Vietnamese linking grammar model

Natural language processing on computers is one of the difficult problems of information technology. Research on natural language processing has been started since the 40s of the 20th century, right after the appearance of electronic computers. Although started later, Vietnamese language ...

The important role of the dependency model is clear. However, the dependent grammar model has linguistic difficulties. According to Nguyen Tai Can [2], there are many debates about the dependence between elements in Vietnamese sentences, for example, some objects can play a minor role in syntax, ...

CHAPTER 1 OVERVIEW OF PHARMACOLOGICAL MODELS FOR NATURAL LANGUAGE According to Jurafsky [70], grammatical relations are ways of formalizing the ideas of traditional grammars such as subject or complement and other relationships. Many grammar models have been proposed according to the following ...

The above problem is solved by the Inside – Outside Algorithm proposed by Baker in 1979 for context-free grammar [81]. This is essentially a variant of the forward – backward algorithm of the hidden Markov model (Hidden Markov Model – HMM). The algorithm allows to calculate the inner and ...

The tree connection grammar was also built for Vietnamese in [22] by extracting from the Vietnamese treebank. In terms of language representation, a tree-connected grammar is capable of representing context-sensitive languages. This approach is effective when the Vietnamese treebank is large ...

The symbol for the set of all correct dependency graphs of the sentence S with the set of dependencies R is GS. This can be considered as a single-layer dependency model. Dependency models according to the Prague school [109] allow for multi-layer dependencies, so it is possible to model semantic ...

In the dependency grammar, dependency is present and the word central is required. It is assumed that from the existence of the dependent word A it can be concluded that the existence of the central word B. The association grammar allows the association to occur or not. That gives the ability to ...

After studying and drawing out the features of this language model, the thesis will focus on solving the following problems: Parsing problem . This is a must-do problem when building a new syntactic representation model. Machine translation problem . The associative grammar model represents many ...

Each word subcategory follows its own syntactic rules, so it has its own linking formulas. However, division into subcategories is not enough to build linking formulas because words in the same subcategory can also have different ways of linking. The thesis has built a dictionary based on the ...

Proper nouns refer to names of objects, specific nouns indicate people, animals, plants, utensils, and objects connected to a singular or plural sub-element. The following links have been built: DpN: Connect the plural determiner with the noun. DsN: Connect singular adjectives with nouns. ...

In the case where both the 3rd and 4th subcomponents are present, ambiguity can occur as shown in Figure 2.6. In the first case the word “of” modifies “wood”, and in the second case the word “of” modifies “table”. This is a phrase that is both syntactically and semantically ...

Association with a noun (noun) exists when the noun (noun) is in the form of a direct or indirect complement. Whether the direct complement is a noun or a noun, a relationship is established for the noun. The noun is the direct object of the action associated with the verb through the O+ ...

Quantitative affixes: related to the measure, calculation or standard of measurement performed by the noun. Links are established between adjectives and nouns indicating the unit of measure: ApNt. For example, the link in the phrase “two thousand meters deep” is shown in figure 2.12 below ...

The thesis builds a linked grammar dictionary consisting of over 40,000 entries based on the extended algorithm of [113] with a discriminant assessment based on the information in the Vietnamese dictionary. 2.2.1. Dictionary expansion algorithm 2.2.1.1 The idea of the algorithm Szolovits [113] ...

The COUNT function takes as inputs the two words L and R and a pair of two pointers to join lists: l points to a connection in the list to the right of a selection of L and r points to a connection belonging to L and R. list to the left of a selection form of R. COUNT returns a number, that is, the ...

Some sentences may not be fully parsed, part of it is also analyzed. The example in Figure 3.8. is the analysis for the sentence “Every empty-handed season is difficult to swallow”. This sentence is a passive but hidden word. Built-in links are still displayed even if the result is a syntax ...

On the whole text (including sentence, paragraph, and item levels), the discourse analyzer gave an accuracy of 63%. At the sentence level, the accuracy achieved is approximately 80%. Deriving from the characteristics of Vietnamese compound sentences that most of the propositional limits can be ...

Find discursive relationships with units that do not appear discursive signs For units that do not appear discursive signs, based on Vietnamese characteristics, the thesis uses the algorithm to find co-occurring words proposed by Marcu [89]. Then, the discourse relations will be assigned as Connect ...

Figure 3.16 below shows the link analysis storage structure of the sentence “I bought a flower”. 1, 2…5 is the ordinal number of the word. Each word has a linked list of connections with the words to its right. Information about each connection includes (type, destination, rank). For example ...

The thesis has not been tested on complex sentences, which are sentences with two or more subject clusters but one cluster covers the remaining clusters, for example “the shirt you bought yesterday was very nice” with two subject clusters “you bought” “beautiful shirt”, the phrase ...

3.3.1.2. Training Algorithm As discussed in Chapter 1 with a context-free grammar, probabilities acting as parameters can initially be generated randomly, and then updated every time a new sentence is analyzed and added to the set. corpus. The training algorithm proposed by [79] aims to recalculate ...

3.3.2. Conjugate Disambiguation Conjugate ambiguity is ambiguity related to phrases that have an equivalent role in a sentence. As noted in [70], the word “and” plays a special role when analyzing a sentence on the associative grammar model because it can contain a regular connection as well as ...

CHAPTER 4 MACHINE TRANSLATION SYSTEM USE ANNOUNCEMENT FORM 4.1. Machine translation overview 4.1.1. Development situation of machine translation in Vietnam Machine translation is a very interesting field of IT due to the need to translate a large number of documents in the fastest time. According ...

4.2. Language difference between Vietnamese and English There are many differences in word morphology between Vietnamese and English languages. However, not all differences can be handled in machine translation. With the associative grammar model, it is possible to construct a machine-readable rule ...

4.3. The machine translation system uses annotated selections When translating a machine with a structure of two different source and target languages, the following problems always arise: Find exact word meanings – resolve ambiguities and word categories. Fix the difference in morphology of the ...

Law of phrase translation Translate phrases into English pronouns Vocabulary in Vietnamese is very complicated. Even dictionaries have differing views on the wording of the terms of a vocative nature. For example, “we”, “we” appear as a pronoun, but the objects that have the same meaning as ...

Left side The left side of the rule consists of a number of words and forms to link those words together. There is a slight difference between the anthology of words and the anthem described in the rule. The selection form in the rule only states the connections that the rule will handle. Before ...

All three translations have limitations. The ADJ translation failed to detect the possessive relationship of the word “world” while the VEtrans translation translated it but failed to translate the top-level comparative adjective and mistranslated the word “species”. Google translation ...

CONCLUSION AND DEVELOPMENT DEVELOPMENT Summary The thesis aims to build a new model to represent Vietnamese syntax. This model follows the current popular approach: dependent and lexicalized approach. To build the association model without the support of linguistic studies, the thesis had to ...

REFERENCES VIETNAMESE [1] Diep Quang Ban (1989) Vietnamese grammar. Education Publishing House. [2] Nguyen Tai Can (1996) Vietnamese grammar (English – Compound words – Short phrases). Hanoi National University Publishing House. [3] Dinh Dien (2002) English – Vietnamese automatic translation ...

[72] M.Kamayani, A. Purwarianti (2011)  Dependency parsing for Indonesian , proceeding of ICEEI, Bangdung,2011. [73] P. H. Khanh (2000)  Good Spelling of Vietnamese Texts, one aspect of CL in Vietnam . Proceeding of ACL-2000, 38th Conference, HongKong, pp. 593-594. [74] Sang-Soo Kim, Seong-Bae ...

APPENDIX APPENDIX 1: DETAILS OF MAJOR RECIPES IN VIETNAMESE LINKS In the appendix we explain with examples the important links in Vietnamese. The division of words into subcategories is based on [16]. To further subdivide, into sub-categories, the thesis refers to the division in [16], and at the ...

Type particle Classical feature Word Example Link Name Link Example Intransitive verb (Vi) Not used in the passive voice operation: no modifier required breathing, sitting, standing, lying down, sleeping, waking, (engine) exploding, (horn) whistling, (wind) blowing ViAp ViEp+ SV- & {RtVi- or RpVi- ...

APPENDIX 2: RESULTS OF LINKED ANALYSIS OF SOME Simplified and compound sentences of two clauses This is the result given by the association parser (which has not processed compound sentences) for the first 50 sentences in the sample corpus of the Vietnamese – English translation system using ADJ. ...

ANNEX 3: SOME TYPICAL TRANSLATION LAW Appendix 3 shows the actual form of archiving in the text file of the rules mentioned in Chapter 4. Therefore, the presentation format is different. In this law, The symbol * indicates any word () indicates any sequence of connections. The sign $1 indicates the ...

ADDENDUM 4: COMPARISON OF THE TRANSLATION RESULTS OF SOME QUESTIONS Sentence 1 (1): My name is Hoa –> My name is bloom. VEtran: My Name is Flower. Google: My name is United. Sentence 2 (2): My mother is a good doctor. –> My mother is a good doctor. VEtran: My mother is a jurisprudent physician. ...

MINISTRY OF EDUCATION AND TRAINING Hanoi University of Science and Technology NGUYEN THI THU HUONG MODEL VIETNAM LINK PHARMACS Specialization: Computer Science Code: 62.48.01.01 PhD THESIS OF INFORMATION TECHNOLOGY Science Instructor: Dr. NGUYEN THUC HAI Prof.Dr. NGUYEN THANH THUY Hanoi – 2013 ...