Dissertations / Theses on the topic 'Translation disambiguation'

Cross-lingual information retrieval (CLIR) allows people to find documents irrespective of the language used in the query or document. This thesis is concerned with the development of techniques to improve the effectiveness of Chinese-English CLIR. In Chinese-English CLIR, the accuracy of dictionary-based query translation is limited by two major factors: translation ambiguity and the presence of out-of-vocabulary (OOV) terms. We explore alternative methods for translation disambiguation, and demonstrate new techniques based on a Markov model and the use of web documents as a corpus to provide context for disambiguation. This simple disambiguation technique has proved to be extremely robust and successful. Queries that seek topical information typically contain OOV terms that may not be found in a translation dictionary, leading to inappropriate translations and consequent poor retrieval performance. Our novel OOV term translation method is based on the Chinese authorial practice of including unfamiliar English terms in both languages. It automatically extracts correct translations from the web and can be applied to both Chinese-English and English-Chinese CLIR. Our OOV translation technique does not rely on prior segmentation and is thus free from seg mentation error. It leads to a significant improvement in CLIR effectiveness and can also be used to improve Chinese segmentation accuracy. Good quality translation resources, especially bilingual dictionaries, are valuable resources for effective CLIR. We developed a system to facilitate construction of a large-scale translation lexicon of Chinese-English OOV terms using the web. Experimental results show that this method is reliable and of practical use in query translation. In addition, parallel corpora provide a rich source of translation information. We have also developed a system that uses multiple features to identify parallel texts via a k-nearest-neighbour classifier, to automatically collect high quality parallel Chinese-English corpora from the web. These two automatic web mining systems are highly reliable and easy to deploy. In this research, we provided new ways to acquire linguistic resources using multilingual content on the web. These linguistic resources not only improve the efficiency and effectiveness of Chinese-English cross-language web retrieval; but also have wider applications than CLIR.

Over the last years, technology has achieved a dominant position in a wide range of fields, causing a profound paradigm shift in our lives. In the area of translation, technology has brought to light useful applications such as machine translation and computer-aided translation. While the former is aimed at automatically translating texts, the latter is intended to support and facilitate the translation process. In consideration of the remarkable success of translation technology, the present master’s thesis proposes a prototype for an innovative CAT tool calledTongue2Tongue which exploits state-of-the-art natural language processing techniques for enabling a wide-coverage, semantically-aware and language-independent retrieval of parallel and comparable texts. More specifically, starting from a text segment in a source language, the proposed CAT tool is capable of providing similar text segments in a target language. This function aims at facilitating the translator in understanding the content of a source text and identifying the most appropriate and adequate translations. The major innovation brought about by Tongue2Tongue consists in the implementation of innovative knowledge-based word sense disambiguation algorithms and techniques which allow to compute large-scale cross-lingual and language-independent semantic similarity among text segments. This means that Tongue2Tongue will be capable of automatically supplying parallel and comparable text segments taking into consideration the semantics of texts and regardless of the languages employed. As far as we know, this approach isbeing implemented for the first time in a CAT tool.

This thesis argues that cross-lingual word sense disambiguation (CL-WSD) can be used to improve lexical selection for machine translation when translating from a resource-rich language into an under-resourced one, especially when relatively little bitext is available. In CL-WSD, we perform word sense disambiguation, considering the senses of a word to be its possible translations into some target language, rather than using a sense inventory developed manually by lexicographers.

Using explicitly trained classifiers that make use of source-language context and of resources for the source language can help machine translation systems make better decisions when selecting target-language words. This is especially the case when the alternative is hand-written lexical selection rules developed by researchers with linguistic knowledge of the source and target languages, but also true when lexical selection would be performed by a statistical machine translation system, when there is a relatively small amount of available target-language text for training language models.

In this work, I present the Chipa system for CL-WSD and apply it to the task of translating from Spanish to Guarani and Quechua, two indigenous languages of South America. I demonstrate several extensions to the basic Chipa system, including techniques that allow us to benefit from the wealth of available unannotated Spanish text and existing text analysis tools for Spanish, as well as approaches for learning from bitext resources that pair Spanish with languages unrelated to our intended target languages. Finally, I provide proof-of-concept integrations of Chipa with existing machine translation systems, of two completely different architectures.

In this project, we have investigated how to perform rule-based machine translation of sets of keywords between two languages. The goal was to translate an input set, which contains one or more keywords in a source language, to a corresponding set of keywords, with the same number of elements, in the target language. However, some words in the source language may have several senses and may be translated to several, or no, words in the target language. If ambiguous translations occur, the best translation of the keyword should be chosen with respect to the context. In traditional machine translation, a word's context is determined by a phrase or sentences where the word occurs. In this project, the set of keywords represents the context. By investigating traditional approaches to machine translation (MT), we designed and described models for the specific purpose of keyword- translation. We have proposed a solution, based on direct translation for translating keywords between English and Swedish. In the proposed solu- tion, we also introduced a simple graph-based model for solving ambigu- ous translations.
I detta projekt har vi undersökt hur man utför regelbaserad maskinöver- sättning av nyckelord mellan två språk. Målet var att översätta en given mängd med ett eller flera nyckelord på ett källspråk till en motsvarande, lika stor mängd nyckelord på målspråket. Vissa ord i källspråket kan dock ha flera betydelser och kan översättas till flera, eller inga, ord på målsprå- ket. Om tvetydiga översättningar uppstår ska nyckelordets bästa över- sättning väljas med hänsyn till sammanhanget. I traditionell maskinö- versättning bestäms ett ords sammanhang av frasen eller meningen som det befinner sig i. I det här projektet representerar den givna mängden nyckelord sammanhanget. Genom att undersöka traditionella tillvägagångssätt för maskinöversätt- ning har vi designat och beskrivit modeller specifikt för översättning av nyckelord. Vi har presenterat en direkt maskinöversättningslösning av nyckelord mellan engelska och svenska där vi introducerat en enkel graf- baserad modell för tvetydiga översättningar.

In recent years there has been an increased interest in domain adaptation techniques for statistical machine translation (SMT) to deal with the growing amount of data from different sources. Topic modelling techniques applied to SMT are closely related to the field of domain adaptation but more flexible in dealing with unstructured text. Topic models can capture latent structure in texts and are therefore particularly suitable for modelling structure in between and beyond corpus boundaries, which are often arbitrary. In this thesis, the main focus is on dynamic translation model adaptation to texts of unknown origin, which is a typical scenario for an online MT engine translating web documents. We introduce a new bilingual topic model for SMT that takes the entire document context into account and for the first time directly estimates topic-dependent phrase translation probabilities in a Bayesian fashion. We demonstrate our model’s ability to improve over several domain adaptation baselines and further provide evidence for the advantages of bilingual topic modelling for SMT over the more common monolingual topic modelling. We also show improved performance when deriving further adapted translation features from the same model which measure different aspects of topical relatedness. We introduce another new topic model for SMT which exploits the distributional nature of phrase pair meaning by modelling topic distributions over phrase pairs using their distributional profiles. Using this model, we explore combinations of local and global contextual information and demonstrate the usefulness of different levels of contextual information, which had not been previously examined for SMT. We also show that combining this model with a topic model trained at the document-level further improves performance. Our dynamic topic adaptation approach performs competitively in comparison with two supervised domain-adapted systems. Finally, we shed light on the relationship between domain adaptation and topic adaptation and propose to combine multi-domain adaptation and topic adaptation in a framework that entails automatic prediction of domain labels at the document level. We show that while each technique provides complementary benefits to the overall performance, there is an amount of overlap between domain and topic adaptation. This can be exploited to build systems that require less adaptation effort at runtime.

Peer to peer systems have been widely used in the internet. However, most of the peer to peer information systems are still missing some of the important features, for example cross-language IR (Information Retrieval) and collection selection / fusion features. Cross-language IR is the state-of-art research area in IR research community. It has not been used in any real world IR systems yet. Cross-language IR has the ability to issue a query in one language and receive documents in other languages. In typical peer to peer environment, users are from multiple countries. Their collections are definitely in multiple languages. Cross-language IR can help users to find documents more easily. E.g. many Chinese researchers will search research papers in both Chinese and English. With Cross-language IR, they can do one query in Chinese and get documents in two languages. The Out Of Vocabulary (OOV) problem is one of the key research areas in crosslanguage information retrieval. In recent years, web mining was shown to be one of the effective approaches to solving this problem. However, how to extract Multiword Lexical Units (MLUs) from the web content and how to select the correct translations from the extracted candidate MLUs are still two difficult problems in web mining based automated translation approaches. Discovering resource descriptions and merging results obtained from remote search engines are two key issues in distributed information retrieval studies. In uncooperative environments, query-based sampling and normalized-score based merging strategies are well-known approaches to solve such problems. However, such approaches only consider the content of the remote database but do not consider the retrieval performance of the remote search engine. This thesis presents research on building a peer to peer IR system with crosslanguage IR and advance collection profiling technique for fusion features. Particularly, this thesis first presents a new Chinese term measurement and new Chinese MLU extraction process that works well on small corpora. An approach to selection of MLUs in a more accurate manner is also presented. After that, this thesis proposes a collection profiling strategy which can discover not only collection content but also retrieval performance of the remote search engine. Based on collection profiling, a web-based query classification method and two collection fusion approaches are developed and presented in this thesis. Our experiments show that the proposed strategies are effective in merging results in uncooperative peer to peer environments. Here, an uncooperative environment is defined as each peer in the system is autonomous. Peer like to share documents but they do not share collection statistics. This environment is a typical peer to peer IR environment. Finally, all those approaches are grouped together to build up a secure peer to peer multilingual IR system that cooperates through X.509 and email system.

Peer to peer systems have been widely used in the internet. However, most of the peer to peer information systems are still missing some of the important features, for example cross-language IR (Information Retrieval) and collection selection / fusion features. Cross-language IR is the state-of-art research area in IR research community. It has not been used in any real world IR systems yet. Cross-language IR has the ability to issue a query in one language and receive documents in other languages. In typical peer to peer environment, users are from multiple countries. Their collections are definitely in multiple languages. Cross-language IR can help users to find documents more easily. E.g. many Chinese researchers will search research papers in both Chinese and English. With Cross-language IR, they can do one query in Chinese and get documents in two languages. The Out Of Vocabulary (OOV) problem is one of the key research areas in crosslanguage information retrieval. In recent years, web mining was shown to be one of the effective approaches to solving this problem. However, how to extract Multiword Lexical Units (MLUs) from the web content and how to select the correct translations from the extracted candidate MLUs are still two difficult problems in web mining based automated translation approaches. Discovering resource descriptions and merging results obtained from remote search engines are two key issues in distributed information retrieval studies. In uncooperative environments, query-based sampling and normalized-score based merging strategies are well-known approaches to solve such problems. However, such approaches only consider the content of the remote database but do not consider the retrieval performance of the remote search engine. This thesis presents research on building a peer to peer IR system with crosslanguage IR and advance collection profiling technique for fusion features. Particularly, this thesis first presents a new Chinese term measurement and new Chinese MLU extraction process that works well on small corpora. An approach to selection of MLUs in a more accurate manner is also presented. After that, this thesis proposes a collection profiling strategy which can discover not only collection content but also retrieval performance of the remote search engine. Based on collection profiling, a web-based query classification method and two collection fusion approaches are developed and presented in this thesis. Our experiments show that the proposed strategies are effective in merging results in uncooperative peer to peer environments. Here, an uncooperative environment is defined as each peer in the system is autonomous. Peer like to share documents but they do not share collection statistics. This environment is a typical peer to peer IR environment. Finally, all those approaches are grouped together to build up a secure peer to peer multilingual IR system that cooperates through X.509 and email system.

A comunicação multilíngue é uma tarefa cada vez mais imperativa no cenário atual de grande disseminação de informações em diversas línguas. Nesse contexto, são de grande relevância os sistemas de tradução automática, que auxiliam tal comunicação, automatizando-a. Apesar de ser uma área de pesquisa bastante antiga, a Tradução Automática ainda apresenta muitos problemas. Um dos principais problemas é a ambigüidade lexical, ou seja, a necessidade de escolha de uma palavra, na língua alvo, para traduzir uma palavra da língua fonte quando há várias opções de tradução. Esse problema se mostra ainda mais complexo quando são identificadas apenas variações de sentido nas opções de tradução. Ele é denominado, nesse caso, \"ambigüidade lexical de sentido\". Várias abordagens têm sido propostas para a desambiguação lexical de sentido, mas elas são, em geral, monolíngues (para o inglês) e independentes de aplicação. Além disso, apresentam limitações no que diz respeito às fontes de conhecimento que podem ser exploradas. Em se tratando da língua portuguesa, em especial, não há pesquisas significativas voltadas para a resolução desse problema. O objetivo deste trabalho é a proposta e desenvolvimento de uma nova abordagem de desambiguação lexical de sentido, voltada especificamente para a tradução automática, que segue uma metodologia híbrida (baseada em conhecimento e em córpus) e utiliza um formalismo relacional para a representação de vários tipos de conhecimentos e de exemplos de desambiguação, por meio da técnica de Programação Lógica Indutiva. Experimentos diversos mostraram que a abordagem proposta supera abordagens alternativas para a desambiguação multilíngue e apresenta desempenho superior ou comparável ao do estado da arte em desambiguação monolíngue. Adicionalmente, tal abordagem se mostrou efetiva como mecanismo auxiliar para a escolha lexical na tradução automática estatística
Crosslingual communication has become a very imperative task in the current scenario with the increasing amount of information dissemination in several languages. In this context, machine translation systems, which can facilitate such communication by providing automatic translations, are of great importance. Although research in Machine Translation dates back to the 1950\'s, the area still has many problems. One of the main problems is that of lexical ambiguity, that is, the need for lexical choice when translating a source language word that has several translation options in the target language. This problem is even more complex when only sense variations are found in the translation options, a problem named \"sense ambiguity\". Several approaches have been proposed for word sense disambiguation, but they are in general monolingual (for English) and application-independent. Moreover, they have limitations regarding the types of knowledge sources that can be exploited. Particularly, there is no significant research aiming to word sense disambiguation involving Portuguese. The goal of this PhD work is the proposal and development of a novel approach for word sense disambiguation which is specifically designed for machine translation, follows a hybrid methodology (knowledge and corpus-based), and employs a relational formalism to represent various kinds of knowledge sources and disambiguation examples, by using Inductive Logic Programming. Several experiments have shown that the proposed approach overcomes alternative approaches in multilingual disambiguation and achieves higher or comparable results to the state of the art in monolingual disambiguation. Additionally, the approach has shown to effectively assist lexical choice in a statistical machine translation system

La désambiguïsation lexicale (DL) et la traduction automatique (TA) sont deux tâches centrales parmi les plus anciennes du traitement automatique des langues (TAL). Bien qu'ayant une origine commune, la DL ayant été conçue initialement comme un problème fondamental à résoudre pour la TA, les deux tâches ont par la suite évolué très indépendamment. En effet, d'un côté, la TA a su s'affranchir d'une désambiguïsation explicite des termes grâce à des modèles statistiques et neuronaux entraînés sur de grandes quantités de corpus parallèles, et de l'autre, la DL, qui est confrontée à certaines limitations comme le manque de ressources unifiées et un champs d'application encore restreint, reste un défi majeur pour permettre une meilleure compréhension de la langue en général.Aujourd'hui, dans un contexte où les méthodes à base de réseaux de neurones et les représentations vectorielles des mots prennent de plus en plus d'ampleur dans la recherche en TAL, les nouvelles architectures neuronales et les nouveaux modèles de langue pré-entraînés offrent non seulement de nouvelles possibilités pour développer des systèmes de DL et de TA plus performants, mais aussi une opportunité de réunir les deux tâches à travers des modèles neuronaux joints, permettant de faciliter l'étude de leurs interactions.Dans cette thèse, nos contributions porteront dans un premier temps sur l'amélioration des systèmes de DL, par l'unification des données nécessaires à leur mise en oeuvre, la conception de nouvelles architectures neuronales et le développement d'approches originales pour l'amélioration de la couverture et des performances de ces systèmes. Ensuite, nous développerons et comparerons différentes approches pour l'intégration de nos systèmes de DL état de l'art et des modèles de langue, dans des systèmes de TA, pour l'amélioration générale de leur performance. Enfin, nous présenterons une nouvelle architecture pour l'apprentissage d'un modèle neuronal joint pour la DL et la TA, s'appuyant sur nos meilleurs systèmes neuronaux pour l'une et l'autre tâche
Word Sense Disambiguation (WSD) and Machine Translation (MT) are two central and among the oldest tasks of Natural Language Processing (NLP). Although they share a common origin, WSD being initially conceived as a fundamental problem to be solved for MT, the two tasks have subsequently evolved very independently of each other. Indeed, on the one hand, MT has been able to overcome the explicit disambiguation of terms thanks to statistical and neural models trained on large amounts of parallel corpora, and on the other hand, WSD, which faces some limitations such as the lack of unified resources and a restricted scope of applications, remains a major challenge to allow a better understanding of the language in general.Today, in a context in which neural networks and word embeddings are becoming more and more important in NLP research, the recent neural architectures and the new pre-trained language models offer not only some new possibilities for developing more efficient WSD and MT systems, but also an opportunity to bring the two tasks together through joint neural models, which facilitate the study of their interactions.In this thesis, our contributions will initially focus on the improvement of WSD systems by unifying the ressources that are necessary for their implementation, constructing new neural architectures and developing original approaches to improve the coverage and the performance of these systems. Then, we will develop and compare different approaches for the integration of our state of the art WSD systems and language models into MT systems for the overall improvement of their performance. Finally, we will present a new architecture that allows to train a joint model for both WSD and MT, based on our best neural systems

碩士
國立清華大學
資訊系統與應用研究所
95
We introduce a new method for automatically disambiguation of word translations by using dependency relationships. In our approach, we learn the relationships between translations and dependency relationships from a parallel corpus. The method consists of a training stage and a runtime stage. During the training stage, the system automatically learns a translation decision list based on source sentences and its dependency relationships. At runtime, for each content word in the given sentence, we give a most appropriate Chinese translation relevant to the context of the given sentence according to the decision list. We also describe the implementation of the proposed method using bilingual Hong Kong news and Hong Kong Hansard corpus. In the experiment, we use five different ways to translate content words in the test data and evaluate the results based an automatic BLEU-like evaluation methodology. Experimental results indicate that dependency relations can obviously help us to disambiguate word translations and some kinds of dependency are more effective than others.

碩士
國立清華大學
資訊工程學系
93
We introduce a new method for automatically disambiguation of word translations by using collocations. In our approach, we learn the the relationships between translation categories and collocations using the information on the Web. The method consists of a training stage and a runtime stage. During the training stage, the method involves automatically acquisition of collocates of target words from a large corpus, distinguishing of collocations into two or more parts by translations of a given word, and learning a translation decision list based on sentences with the target word and its collocates automatically acquired from the Web. At runtime, the target word in the given sentence is translated according to the decision list model. We also describe the implementation of a prototype system of the proposed method, experiments, and evaluation. In the experiment, we used four polysemous words to assess the performance of the method compare the results against judgments made by human subjects. Experimental results indicate that the proposed unsupervised method based on the Web as corpus overcomes the knowledge acquisition bottleneck and provides a promising approach for word translation disambiguation.

碩士
元智大學
資訊工程學系
98
This paper proposes a Japanese opinion word translation method based on unsupervised word sense disambiguation. The method comprises the corpus preparation, opinion word dictionary construction, and weighting method. Different from the machine translation, our method does not need parallel corpora, tagged corpora or parsing tree banks. Our method is low-cost but effective, and requires a well-made bilingual dictionary only. Besides, our method can extract key information from the opinions to help users understand the opinions. We construct four configurations and evaluate our method on four Japanese opinion words with high frequency. The evaluation result shows that the dependency grammar and opinion word dictionary is effective on opinion word translation. Our method can deal with the translation disambiguation problem and improve the translation precision to help user realize Japanese opinions.