Hindi Text Research Articles

Testing and Results of Hindi-Dogri Machine Translation System

The Hindi-Dogri Machine Translation System is based on the direct approach of Machine Translation (MT). It translates Hindi text into Dogri. This paper presents in brief the development of the system and details of testing and the evaluation of the results of this system.

Determination of the Distribution of Sentence Length Frequencies for Hindi Language Texts and Utilization of Sentence Length Frequency Profiles for Authorship Attribution

The present paper examines the application of sentence length frequency profiling for the characterization of the writing styles of different authors in authorship attribution. The frequency distribution of the sentence lengths is first determined for various Hindi texts, and the parameters of the derived distributions associated with the selected statistical features calculated on the basis of frequency profile are then used for description of 77 texts written by four authors.

Recognition of Handwritten Hindi Text Using Middle Region of the Words

Offline handwritten Hindi text recognition is a very tedious task. In this paper, a novel method using middle region of the words for recognition of handwritten Hindi text is proposed. A segmentation based approach is used for recognition. Although many efforts have been made to recognize isolated characters and words, a little work has been done to recognize the offline handwritten Hindi text by segmenting the sentences into lines and lines into words. The uniqueness of this approach lies in the fact that many of the commonly used words can be recognized by matching all the characters in the middle zone even by ignoring the upper modifiers, lower modifiers and half characters. Another advantage is that it is not word specific i.e. any number of words can be added to the list to be recognized. Topological features are used for recognition of characters and efforts are made to correctly extract the features. Results obtained with the proposed technique are very challenging.

A BIDIRECTIONAL TEXT TRANSCRIPTION OF BRAILLE FOR ODIA, HINDI, TELUGU AND ENGLISH VIA IMAGE PROCESSING ON FPGA

Communication gap establishes an aura of unwillingness of understanding the factor behind. Basically, this is one of the common agenda for the visually challenged people. In order to bridge this gap, a proper platform of learning for both the mass and the visually challenged for any native language is emphasized in this paper through Braille pattern. Braille, a code, well known to visually challenged as their mode of communication is now converted into normal text in Odia, Hindi, Telugu and English languages using Image segmentation as the base criteria with MATLAB as its simulation field so that every person can be able to easily decode the information being conveyed by these people. The algorithm makes the best use of segmentation, histogram analysis, pattern recognition, letter arrays, data base generation with testing in software and dumping in using Spartan 3e FPGA kit. This paper also elaborates on the reverse conversion of native languages and English to Braille making the paper to be more compatible. The processing speed with efficiency and accuracy defines the effective features of this paper as a successful approach in both software and hardware.

Segmentation of touching modifiers and consonants in middle region of handwritten Hindi text

Character segmentation is a major problem in any text recognition system. The most common problem in the recognition of handwritten text is the presence of touching of left modifier with the consonant in the middle region of the word. In Optical Character Recognition (OCR) system, the recognition rate decreases due to the presence of touching characters. The determination of presence of touching characters is a very tedious task. Based on the structural properties of the text, a new algorithm is proposed to segment left modifier from the consonant in the middle region of the word. The results obtained with the proposed algorithm are very challenging. The problem of over segmentation that occurs in the segmentation of touching left modifier from consonant in the middle region, are also explained.

A Novel Approach for Hindi Text Description to Speech and Expressive Speech Synthesis

A Novel Approach for Hindi Text Description to Speech and Expressive Speech Synthesis

Automation and Validation of Annotation for Hindi Anaphora Resolution

The process of labelling any language genre by which one can extract useful information is called annotation. This provides syntactic information about a word or a word phrase. In this paper, an effort has been made to provide the algorithm for semiautomatic annotation for Hindi text to cater anaphora resolution only. The study was conducted on twelve files of Ranchi Express available in EMILLE corpus. The corpus is originally tagged for demonstrative pronouns. The detection of the pronouns is supported by the incorporation of seven tags. However the semantic interpretation of the demonstrative pronoun is not supported in the original corpus. In this paper an effort has been made to automate the process of tagging as well as the handling of semantic information through addition tags. It was conducted on 1485 demonstrative pronouns. The average accuracy of precision, recall and F measure is 74, 71 and 72 respectively.

Monolingual Information Retrieval using Terrier: FIRE 2010 Experiments Based on N-gram Indexing

Abstract N-gram based indexing technique has been proved as a useful technique for efficient document retrieval. We applied the n-gram approach and performed experiments in Hindi language text collections. The experiments are performed on the dataset of FIRE 2010 Hindi text collections. We used the Terrier open search engine for experimental purpose. Our experiments state that 4-gram gives the best results among all n-grams of different length. The results show an increase in value of mean average precision.

A Novel Segmentation Methodology for Cursive Handwritten Documents

ABSTRACTSegmentation in handwritten documents is a very challenging task because in handwritten documents curved text lines and non-uniform skews appear frequently. Basically segmentation means to analyse the document image into its sub component as text line, words, or ligatures and finally character. Various handwritten text recognition systems take segmented character as input to recognize them and some recognition systems which are based on holistic approaches use word level segmentation. In this paper, we have implemented a complete framework of segmentation for handwritten documents with various languages. A novel connectivity strength parameter is used for deciding the groups of the components which belong to the same line. Over-segmentation is also removed with the help of depth first search approach and iterative use of the connectivity strength function. We have implemented and tested this approach with English, Hindi, and Urdu text images taken from benchmark database and find that it is a language adaptive approach which provides encouraging results. The average accuracy of the proposed technique is .

A new approach for unsupervised word sense disambiguation in Hindi language using graph connectivity measures

Word sense disambiguation (WSD) is an important task in computational linguistics as it is essential for many language understanding applications. In this paper, we propose a graph-based unsupervised WSD method for Hindi text which disambiguates multiple ambiguous words present in the sentence simultaneously. In our approach, we first construct the semantic graph for each interpretation of the given sentence by establishing semantic relations between the pair of words present in the sentence. We use Hindi WordNet to establish semantic relations between the pair of words and then we construct the graph. We find the cost of spanning tree corresponding to each semantic graph and the interpretation for which spanning tree has the minimum cost is identified. This interpretation is considered as the resulting interpretation. Our approach also considers all open class words unlike the previous approaches which focus only on noun.

An Unit Selection based Hindi Text To Speech Synthesis System Using Syllable as a Basic Unit

An Unit Selection based Hindi Text To Speech Synthesis System Using Syllable as a Basic Unit

Conversion of Braille to Text in English, Hindi and Tamil Languages

The Braille system has been used by the visually impaired for reading and writing. Due to limited availability of the Braille text books an efficient usage of the books becomes a necessity. This paper proposes a method to convert a scanned Braille document to text which can be read out to many through the computer. The Braille documents are pre processed to enhance the dots and reduce the noise. The Braille cells are segmented and the dots from each cell is extracted and converted in to a number sequence. These are mapped to the appropriate alphabets of the language. The converted text is spoken out through a speech synthesizer. The paper also provides a mechanism to type the Braille characters through the number pad of the keyboard. The typed Braille character is mapped to the alphabet and spoken out. The Braille cell has a standard representation but the mapping differs for each language. In this paper mapping of English, Hindi and Tamil are considered.

Optical Character Recognition for Hindi Language Using a Neural-network Approach

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the documents textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.

Tyrants, Villains, Belles and Saints: Stereotyped Portraits of Muslim Characters in Early Hindi Novels

This paper seeks to look at the prose fiction and essays published in Hindi in North India in the second half of the 19th century and the early 20th century from the viewpoint of contemporary religious controversies and communal developments. It suggests a closer look at a few representative Hindi texts by leading Hindi authors (Bharatendu Harishchandra, Devakinandan Khatri, Kishorilal Gosvami). These littérateurs made quite special efforts to point out the religious backgrounds of the fictional characters in their works and, thus, to create a general awareness about the roles of Hindus and Muslims, both in contemporary Indian society and in the historical perspective. Being rather assertive Hindus themselves, they not only pointed out certain negative sides of “the other” community but, also—as in the case of Gosvami—severely criticized the erstwhile Islamic rulers of India. Why was the task of portraying Muslims so crucial for Hindi literature, especially at the time of serious socio-political and religious turbulences? How does this interest go along with the identity-forming agenda of the epoch? What are the ways to structure and generalize the relevant attitudes of the authors and to explain them from the point of view of the historical development of the post-Mutiny society in North India? These are some of the questions to be approached in this paper.

Analysis for the significance of statistical word-length features in genre discrimination of Hindi texts

In automatic text categorization procedure, quantifiable features’ information is extracted from a text and on the basis of the information the text is sorted as a category. This information consists of values of set of one or more measurements, where the measurements can be considered as frequencies or function of frequencies of linguistic elements. In the process of text classification and genre discrimination, the role of the systematic study of word length and the analyses of word-length statistics of different texts has been established by researchers for various languages. In the present paper an attempt has been made to test the contribution of quantitative word length features in classification of written texts of Hindi Language by extracting quantitative measures with the help of word length profiles and frequencies.

Prashnottar: A Hindi Question Answering System

This paper presents an approach to extract answers from Hindi text for a given question. It is based on understanding the meaning of the given question and expressing them in query logic language. The Hindi text is analyzed to understand the semantic of each sentence and relevant answer is extracted for the given question. The answers are extracted for the questions of type when, where, how many and what time. The experimental results are satisfactory.

Discrimination Of English To Other Indian Languages (Kannada And Hindi) For Ocr System

India is a multilingual multi-script country. In every state of India there are two languages one is state local language and the other is English. For example in Andhra Pradesh, a state in India, the document may contain text words in English and Telugu script. For Optical Character Recognition (OCR) of such a bilingual document, it is necessary to identify the script before feeding the text words to the OCRs of individual scripts. In this paper, we are introducing a simple and efficient technique of script identification for Kannada, English and Hindi text words of a printed document. The proposed approach is based on the horizontal and vertical projection profile for the discrimination of the three scripts. The feature extraction is done based on the horizontal projection profile of each text words. We analysed 700 different words of Kannada, English and Hindi in order to extract the discrimination features and for the development of knowledge base. We use the horizontal projection profile of each text word and based on the horizontal projection profile we extract the appropriate features. The proposed system is tested on 100 different document images containing more than 1000 text words of each script and a classification rate of 98.25%, 99.25% and 98.87% is achieved for Kannada, English and Hindi respectively.

Portrait of a Raja in a Badshah’s World: Amrit Rai’s Biography of Man Singh (1585)

AbstractA wealth of Old Hindi texts in the Rajasthani and Brajbhasha dialects survives from the early modern period, but they remain an underused archive of Mughal history. TheMāncarit(“Biography of Man Singh,” 1585) of Amrit Rai, one of the earliest known examples of Rajput literature about a Mughalmanṣabdār, provides fascinating perspectives on Mughal power, as seen from the perspective of the court of Man Singh Kachhwaha, one of the leading regional kings of Akbar’s day. Amrit Rai was as much a poet as an historian, which makes theMāncaritand the many Rajput texts like it challenging to interpret, but the possibility of gaining alternative perspectives on Mughal state formation makes such a hermeneutic enterprise essential.

The Hazards in Segmentation of Handwritten Hindi Text

Optical Character Recognition (OCR) is a process to recognize the handwritten or printed scanned text with the help of a computer. Segmentation is very important stage of any text recognition system. The problems in segmentation can lead to decrease in segmentation rate and hence recognition rate. A good segmentation technique can improve the recognition rate. This paper deals with the hazards that occur in segmentation of handwritten Hindi text. We also explained the main reasons for some of these problems.

The Influence of English on the History of Hindi Relative Clauses

Abstract The influence of Hindi on English has been well documented; however, little has been said about the influence of English on the structure of Hindi. In this paper I provide evidence that Hindi “embedded” (i.e. post-nominal) relative clauses result from English influence. Hindi originally had Relative-Correlative (RC-CC) constructions that could adjoin to the left or the right of the main clause. Since evidence from early Hindi is limited, I draw on Awadhi and Braj Bhakha to provide greater time depth for the earlier history of Hindi. In addition I examine early 19 th century grammars and texts. None of these provide unambiguous evidence for embedded relative clauses. By contrast, late 19 th century and early 20 th century Hindi texts translated from English exhibit many instances of central embedded relative clauses (besides the old adjoined relativecorrelatives), thus supporting the argument that Hindi embedded relative clauses result from the influence of English. I argue that what may have helped in this developed is the occasional occurrence of potentially ambiguous structures in earlier Hindi, which could be reinterpreted as involving embedding, rather than a relative-correlative construction with deleted correlative pronoun.