INTRODUCTION
1.1 Overview
Ambiguity is bound to occur in human languages. It is so because large number of the words in any language having more than one meanings. The property in natural languages to have multiple meanings is known as polysemy. For example in English, “pen” can be a writing instrument or an animal enclosure. Similarly in Hindi “हार” can be “माला” or “पराजय”. Sometimes two completely different words are spelled the same is called as homonymy. For example, “can”, can be used as verb or as container. Distinction between polysemy & homonymy is not always clear. Hence it become necessary to identify the correct sense of a word and the correct sense of an ambiguous word should be selected based on the context where it occurs.
Thus the problem of word sense disambiguation (WSD) is defined as the task of automatically assigning the most appropriate meaning to an ambiguous word depending on the given context. WSD is considered as an open and AI-hard problem in natural language processing (NLP) and is used as in between step for many applications like Machine Translation (MT), Information Retrieval (IR), Question Answering
…show more content…
To resolve the ambiguity of a word, firstly we need to determine the different senses of the each word and then we have to assign the appropriate meaning or sense to each occurrence of a word in a sentence. Many studies on word sense disambiguation have proposed to resolve the ambiguity of a sentence. Indian language Hindi is supposed to be one of the morphologically rich languages. Hence the main focus of this work is to resolve the ambiguity of a word from Hindi sentence by using unsupervised graph-based algorithm for word sense disambiguation. Graph-based method gives the most “important node” among the set of graph nodes with the help of graph centrality algorithms and similarity measures which are representing its
First, a brief background in the three dimensions of language discussed throughout this paper. The functional, semantic, or thematic dimensions of language as previously mentioned are often used in parallel with each other. Due, to this fact it is important to be able to identify them as they take place and differentiate between these dimensions i...
Desperately, people turn to use some words loosely. Take note when you are talking with people and you hear them using reminiscent words such as smart, pretty, beautiful, intelligent, or love in sentences. For the purpose of this paper, I will focus on the word Love due to the fact that love turns to apply in all the other words that people use loosely. There are numerous definitions of the word love, but I will pick one from Dictionary.com that states: A feeling of warm personal attachment or deep affection, as for a parent, child, or friend. It’s obvious that a large majority of people are content when they hear the phrase “I Love You”. On the other hand, when a person says I love you, it can be misinterpreted effortlessly. One question I
In “Defending Against the Indefensible” by Neil Postman, he proposes a different way of viewing the English language. He says that our civilization is being manipulated by the ambiguity in English, and students are most easily affected by the school environment. Thus, he proposes seven key ideas that students should remember in order to avoid the dangers and loopholes that twist the original meaning of statements.
A field bound to a CV is constrained to contain only values from that CV
One word can have multiple meanings. For instance, the word “gun” can signify protection or even a threat. For few, if someone has a gun they can view it
The first IR system was built which used indexes and concordances. When the first large scale information systems were developed, computers can search indexes must better than human, which required more detailed indexing. However, indexing could also become too expensive and time consuming. Therefore, the idea of free-text searching is initiated, which eliminates the need for manual indexing. Objections pointed out that selecting the right words might not be the correct label for a given subject. One solution is official vocabularies. The idea of recall and precision also came out as methods for evaluating information retrieval systems, and they showed that free-text indexing was as effective as manual indexing and much cheaper. New information retrieval techniques such as relevance feedback, multi-lingual retrieval were invented. The 1960s also was the start of research into natural language question-answering, and researchers began building systems ...
This paper will explain the process we, as humans usually follow to understand a certain text or utterance. This explanation would be achieved through the analysis of two journal articles from semantics and pragmatics perspective, taking into account a range of techniques associated with each of the two concepts including:
There are many types of polysemy, some of which view the polysemous word as having primary meaning and secondary meaning, i.e. the meaning which a word refers to in the external world and what it refers to in the second understanding of the word. Other types of polysemy can be dealt with lexically, i.e. these types view the literal meaning and the figurative meaning of the polysemous word. Accordingly, there is referential polysemy, and lexical polysemy which is subdivided into linear polysemy and subsuming polysemy.
Lexicon Based techniques work with respect to a suspicion that the aggregate extremity of a report or sentence is the total of polarities of the individual words or phrases.
... applied on different Domain data sets and sub level data sets. The data sets are applied on Maximum entropy, Support Vector Machine Method, Multinomial naïve bayes algorithms, I got 60-70% of accuracy. The above is also applied for the Unigrams of Maximum entropy, Support Vector Machine Method, Multinomial naïve bayes algorithms achieved an accuracy of 65-75%. Applied the same data on proposed lexicon Based Semantic Orientation Analysis Algorithm, we received better accuracy of 85%. In subjective Feature Relation Networks Chi-square model using n-grams, POS tagging by applying linguistic rules performed with highest accuracy of 80% to 93% significantly better than traditional naïve bayes with unigram model. The after applying proposed model on different sets the results are validated with test data and proved our methods are more accurate than the other methods.
What is a word? How the translator deals with this gap? What influences his choices? These are few of the question we will try to explain in this paper. We will pay a particular attention to the cultural differences and the translational gaps raised from it. In my opinion the non-equivalence in translation is due above all by the cultural barriers that influence our lifes.
The field of Computational Linguistics is relatively new; however, it contains several sub-areas reflecting practical applications in the field. Machine (or Automatic) Translation (MT) is one of the main components of Computational Linguistics (CL). It can be considered as an independent subject because people who work in this domain are not necessarily experts in the other domains of CL. However, what connects them is the fact that all of these subjects use computers as a tool to deal with human language. Therefore, some people call it Natural Language Processing (NLP). This paper tries to highlight MT as an essential sub-area of CL. The types and approaches of MT will be considered, and limitations discussed.
Literature is always interactive. Thus, not only can the thoughts of people who write/translate it, but also those of people who read it can interfere. Different cultural backgrounds, growth environment etc. of different people will be the factors that can disrupt the intact understanding of the readers. Furthermore, the ‘taste’ of a word also can be related to the perception
Language is a means of human communication whether verbally or nonverbally. In everyday life we use language to express our thoughts, feelings ,attitudes,etc.A great amount of social interactions takes place every day over the telephone ,by online chats, face –to face interaction or at workplaces .We use language of different forms for different functions as in to inform, question , and sometimes to strengthen social relationships or just to keep the social wheels turning smoothly. Moreover, understanding one's own language and even other cultures’ language is important to arrive at a successful and effective communication with others . The study of language can be undertaken in various ways .Semantics and pragmatics are two branches of linguistics which are concerned with the study of meaning.
C. Bizer, J. Lehmann, G. Kobilarov, S. Auer, C. Becker, R. Cyganiak, and S. Hellmann. Dbpedia – a crystallization point for the web of data. Web Semantics: Science, Services and Agents on the WWW, September 2009.