Publications

Abstract : Machine Translation is an application of Computational Linguistics which is primarily concerned with designing software that translates a text from one natural language to another natural language. This is a complex process since processing of natural language requires linguistic knowledge of the source language and the target language from word level to sentence level and their contrasting features at all these levels. This is a difficult task, because all natural languages are highly expressive. That means a single word can have many meanings and many words can have a single meaning. So finding equivalences between the source and the target languages is a challenging task. The linguistic units like the prepositions and auxiliary verbs are polysemous. The English auxiliary verbs like ‘be’, ‘have’ and ‘do’ and the other semi-auxiliary verbs like ‘get’, ‘let’, ‘make’ and ‘help’, etc., are expressive. They act as helping verbs or verbs functioning as tense, aspect and modality markers or copulative verbs or causative verbs. The syntax and semantics of a sentence is based on the main verb. The concept of causation is part of the semantics of the verb itself. Causation means that one named entity (NP1) makes somebody else do something or causes another named entity (NP2) to be in a certain state. Semantically causative verbs refer to a causative situation which has two components: (a) the causing situation or the antecedent, (b) the caused situation or the consequent. These two combine to make a causative situation. There are three types of causatives are identified in natural languages. They are—morphological causatives, lexical causatives and periphrastic causatives. This study mainly focuses on resolving the issues related to the translation of English periphrastic causative sentences with the auxiliary verbs ‘have’, ‘get’, and ‘make’ into Hindi. A contrastive study of the two languages on causative formation has been made as a first step in this direction. The next step is to develop an MT system for translation of English periphrastic causative constructions into their equivalent Hindi causative forms. In English causative meaning is realized by the use of auxiliary verbs rather than by inflection. Hindi makes use of inflectional suffixes to realize the causative meaning. So causativization in English is different from that in Hindi. As already noted, English shows periphrastic causation whereas Hindi shows morphological causation. In Hindi all causative verb forms show inflection, Person, Number and Gender (PNG) marking and specific causative functions. English takes advantage of a set of verbs like ‘have’, ‘make’, ‘get’ ‘need’ and ‘help’ to bring out the causative meaning. At the time of translation from English to Hindi the selection of causative verb form is very important. The selection of translation equivalence in Hindi depends on many factors. Hindi has two causative inflections—the direct causative and the indirect causative forms. In Hindi, the causative verbs show all the other characteristic features of transitive verbs. They also indicate tense and PNG inflections like any other transitive verb. Transferring the causative information in the source language (English) to the target language (Hindi) is a real challenge. Classification of English verbs by Levin comes handy to solve certain problems which occur while transferring the periphrastic causative construction from English to Hindi. In this paper we have elaborated on the contrastive nature of causative constructions in English and Hindi, pointing out where they differ and where they can be easily matched. Linguistic rules are written to map causative constructions from English to Hindi. Also a system is developed to implement the linguistic rules and to convert the causative constructions from English to Hindi. After collecting the different types of periphrastic causative sentences from the source language, we find out their translation equivalence in Hindi on the basis of the main verb in the source language (SL). We identified the 42 different causative verb forms in Hindi. Then we prepared a set of separate linguistic rules for the transfer of the causative constructions of source language into target language. These transfer rules are utilized to develop a Rule-based Machine Translation system (RBMTs) for translating periphrastic causative sentences from English to Hindi. The output of this newly developed system has been verified by human evaluators. Translation of different types of causative sentences gives commendable result (more the 80% accuracy). © Springer Nature Switzerland AG 2019.