Figure - uploaded by Prateek Agrawal
Content may be subject to copyright.
Similar publications
The teaching evaluation module is an important guarantee of teaching effectiveness, and as an important part of the multimedia teaching system, it needs special attention. This paper combines artificial intelligence and multimedia teaching effect evaluation, proposes a foreign language translation multimedia teaching effect evaluation model based o...
Introduction
Causes of deaths often go unrecorded in lower income countries, yet this information is critical. Verbal autopsy is a questionnaire interview with a family member or caregiver to elicit the symptoms and circumstances preceding a death and assign a probable cause. The social and cultural aspects of verbal autopsy have gotten less attent...
In this paper, we introduce MedLane -- a new human-annotated Medical Language translation dataset, to align professional medical sentences with layperson-understandable expressions. The dataset contains 12,801 training samples, 1,015 validation samples, and 1,016 testing samples. We then evaluate one naive and six deep learning-based approaches on...
To solve the problem that English and Chinese are different in many aspects and often misunderstood in communication, the author proposes a machine foreign language translation evaluation system based on Internet of Things automation technology. By designing an interactive English-Chinese machine translation A system based on the B/S framework can...
Citations
... An estimated two billion people, or approximately a third of the world's population, utilize English now. [1] Because English is a language that is widely used throughout the world, the majority of official correspondence and papers are written in it. English seems to be the language of coding in the realm of computer programming. ...
... They applied this to transliterate personal names over LDC dataset. Jain and Agarwal (2017) [6] explained two methods of developing transliteration tool that converts English text to Sanskrit. First approach is by using a physical keyboard for the purpose while second approach involves the use of a virtual keyboard. ...
In this paper, we have shown a method of improving the quality of neural machine translation by translating/transliterating name entities as a preprocessing step. Through experiments we have shown the performance gain of our system. For evaluation we considered three types of name entities viz person names, location names and organization names. The system was able to correctly translate mostly all the name entities. For person names the accuracy was 99.86%, for location names the accuracy was 99.63% and for organization names the accuracy was 99.05%. Overall, the accuracy of the system was 99.52%
... Transliteration is a process to convert any script written in one language into another language [49,51,53,87]. In the proposed work, a tool is developed to transliterate English script into equivalent Sanskrit language [89,90]. ...
Sanskrit is claimed as the second oldest language of the world and in ancient days, Sanskrit was considered as mother tongue in the larger part of India. But now, it is struggling for its acceptance in common people. Objective of the work is to develop algorithms for stemming of Sanskrit words, implement semantic analysis, discourse integration and pragmatic analysis. Another objective is to implement a translation tool that is able to translate Sanskrit text into Hindi. Method: Rule based method is used to prepare the corpora and implement the proposed work. An interface is made available through which step by step translation can be seen and understood.
This tool will be helpful to those who are familiar in Hindi language but unable to learn Sanskrit due to the scarcity of language experts. More than 60 Million people from India and abroad who are active Hindi users and work on computer, can get themselves connected with Sanskrit and also can learn the Sanskrit fundamentals by self
... Especially, sequence to sequence character mapping technique is mostly implemented in the tasks of the machine learning-based transliteration. The transliteration method has been proposed for linguistics [56] of Sanskrit that translates it into English. Furthermore, the attention-based machine learning approach is utilized to translates the English language into Persian. ...
Urdu language written in English alphabets for communication is known as Roman Urdu. In pronunciation, both are the same but different in spelling and have different shapes of the alphabet. A survey acknowledges that 300 million people are speaking Urdu and about 11 million speakers in Pakistan from which maximum users prefer Roman Urdu for the textual communication. Today most of the modern technologies like computers and mobile phones using English script, due to this local Urdu user has to use English letters to type Urdu script that is Roman Urdu. In this research, Roman Urdu to Urdu Translator (RUTUT) is proposed that consists of preprocessing methods, rule-based character substitution and Unicode based character mapping techniques. It can transliterate the messages or descriptions from the Roman Urdu script to Urdu script which may help the Urdu speaker to elaborate their message in efficient manners. The focus of this research is to analyze the issues related to the Roman Urdu script to Urdu script transliteration and develop a translator based on the concepts of transliteration. This research analyzed Roman Urdu data and identified different rules-based character substitution techniques that transform the Roman Urdu into Urdu script at fundamental levels. This research is carried out using a python programming language in programming tool Anaconda in Jupiter notebook and user-friendly Graphical User Interface (GUI) created by using Tkinter library. To evaluate the RUTUT, different translational tests are performed and compare those results with famous Google online translator and ijunoon online transliteration. The analyses of results show that the proposed RUTUT approach translates accurately than Google online translator and ijunoon online transliteration.
... A tool is implemented by [26] to paraphrase the Hindi sentences by using active-passive voice rules and synonym-antonym replacement methods. An algorithm for the transliteration from English to Sanskrit text is presented providing 100% accuracy [12]. The process performs the mapping by making use of Hindi Unicode characters. ...
... In other words, the phonetic similarity of the two languages is taken into account for transliteration. We have used a set of rules to perform this mapping from Latin to Devanagari script giving a 100% accuracy based on [12]. ...
Machine Translation is an area of Natural Language Processing which can replace the laborious task of manual translation. Sanskrit language is among the ancient Indo-Aryan languages. There are numerous works of art and literature in Sanskrit. It has also been a medium for creating treatise of philosophical work as well as works on logic, astronomy and mathematics. On the other hand, Hindi is the most prominent language of India. Moreover,it is among the most widely spoken languages across the world. This paper is an effort to bridge the language barrier between Hindi and Sanskrit language such that any text in Hindi can be translated to Sanskrit. The technique used for achieving the aforesaid objective is rule-based machine translation. The salient linguistic features of the two languages are used to perform the translation. The results are produced in the form of two confusion matrices wherein a total of 50 random sentences and 100 tokens (Hindi words or phrases) were taken for system evaluation. The semantic evaluation of 100 tokens produce an accuracy of 94% while the pragmatic analysis of 50 sentences produce an accuracy of around 86%. Hence, the proposed system can be used to understand the whole translation process and can further be employed as a tool for learning as well as teaching. Further, this application can be embedded in local communication based assisting Internet of Things (IoT) devices like Alexa or Google Assistant.
... As per Indian Censes 2001 report, there were approximately 42 million Indians having Hindi as their first language [2]. Recent research has shown a lot of automatic work done text written in English language [3][4][5], title generation for articles [6][7][8]10] but the scenario for Hindi language is not appreciable. According to English language there is a categorization of alphabets into two parts: 21 Consonants and 05 Vowels. ...
This paper explains 02 methods to generate the headings or titles of Hindi stories. We have developed a title generation tool that takes a story (without any length limit) as input and suggests some titles based on (i) keyword matching and (ii) proverb sensing. In keyword matching approach, it deals with database which includes keywords associated with each proverb. The corpora contain 35135 Hindi words which are classified separately among Nouns, Adjectives, Verbs, Adverbs, and Quantifiers etc. Both algorithms for generating the titles are described in this paper. RD Parts Of Speech Tagger (an open source POS tagger) has been referred and some tagged word enhancements have been done in the POS tagger corpora to improve the efficiency. Our proposed tool was tested on randomly selected 40 common Hindi short stories and the system produces more than 90% relevant (The results were verified and validated by 02 School Hindi Teachers having more than 10 years experience (St. Soldiers Public School, Jalandhar, Punjab, India)) titles using proverb sensing method. This application can be recommended as an informative tool for school going students as well as for school Hindi teachers as an effective pedagogy tool for teaching and learning. It can also be helpful to Hindi newspaper editors, blog writers and technical writers in finding the tentative titles for their articles.
... For example: अं बानी अमीर ऱड़का है // Hindi Sentence अं बानी/NNP अमीर/JJ ऱड़का/NN है /VM // Sentence after POS tagging In our proposed system, the user can input the text in any of the following three ways: 1) User can input the text in Hindi by using virtual keyboard [13] provided in our proposed tool interface. The user needs to click on the Hindi alphabet keys given on virtual keyboard and type the text accordingly. ...
... Specifically, sequence to sequence has been applied to the task of machine transliteration too. [23] transliterates from Sanskrit to English while [12] transliterates from English to Persian using attention based approach. Major challenge of transliteration is addressing the difference in syntax, semantics and morphology between the source language and the target language. ...
Neural Machine Translation models have replaced the conventional phrase based statistical translation methods since the former takes a generic, scalable, data-driven approach rather than relying on manual, hand-crafted features. The neural machine translation system is based on one neural network that is composed of two parts, one that is responsible for input language sentence and other part that handles the desired output language sentence. This model based on encoder-decoder architecture also takes as input the distributed representations of the source language which enriches the learnt dependencies and gives a warm start to the network. In this work, we transform Roman-Urdu to Urdu transliteration into sequence to sequence learning problem. To this end, we make the following contributions. We create the first ever parallel corpora of Roman-Urdu to Urdu, create the first ever distributed representation of Roman-Urdu and present the first neural machine translation model that transliterates text from Roman-Urdu to Urdu language. Our model has achieved the state-of-the-art results using BLEU as the evaluation metric. Precisely, our model is able to correctly predict sentences up to length 10 while achieving BLEU score of 48.6 on the test set. We are hopeful that our model and our results shall serve as the baseline for further work in the domain of neural machine translation for Roman-Urdu to Urdu using distributed representation.
... Specifically, sequence to sequence has been applied to the task of machine transliteration too. [23] transliterates from Sanskrit to English while [12] transliterates from English to Persian using attention based approach. Major challenge of transliteration is addressing the difference in syntax, semantics and morphology between the source language and the target language. ...
The main aim of this paper is to develop a language model for translating the English language to Garhwali, a language spoken in the Garhwal region of Uttarakhand, India. The model will use state-of-the-art natural language processing techniques, including machine learning and neural networks, to enable accurate and efficient translation of English sentences into Garhwali and vice versa. The model will be trained on a large dataset of parallel English-Garhwali text to ensure high accuracy and fluency of the translations. The successful development of this language model will help bridge the language barrier between English speakers and Garhwali speakers, facilitate communication and exchange of ideas, and promote cultural exchange and understanding. Local language conversion system can help to improve the user experience by providing content in the language that the user is most comfortable with. It can help to reduce confusion and frustration, and make the user experience more enjoyable. Keywords: Statistical Machine Translation, Mathematical model, English-Garhwali, Evaluation.
