The paper reports an Example based Machine Translation System for translating News Headlines from English to Bengali. The input headline is initially searched in the Direct Example Base. If it cannot be found, the input headline is tagged and the tagged headline is searched in the Generalized Tagged Example Base. If a match is obtained, the tagged headline in Bengali is retrieved from the example base, the output Bengali headline is generated after retrieving the Bengali equivalents of the English words from appropriate dictionaries and then applying relevant synthesis rules for generating the Bengali surface level words. If some named entities and acronyms are not present in the dictionary, transliteration scheme is applied for obtaining the Bengali equivalent. If a match is not found, the tagged input headline is analysed to identify the constituent phrase(s). The target translation is generated using English-Bengali phrasal example base, appropriate dictionaries and a set of heuristics for Bengali phrase reordering. If the headline still cannot be translated using example base strategy, a heuristic translation strategy will be applied. Any new input tagged headline along with its translation by the user will be inserted in the tagged Example base after generalization.

A Semantics-based English-Bengali EBMT System for Translating News Headlines

Information on subcategorization and selectional restrictions in a valency dictionary is important for natural language processing tasks such as monolingual parsing, accurate rule-based machine translation and automatic summarization. In this paper we present an efficient method of assigning valency information and selectional restrictions to entries in a bilingual dictionary, based on information in an existing valency dictionary. The method is based on two assumptions: words with similar meaning have similar subcategorization frames and selectional restrictions; and words with the same translations have similar meanings. Based on these assumptions, new valency entries are constructed for words in a plain bilingual dictionary, using entries with similar source-language meaning and the same target-language translations. We evaluate the effects of various measures of semantic similarity.

/pdf/a-method-of-creating-new-valency-entries-48ymzxx39r.pdf

A method of creating new valency entries

In this paper we introduce a fully automatic method to extend an existing rich bilingual valency dictionary by using information from multiple plain bilingual dictionaries. We evaluate our method using a translation regression test, and get an improvement of 7%.

/pdf/an-automatic-method-of-creating-valency-entries-using-plain-3wp5lczw3p.pdf

An automatic method of creating valency entries using plain bilingual dictionaries

A machine-translation apparatus using multi-level verbal-phrase patterns includes: a simple sentence generation unit for generating an input simple sentence; a basic verbal-phrase pattern-matching unit for trying a match of a semantic code of each case component of the input simple sentence with basic verbal-phrase patterns; a default verbal-phrase pattern matching unit for trying a match of a size and case prepositions of the input simple sentence with default verbal-phrase patterns having a verb identical to that of the input simple sentence; a default word-order matching unit for trying a match of a word-order of the input simple sentence with default word-order verbal-phrase patterns having a case component structure identical to that of the input simple sentence; and a default preposition matching unit for generating a target sentence of an input sentence with default preposition patterns having a context identical to that of the input simple sentence.

Machine-translation apparatus using multi-stage verbal-phrase patterns, methods for applying and extracting multi-stage verbal-phrase patterns

In a machine translation system, word sense disambiguation has an essential role in the proper translation of words when the target word can be translated differently depending on the context. Previous research on sense identification has mostly focused on adjacent words as context information. Therefore, in the case of nominal compounds, sense tagging of unit nouns mainly depended on other nouns surrounding the target word. In this paper, we present a practical method for the sense tagging of Korean unit nouns in a nominal compound. To overcome the weakness of traditional methods regarding the data sparseness problem, the proposed method adopts complement-predicate relation knowledge that was constructed for machine translation systems. Our method is based on a sentential form recovery technique, which recognizes grammatical relationships between unit nouns. This technique makes use of the characteristics of Korean predicative nouns. To show that our method is effective on text in general domains, the experiments were performed on a test set randomly extracted from article titles in various newspaper sections.

Noun Sense Identification of Korean Nominal Compounds Based on Sentential Form Recovery

This paper addresses a new method of constructing Korean-Chinese verb patterns from existing patterns. A verb pattern is a subcategorization frame of a predicate extended by translation information. Korean-Chinese verb patterns are invaluable linguistic resources that are not only used for Korean-Chinese transfer but also for Korean parsing. Usually a verb pattern has been either hand-coded by expert lexicographers or extracted automatically from bilingual corpus. In the first case, the dependence on the linguistic intuition of lexicographers may lead to the incompleteness and the inconsistency of a dictionary. In the second case, extracted patterns can be domain-dependent. In this paper, we present a method to construct Korean-Chinese verb patterns semi-automatically from existing Korean-Chinese verb patterns that are manually written by lexicographers.

/pdf/semi-automatic-construction-of-korean-chinese-verb-patterns-479xurol0k.pdf

Semi-automatic construction of Korean-Chinese verb patterns based on translation equivalency

This paper describes our ongoing project "Korean-Chinese Machine Translation System". The main knowledge of our system is verb patterns. Each verb can have several meanings and each meaning of a verb is represented by a verb pattern. A verb pattern consists of a source language pattern part for the analysis and the corresponding target language pattern part for the generation. Each pattern part, according to the degree of generality, contains lexical or semantic information for the arguments or adjuncts of each verb meaning. In this approach, accurate analysis can directly lead to natural and correct generation. Furthermore as the transfer mainly depends upon verb patterns, the translation rate is expected to go higher, as the size of verb pattern grows larger.

Korean-Chinese Machine Translation Based on Verb Patterns

This paper addresses a Korean-English machine translation system for scientific papers. The MT system is supported by CL (Controlled Language)-guided source language rewriting. After analyzing the translation errors of the system, we defined Korean rewriting rules to avoid the linguistic obstacles that may affect the translation accuracy. To support this, a Korean CL-checker was implemented. We showed that this CL-guided MT system can improve the translation accuracy by about 13% by adopting CL rewriting rules. However, this improvement is still not enough for various purposes, because most of the users of the MT system may want to submit the translated texts to a conference or an academic journal. As the MT output contains erroneous expressions, a language model module was added to the pattern-based MT engine. The system automatically detects expressions with low frequency and asks the authors to examine the translation. By adopting CL rewriting rules and language model module to the existing MT engine, almost "professional" translations can be obtained.

CL-Guided Korean-English MT System for Scientific Papers

Patent MT is emerging as a killer application domain for MT, as there is a strong need for fast and cheap translations for patent documents. Most of the Korean-English MT engines hitherto have suffered from the poor syntactic analysis performance and the lack of linguistic resources. We customized a Korean syntactic parser based on the linguistic characteristics of the patent documents, especially focusing on minimizing the noise in acquiring the co-occurrence data for Korean syntactic parsing. We will show that the improvement of the quality of co-occurrence data and other customization processes can lead to the im prove ment of the parsing accuracy and thus the improvement of the translation quality.

A korean syntactic parser customized for korean-english patent MT system

This paper addresses the problem of the unknown light verb construction in Korean in the context of Korean-to-English patent machine translation. The light verb construction in Korean is composed of a light verb ‘ha’ and a predicative noun. The predicative nouns are generally sino-Korean words or loan words mostly from English in deverbal form. Previous researches on the light verb construction were mostly focused on the linguistic explanation about the thematic role assignment and the argument realization. In this paper, we will present a method for treating the LVC words that are not in the dictionary of Korean-to-English patent MT system. We introduce 4 types of unknown LVCs and present a method for generating the target word automatically. The evaluation of the automatically translated unknown words by professional translators showed 70.06% accuracy.

Munpyo Hong

Papers

Semi-automatic construction of Korean-Chinese verb patterns based on translation equivalency

Korean-Chinese Machine Translation Based on Verb Patterns

CL-Guided Korean-English MT System for Scientific Papers

A korean syntactic parser customized for korean-english patent MT system

Treating unknown light verb construction in korean-to-english patent MT