Thesis--University of Pittsburgh. / Includes bibliographical references.

Thesis (Ph. D.)--University of Wisconsin--Madison, 1972. / Typescript. Vita. eContent provider-neutral record in process. Description based on print version record. Includes bibliography.

Risālat al-duktūrāh -- Jāmiʻat ʻAyn Shams. / Bibliography: p. 495-522.

Call number: LD2668 .T4 1978 O54 / Master of Arts

Due to the lack of short vowels or diacritics in Persian orthography, many Natural Language Processing applications for this language, including information retrieval, machine translation, text-to-speech, and automatic speech recognition systems need to disambiguate the input first, in order to be able to do further processing. In machine translation, for example, the whole text should be correctly diacritized first so that the correct words, parts of speech and meanings are matched and retrieved from the lexicon. This is primarily because of Persian’s ambiguous orthography. In fact, the core engine of any Persian language processor should utilize a diacritizer and a lexical disambiguator. This dissertation describes the design and implementation of an automatic diacritizer for Persian based on the state-of-the-art Finite State Transducer technology developed at Xerox by Beesley & Karttunen (2003). The result of morphological analysis and generation on a test corpus is shown, including the insertion of diacritics. This study will also look at issues that are raised by phonological and semantic ambiguities as a result of short vowels in Persian being absent in the writing system. It suggests a hybrid model (rule-based & inductive) that is inspired by psycholinguistic experiments on the human mental lexicon for the disambiguation of heterophonic homographs in Persian using frequency and collocation information. A syntactic parser can be developed based on the proposed model to discover Ezafe (the linking short vowel /e/ within a noun phrase) or disambiguate homographs, but its implementation is left for future work.

Due to the lack of short vowels or diacritics in Persian orthography, many Natural Language Processing applications for this language, including information retrieval, machine translation, text-to-speech, and automatic speech recognition systems need to disambiguate the input first, in order to be able to do further processing. In machine translation, for example, the whole text should be correctly diacritized first so that the correct words, parts of speech and meanings are matched and retrieved from the lexicon. This is primarily because of Persian’s ambiguous orthography. In fact, the core engine of any Persian language processor should utilize a diacritizer and a lexical disambiguator. This dissertation describes the design and implementation of an automatic diacritizer for Persian based on the state-of-the-art Finite State Transducer technology developed at Xerox by Beesley & Karttunen (2003). The result of morphological analysis and generation on a test corpus is shown, including the insertion of diacritics. This study will also look at issues that are raised by phonological and semantic ambiguities as a result of short vowels in Persian being absent in the writing system. It suggests a hybrid model (rule-based & inductive) that is inspired by psycholinguistic experiments on the human mental lexicon for the disambiguation of heterophonic homographs in Persian using frequency and collocation information. A syntactic parser can be developed based on the proposed model to discover Ezafe (the linking short vowel /e/ within a noun phrase) or disambiguate homographs, but its implementation is left for future work.

Due to the lack of short vowels or diacritics in Persian orthography, many Natural Language Processing applications for this language, including information retrieval, machine translation, text-to-speech, and automatic speech recognition systems need to disambiguate the input first, in order to be able to do further processing. In machine translation, for example, the whole text should be correctly diacritized first so that the correct words, parts of speech and meanings are matched and retrieved from the lexicon. This is primarily because of Persian’s ambiguous orthography. In fact, the core engine of any Persian language processor should utilize a diacritizer and a lexical disambiguator. This dissertation describes the design and implementation of an automatic diacritizer for Persian based on the state-of-the-art Finite State Transducer technology developed at Xerox by Beesley & Karttunen (2003). The result of morphological analysis and generation on a test corpus is shown, including the insertion of diacritics. This study will also look at issues that are raised by phonological and semantic ambiguities as a result of short vowels in Persian being absent in the writing system. It suggests a hybrid model (rule-based & inductive) that is inspired by psycholinguistic experiments on the human mental lexicon for the disambiguation of heterophonic homographs in Persian using frequency and collocation information. A syntactic parser can be developed based on the proposed model to discover Ezafe (the linking short vowel /e/ within a noun phrase) or disambiguate homographs, but its implementation is left for future work.

Thesis in Political Science, University of Oslo, Institute of Political Science, 1998.

Due to the lack of short vowels or diacritics in Persian orthography, many Natural Language Processing applications for this language, including information retrieval, machine translation, text-to-speech, and automatic speech recognition systems need to disambiguate the input first, in order to be able to do further processing. In machine translation, for example, the whole text should be correctly diacritized first so that the correct words, parts of speech and meanings are matched and retrieved from the lexicon. This is primarily because of Persian’s ambiguous orthography. In fact, the core engine of any Persian language processor should utilize a diacritizer and a lexical disambiguator. This dissertation describes the design and implementation of an automatic diacritizer for Persian based on the state-of-the-art Finite State Transducer technology developed at Xerox by Beesley & Karttunen (2003). The result of morphological analysis and generation on a test corpus is shown, including the insertion of diacritics. This study will also look at issues that are raised by phonological and semantic ambiguities as a result of short vowels in Persian being absent in the writing system. It suggests a hybrid model (rule-based & inductive) that is inspired by psycholinguistic experiments on the human mental lexicon for the disambiguation of heterophonic homographs in Persian using frequency and collocation information. A syntactic parser can be developed based on the proposed model to discover Ezafe (the linking short vowel /e/ within a noun phrase) or disambiguate homographs, but its implementation is left for future work.

This dissertation investigates the verbal system of Persian and is focused on the interaction of modality, tense, aspect and negation in this language. The dissertation challenges the idea that the syntactic structure maps on to the semantic interpretation or vice-versa.It is argued that modals are raising constructions in some languages (Wurmbrand 1999). Modals in Persian, which do not have subject-raising constructions, show different behavior. First, the root complex modals are generally syntactic control in Wurmbrand's (1998, 2001) proposal. There are just a few gaps with respect to dynamic root modals. Second, all epistemic modals which are either defective auxiliary modals or complex modals take default agreements and are pseudo-raising constructions. Third, the syntactic structures of modals show that there is no one-to-one correspondence between the structural positions and semantic interpretations of modals in Persian except in the auxiliary modal bâyad 'must'.The second contribution of this dissertation is that the class of restructuring verbs varies across languages. German semantic control verbs are instances of restructuring constructions (Wurmbrand 2001) while the only case of restructuring in Persian is the functional restructuring which appears in auxiliary modals such as bâyad 'must' and šâyad 'may' since they are mono-clausal and do not have a CP.This dissertation also investigates the structure of complex verbal forms in Persian. It is argued that Persian future tense is an instance of Serial Verb Constructions. However, progressives which are bi-clausal constructions are Aspectual Complex predicates.In the case of the structural analysis of the interaction of Persian modals and negation, this dissertation shows that the syntactic structure maps on the semantic interpretation or vice-versa. There are just a few gaps with respect to the scope possibilities of particular modals.The final contribution of this dissertation is related to the problem of the word order of NV elements and LV within complex predicates. This research provides three suggestions regarding the clausal complement position in complex predicates, and suggests that the vP remnant movement is the most reasonable one, since it is compatible with the recent trends of syntactic theories and suggested for some other languages (Mahajan 2003).