating well-constructed messages. Although various verb and sentence impairment therapies for persons with aphasia (PWA) are presented, there has been no published study of Persian verb treatment protocol for linguistic and cross-linguistic purposes. Aims: This study was aimed at introducing a verb treatment protocol founded upon the Persian syntax, teaching to link the key thematic information of verbs, and targeting treatment at the word and sentence level. Methods & Procedures: A single-subject study with multiple baselines design across participants was conducted. The efficacy of Persian Verb and Sentence Production Protocol (PVSP) on three agrammatic non-fluent patients was examined. Verb production skills at the word and sentence level were examined. The Mean Sentence Length (MSL) and sentence production across different tasks were measured at baseline and daily treatment probes. Outcome and Results: Three participants notably improved in verb percent production at the word level in experimental items (from 3.3% to 88% for participant 1, from 1.17% to 27.6% for participant 2 and from 3.75% to 58.6% for participant 3). Generalisation to control items were observed (from 10% to 81.2% for participant 1, from 24.9% to 52.98% for participant 2, from 19.7% to 60.89% for participant 3). All participants also enhanced in verb percent production at the sentence level in experimental items (from 13.3% to 67% for participant 1, from 16.6% to 40% for participant 2, and from 5.7% to 55% for participant 3). Generalisation to control items was noted (from 20% to 57% for participant 1, from 23.3% to 43.5% for participant 2, from 5% to 61% for participant 3). The results of the maintenance and follow-up phases were subsequently remarkable. Pre-post measures of MSL in connected speech (free speech) were improved outstandingly (from 1 to 4.3 for participant 1, from 3.5 to 8 for participant 2, from 0 to 5.2 for participant 3). Conclusions : PVSP seems to be beneficial to various degrees for Persian-speaking agrammatic non-fluent patients, enhancing their verb retrieval and sentence making skills.

English to Persian Translation Accuracy of “Rules and Regulations” of In-Ternational Banking System

This study comparatively analyzed the English to Persian translations of “rules and
 regulations” of the international banking system, at lexicon, phrase, sentence and
 paragraph levels to find out if the translations had been semantically comparable to
 their English versions. The translated texts, together with their English scource texts,
 were handed in to raters to assess and score semantically based on a three-point scale
 of “incorrect”, “fair” and “correct”. According to the results, the majority (96%) of lexicons
 had been translated correctly into Persian, while a small percentage of translated
 lexicons (3%) had a fair quality and an even smaller percentage (1%) were incorrectly
 translated. As for the phrases, most of them (86%) had been translated correctly into
 Persian, while a small percentage of translated phrases (8%) had a fair quality and an
 even smaller percentage (6%) had been incorrectly translated. Regarding sentences,
 44% of their translations had a good and 44% had fair quality, whereas some smaller
 numbers (12%) had been incorrectly translated. Compared to previous components, i.e.
 lexicon and phrases, the percentage of incorrect translations had noticeably increased
 at the level of sentence. Yet, the mean words in Persian sentences (i.e., 23.48) were
 rather similar to the source language sentences (i.e., 25.72). Regarding paragraphs, the
 majority (40%) of the translations had either a good or fair quality, while a significant
 number (20%) had been incorrectly translated. So, unlike the lexicons and phrases, a
 significant number of sentences and paragraphs had semantically been inaccurately
 translated. In addition, the mean number of words in Persian paragraphs (64.6) was
 considerably smaller than the mean words in English paragraphs (71.1).

Feature Engineering in Persian Dependency Parser

Dependency parser is one of the most important fundamental tools in the natural language processing, which extracts structure of sentences and determines the relations between words based on the dependency grammar. The dependency parser is proper for free order languages, such as Persian. In this paper, data-driven dependency parser has been developed with the help of phrase-structure parser for Persian. The defined feature space in each parser is one of the important factors in its success. Our goal is to generate and extract appropriate features to dependency parsing of Persian sentences. To achieve this goal, new semantic and syntactic features have been defined and added to the MSTParser by stacking method. Semantic features are obtained by using word clustering algorithms based on syntagmatic analysis and syntactic features are obtained by using the Persian phrase-structure parser and have been used as bit-string. Experiments have been done on the Persian Dependency Treebank (PerDT) and the Uppsala Persian Dependency Treebank (UPDT). The results indicate that the definition of new features improves the performance of the dependency parser for the Persian. The achieved unlabeled attachment score for PerDT and UPDT are 89.17% and 88.96% respectively.

Morphology of composition functions in persian sentences through a newly proposed classified fuzzy method and center of gravity defuzzification method

Morphology of composition functions in persian sentences through a newly proposed classified fuzzy method and center of gravity defuzzification method