Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

International Journal of Computer and Applications

is the conversion of a text from one script to another, and thus representing words from one language using the approximate phonetic or spelling equivalents of another language. Machine Transliteration has come out to be an emerging and a very important research area in the field of machine translation. Transliteration systems are very beneficial for removing the language and scriptural barriers. It has gained prime importance as a supporting tool for machine translation and cross-language information retrieval, especially when proper names and technical terms are involved. Various techniques are available for transliteration process. This paper is intended to give a brief overview of commonly used machine transliteration techniques.

/pdf/review-of-machine-transliteration-techniques-4kqwazto10.pdf

Review of Machine Transliteration Techniques

Machine Transliteration has come out to be an emerging and a very important research area in the field of machine translation. Transliteration basically aims to preserve the phonological structure of words. Proper transliteration of name entities plays a very significant role in improving the quality of machine translation. In this paper we are doing machine transliteration for English-Punjabi language pair using rule based approach. We have constructed some rules for syllabification. Syllabification is the process to extract or separate the syllable from the words. In this we are calculating the probabilities for name entities (Proper names and location). For those words which do not come under the category of name entities, separate probabilities are being calculated by using relative frequency through a statistical machine translation toolkit known as MOSES. Using these probabilities we are transliterating our input text from English to Punjabi.

Rule Based Transliteration Scheme for English to Punjabi

Language transliteration is one of the important ar eas in NLP. Transliteration is very useful for conv erting the named entities (NEs) written in one script to a nother script in NLP applications like Cross Lingua l Information Retrieval (CLIR), Multilingual Voice Ch at Applications and Real Time Machine Translation (MT). The most important requirement of Translitera tion system is to preserve the phonetic properties of source language after the transliteration in target language. In this paper, we have proposed the name d entity transliteration for Hindi to English and Mar athi to English language pairs using Support Vector Machine (SVM). In the proposed approach, the source named entity is segmented into transliteration uni ts; hence transliteration problem can be viewed as sequ ence labeling problem. The classification of phonet ic units is done by using the polynomial kernel functi on of Support Vector Machine (SVM). Proposed approach uses phonetic of the source language and nas two features for transliteration.

/pdf/hindi-and-marathi-to-english-machine-transliteration-using-wa50rfwcth.pdf

Hindi and marathi to english machine transliteration using svm

Machine transliteration has received significant research attention in recent years. In most cases, the source language has been English and the target language is an Asian language. This paper focuses on Hindi to English machine transliteration of Indian named entities such as proper nouns, place names and organization names using conditional random fields (CRF). Hindi is the national language of the India and spoken by more than 500 millions Indian. Hindi is the world‟s fourth most commonly used language after Chinese, English and Spanish. This system takes Indian place name as an input in Hindi language using Devanagari script and transliterates it into English. The input to the system is provided in the form of syllabification in order to apply the n-gram techniques. As more than 50% named entities are formed as a combination of two and three syllabic units, the ngram approach with unigrams, bigrams and trigrams of Hindi are used to train the corpus. The system provides the satisfactory performance for trigrams as compared to unigrams and bigrams. General Terms Machine Transliteration

/pdf/hindi-to-english-machine-transliteration-of-named-entities-3g4zwfuxv6.pdf

Hindi to English Machine Transliteration of Named Entities using Conditional Random Fields

An important aid in analysis & display of speech is sound spectrogram. It represents time-frequency-intensity display of short time spectrum. The quality of speech can be studied by visual inspection of spectrogram. This is one of the important applications of spectrogram in speech processing especially in speech enhancement. Another application of spectrogram is in isolating voiced and unvoiced regions. But to conclude from visual inspection the clarity of spectrogram is also important. Before plotting the spectrogram the time domain speech signal is converted to frequency domain. The transform domain used plays vital role in resolution of spectrogram. Generally Fast Fourier Transform is used to convert the time domain signal into frequency domain signal. This paper discusses the effect of using different transform for converting the time domain speech signal into frequency domain before plotting spectrogram. . It is observed that resolution of speech spectrogram is transform dependent.

/pdf/multi-resolution-speech-spectrogram-53ej9kkiu6.pdf

Multi-Resolution Speech Spectrogram

During last two decades, most of the named entity (NE) machine transliteration work in India has been carried out by using English as a source language and Indian languages as the target languages using grapheme model with statistical probability approaches and classification tools. It is evident that less amount of work has been carried out for Indian languages to English machine transliteration.

Hindi and Marathi to English NE Transliteration Tool using Phonology and Stress Analysis

Machine transliteration has received significant research attention in last two decades. It is observed that Hindi to English and Marathi to English named entity machine transliteration is comparably less studied. Currently, research work in this domain is carried out by using grapheme based statistical approaches. But, to achieve better accuracy for the transliteration, an adequate bilingual text corpus is a mandatory requirement for statistical approaches. This paper focuses on Hindi to English and Marathi to English direct machine transliteration of Indian-origin named entities such as proper names, place names and organization names. Proposed phonetic based statistical approach uses phoneme and named entity length as features for supervised learning and transliterates them in English using full consonant based phonetic scheme without support of corpus. This system takes Indian origin named entities as an input in Hindi and Marathi using Devanagari script and transliterates it into English by using only two weights.

Optimizing Transliteration for Hindi/Marathi to English Using only Two Weights

Almost all transactions ranging from various domains such as travel, shopping, insurance, entertainment, hotels, appointments etc. are available through Internet based applications. Needless to say, all these applications require the knowledge of English. As Internet users are growing day by day, it is logical to say that, there is a great demand to develop tools and applications to support Indian languages for them. The solution to provide local language support in the web based commercial applications is Machine Translation which can be used to translate static labels on web form and Machine Transliteration to transliterate dynamic user inputs from local language into the default language English. It is challenging to transliterate names and technical terms occurring in the user input across languages with different alphabets and sound inventories. This paper focuses important issues which frequently occur in Hindi to English and Marathi to English named entities machine transliteration.

/pdf/issues-in-hindi-to-english-and-marathi-to-english-machine-459hwiv217.pdf

Shantanu K. Dixit

Papers

Hindi to English Machine Transliteration of Named Entities using Conditional Random Fields

Multi-Resolution Speech Spectrogram

Hindi and Marathi to English NE Transliteration Tool using Phonology and Stress Analysis

Optimizing Transliteration for Hindi/Marathi to English Using only Two Weights

Issues in Hindi to English and Marathi to English Machine Transliteration of Named Entities