Parallel Corpora

The availability of partially overlapping parallel corpora for a language pair opens up opportunities for automatically comparing, evaluating and improving them. We compare and evaluate the alignment quality of two English-Estonian parallel corpora that have been created independently, but contain overlapping texts. We describe how to determine the overlapping parts and find their alignment similarities that allow us to economize

Resumen: Los corpus de textos son herramientas de larga tradición y numerosas aplicaciones. De todos los tipos existentes, este trabajo se centra en uno en concreto: el corpus paralelo alineado. Tomando como punto de partida un corpus paralelo alineado de textos museísticos escritos originariamente en inglés y traducidos al español, se propone una metodología que pasa por cuatro fases esenciales. Con el apoyo de trabajos previos al respecto, y tras el recurso a programas de software —de pago y gratuitos, específicos y creados con otros fines—, se comprueba que, si bien es posible llevar a cabo la compilación del corpus, el camino está lleno de obstáculos, algunos salvables y otros no, como ha sucedido con la conservación de repeticiones en el corpus alineado.
Abstract: Text corpora are tools having both a long tradition in research and a variety of applications. Of all existing types, this paper focuses specifically on parallel, aligned corpora. By taking one of this corpora as a starting point—a parallel, aligned corpus from museum texts originally written in English and subsequently translated into Spanish—, the aim of this article is to propose a methodology that consists of four basic stages. By the revision of previous literature on the topic, and by using multiple software programs—proprietary and free, specifically created for corpus compilation and created for other purposes—, it is concluded that, although the compilation of corpora such as the one that was intended is a feasible task, the procedure is full of obstacles. Some obstacles were overcome, while some were not; that is the case, for example, of the repetitions on the aligned corpus, which are not present in the corpus.

Rule Based Machine Translation (RBMT) and Statistical Machine translation (SMT) have different approach in performing translation task. RBMT uses linguistic rule between two languages which is built manually by human in general, whereas SMT uses co-occurrence statistic of word in parallel corpora. We combine those different approaches into Indonesian-English Hybrid Machine Translation (HMT) system to get the advantage from both kind of information. Initially, Indonesian text is inputted into RBMT. Then, the output will be edited by SMT to generate the final translation of English text. SMT is capable to do this because on the training process, it uses RBMT's output (English) as source material and real translation (English) as target material. Unavailability of ready to use Indonesian-English RBMT system becomes a challenge to do this research. Our study shows that SMT still outperforms HMT by 8.01% in average.

The aim of this paper is to investigate Polish equivalents of English phrasal verbs as found in an English-Polish (E-P) parallel corpus PHRAVERB. Given the semantic idiosyncrasy exhibited by phrasal verbs, it is assumed that the equivalents generated by PHRAVERB will often differ from those found in E-P dictionaries. The qualitative corpus analysis aims to show that arriving at the desirable Polish counterpart involves a detailed semantic breakdown of the English structure, a careful analysis of the context in which it is used, as well as linguistic and translation skills, necessary to detect the nuances and subtleties of meaning in both languages. PHRAVERB is used to analyze the lexicographic potential (LP) of corpus equivalents. Four levels of LP have been established – high, average, low and zero – to evaluate which corpus-derived equivalents are eligible for inclusion in E-P dictionaries. To this end, 2,514 occurrences of PVs in the parallel corpus, with their equivalents, have been identified and analyzed.

In this paper we present a method for term extraction that can be used in classroom with translation students. The terms are extracted from a multilingual parallel corpus with the aid of a parallel concordancer, AntPConc. Our work is focused on English-Greek medical terminology translation, but the method can be transferred to other language pairs and other fields of terminology.

Rafael guzmán tiRado iRina a. VotyakoVa (ed.) gRanada 2013 tipología léxica cualquier forma de reproducción, distribución, comunicación pública o transformación de esta obra sólo puede ser realizada con la autorización de sus titulares, salvo excepción prevista por la ley. Diríjase a CEDRO (Centro Español de Derechos Reprográficos www.cedro.org), si necesita fotocopiar o escanear algún fragmento de esta obra. © los autoRes.

The paper discusses the main trends in the development of the parallel corpora within the RNC since 2015. The New languages section deals with seven new language pairs that emerged during this period, their architecture and tagging.
Compared with the list of languages that form bilingual parallel pairs with Russian available in 2015, the following new languages have appeared in the RNC: Bashkir, Buryat, Chinese, Czech, Finnish, Lithuanian, Swedish. Creating the parallel subcorpora comes as the combined efforts of autonomous Russian and foreign teams coordinated by the team of developers of the RNC in Moscow. Virtually all the new languages offer specific challenges for the Corpus developers with regard to their annotation. The size of some of the language pairs already available in 2015 has also significantly increased in four years.
The New challenges section goes further to explore some general trends of parallel corpora across different language pairs such as regional/national language varieties, representativeness with regard to text genres, new annotation and search types etc. At the present stage,
both due to an increase in the typological diversity of the languages and scripts involved, and through the use of more complex morphological analyzers, the set of additional markup parameters has been significantly expanded. The purpose of incorporating polycentric language samples into the corpus has become one of the most important. The genre representativeness of corpora, which was only being planned in 2015, is one of the main goals in 2019, and this goal is taken into account from the very beginning of the creation of new language pairs.
A case study is dedicated to studying pluperfect in 24 languages of Europe in an expanded multilingual corpus. The analysis of a multilingual text based on the material of an extended collection allows us to construct a network of distances between the data for the Pluperfect category in 24 European languages/lects.

The article presents the analysis of etiquette formulas (forms of address, greetings and farewells) used between teachers of Russian as a foreign language and students studying Russian outside Russia. the survey was conducted among 100 teachers of Russian as a foreign language from 30 countries. the authors also analyze examples of the use of speech etiquette in parallel corpora and validate the pragmatics against a number of well-established dictionaries of the Rus-sian language. the authors conclude that during speech acts, different linguistic pictures of the world and the norms of language politeness of teachers and students influence each other. the authors observed the culturally conditioned lacunarity of the forms of address and cases of substitution of speech etiquette. the obtained results of the study can be explained by the dynamic development of Russian speech etiquette and the lack of stable norms that can be offered to students in the teaching process.

"This article presents a corpus-based study of the metaphorical and metonymical use of the words "head" and "heart," together with the Norwegian correspondents "hode" and "hjerte." The continuum between metaphor and metonymy is explored, as well as the extent to which the non-literal expressions containing "head"/"heart" and "hode"/"hjerte" correspond to each other. The data analyzed is gathered from the English-Norwegian Parallel Corpus.
It is necessary to differentiate various meanings of these expressions in order to pinpoint cross-linguistic similarities and differences. Although a relatively high degree of mutual correspondence is found, the relationship is said to be asymmetrical, especially as regards "head"/"hode", since English seems to employ more metaphorical meanings of this lexeme."

摘要：
最近几十年，语料库语言学已成为现代应用语言学的支柱。因此，本文的宗旨是更深入地探讨语料库建设的一些认知性和操作性的步骤，以便把语料库观念向广大的研究人员推广。本文主要分为三个部分：
1. 语料库建设：理论与实践
2. 语料文本的加工层面
3. 语料格式属性的标注
第一部分探讨语料库语言学作为新学科发展的必要性，即从讨论学科的理论观念阶段进一步发展到应用的阶段，容纳最近该学科在工作方法论上所发生的新变化。在这个范围内，本文先探讨语料库语言学的定义和语料库的类型，目的是想确定一些更细致、可靠的语料库分类标准，以及所引出的语料库建设需求。
第二部分探讨语料库建设筹备阶段的语料加工层面，这部分又分三个部分：其一，语料文本的来源。详细地讨论文本的两种来源——纸质文本和电子文本；其二，现存的电子文本形式；其三，语料规范的不同层次。主要讨论四种层次：1-语料收取和记录语料库编纂有关的信息，2-文本储存阶段，3-文本转换阶段，4-选取语料样本阶段 。
第三部分探讨语料库建设中的语料格式属性标注，集中讨论双语语料库的建设，因为该语料库是应用语言学的基石，把实际运用的语言作为出发点来进行不同方面的应用研究，如翻译学、辞典编纂学、外语教学等。

关键词：语料库、语料加工、计算机语料库、计算机语料库规范问题、语料格式属性标注、XML语言与语料格式属性标注、汉阿对齐语料库、汉阿对应语料库。

В статье рассматривается на корпусном материале русская конструкция типа пошёл было в сопоставлении с белорусским плюсквамперфектом (форма типа пайшоў быў). Выявлены некоторые особенности менее изученной белорусской формы -прежде всего, формальные и семантические архаизмы по сравнению с русским было, а также особенности семантической сочетаемости. Особо рассмотрены условия появления той или иной формы, связанные с «вольностью» в переводе.

This paper presents a bilingual corpus-based study of the use of several nouns meaning ‘time’ or time units (‘hour’, ‘minute’, ‘moment’) in Bulgarian and Ukrainian. All matching instances of these words in a collection of parallel texts consisting of original Bulgarian and Ukrainian fiction as well as translations from two other Slavic languages (Polish and Russian) were sought out, separating the uses of the singular and the plural where appropriate. The main question is what we can learn by comparing the frequencies of the various correspondences of Bulgarian and Ukrainian words.

In this thesis we describe and evaluate a tool for automatic generation of translations for multiword English terms into Spanish from a monolingual specialized Spanish corpus, compiled by means of web crawling. The resulting translations may be further used to expand or to revise the existing lexicographic resources, i.e. language for specific purposes dictionaries, terminological databases and translation memories. We evaluate the output with the precision and recall metrics and apply our approach to the small English-Spanish glossary in the legal domain that serves both as a reference dictionary and a source for input multiword terms. We analyze the obtained results and suggest possible solutions to the detected problems based on the theoretical part of this research devoted to the issues of machine translation, the use of dictionaries and corpora (non-parallel corpora in particular) for machine translation tasks, and the works on automatic terminology extraction.

The paper reports on a study based on the data drawn from such a corpus. The aim of the study was to find and examine the closest Polish translation equivalents of two semantically related verbs in Czech. The author starts with the analysis of the equivalents found in a traditional Czech-Polish dictionary and then compares her results with the citation from form InterCorp, described in detail in Chapters 1 and 2. The author also attempts to automatically profile the located equivalents and concludes that the data is not sufficient for applying the Word Sketch analysis,  thus instead she conducts this analysis manually. In the last sections of the chapter Kaczmarska puts her analysis in a lager perspective by presenting her research aiming at establishing an algorithm facilitating excerption of translation equivalents of verbs expressing emotion.

This paper concentrates on the verbal moods used after Spanish adverbs expressing potentiality (quizá(s), tal vez, probablemente, posiblemente). With the use of the corpus CREA, we sought to determine whether there is a preference for either the indicative or subjunctive after each adverb, and, consequently, whether a reason for the preference of either mood exists. With the assistance of the parallel corpus InterCorp we have been able to present a summary of Czech translations of these grammatical constructions, in order to show the possibilities of reflecting the semantic difference between Spanish subjunctive and indicative in Czech. Based upon these observations it is possible to create a scale that compares potentiality in Czech and Spanish.

We report on a project to annotate biblical texts in order to create an aligned multilingual Bible corpus for linguistic research, particularly computational linguistics, including automatically creating and evaluating translation lexicons and semantically tagged texts. The output of this project will enable researchers to take advantage of parallel translations across a wider number of languages than previously available, providing, with relatively little effort, a corpus that contains careful translations and reliable alignment at the near-sentence level. We discuss the nature of the text, our annotation process, preliminary and planned uses for the corpus, and relevant aspects of the Corpus Encoding Standard (CES) with respect to this corpus. We also present a quantitative comparison with dictionary and corpus resources for modern-day English, confirming the relevance of this corpus for research on present day language.

We present HindEnCorp, a parallel corpus of Hindi and English, and HindMonoCorp, a monolingual corpus of Hindi in their release version 0.5. Both corpora were collected from web sources and preprocessed primarily for the training of statistical machine translation systems. HindEnCorp consists of 274k parallel sentences (3.9 million Hindi and 3.8 million English tokens). HindMonoCorp amounts to 787 million tokens in 44 million sentences. Both the corpora are freely available for non-commercial research and their preliminary release has been used by numerous participants of the WMT 2014 shared translation task.

La lingüística histórica, en su camino hacia la consagración como disciplina autónoma, no ha podido, o no ha querido, distanciarse de las corrientes anejas que transitan y evolucionan en el seno de una lingüística más general y abarcadora. Dentro de esa corriente se encuentra la denominada Lingüística de corpus, marco en el que, desde hace no mucho más de veinte años, viene desarrollándose una nueva corriente de estudio de raigambre anglosajona denominada Corpus-based Translation Studies (CTS). Los estudios fundamentados en esta relativamente nueva disciplina se orientan a la consideración y análisis de hechos de lengua contemporáneos, tal y como cabría esperar dada su relación con la lingüística de corpus. En este artículo se describirán los postulados más interesantes de los trabajos amparados en las teorías y métodos de los CTS y, desde una perspectiva crítica, se insistirá en la dimensión histórica de las lenguas y en los aspectos discursivo-tradicionales muchas veces olvidados o interesadamente obviados en pos del establecimiento de leyes o reglas universales que den validez al paradigma teórico propuesto.

Canonical question tags feature prominently in spoken English, where they display great versatility. At face value they are meant to elicit a response from a co-participant in the form of (dis)agreement with the proposition to which the tag has been added. Their pragmatic scope is, however, considerably broader: they serve as politeness strategies but also emphasize the speaker's convictions or mark accusations. Like many other languages, Dutch does not have a similar structure, which raises questions as to what devices Dutch employs to serve the same purpose as question tags. This contrastive study examines such correspondents in a parallel corpus of English novels and their Dutch translations. Three structures can be identified: pragmatic markers, clause-final parentheticals and combinations of these. The data indicate a preference for pragmatic markers (most notably "hè" and "toch"), which predominantly appear either as invariant tags or clause-medially, indicating subtle shifts in utterance interpretation.

يُعْتَبَر علم الذخائر اللغوية من العلوم اللغوية التأسيسية التي تُرَسِّخْ مفهوم دراسة اللغة في بيئتها الطبيعية، بعيدًا عن القياس اللغوي المنطقي الذي ساد في حقل الدراسات اللغوية قرونًا عدة. إن علم الذخائر اللغوية، الذي أَسَّسَ له عالم اللغة الإنجليزي ليتش (Leech)( ) في النصف الثاني من القرن العشرين، هو علم يبحث في كيفية جمع النصوص اللغوية الطبيعية وتهيئتها وترميزها؛ بحيث تكون صالحة للبحث اللغوي ودراسة الظواهر اللغوية الطبيعية على مستوى أفرع علم اللغة بنظرياته وتطبيقاته الحديثة. يحتل علم الذخائر اللغوية، باعتباره إحدى المنهجيات التي تمهد لدراسة اللغة الطبيعية بشكل موضوعي، مكانة متقدمة في حقل اللسانيات الحديثة. ولا غنى للباحث اللغوي عن التعرف على مفاهيم هذا العلم وفنياته وتطبيقاته، بل وطُرُق بناء الذخائر اللغوية بأحجامها المختلفة لخدمة أغراض بحثية معينة.
فالذخيرة اللغوية، وفقًا لمفاهيم علم الذخائر اللغوية، هي بناء لغوي يتمتع بمواصفات ومعايير فنية تجعله قادرًا على استيعاب النصوص اللغوية وإتاحتها للبحث اللغوي العام والخاص. وينبغي أن تخضع النصوص اللغوية التي يحتويها هذا البناء إلى قواعد معينة من حيث أساليب الجمع، ونِسَب التمثيل، وطرق المعالجة قبل عملية الجمع وبعدها، ومنهجيات الترميز والأساليب التي يتم على أساسها عمليات الاستعلام والاستدعاء حسب متطلبات البحث اللغوي...

We report on a project to annotate biblical texts in order to create an aligned multilingual Bible corpus for linguistic research, particularly computational linguistics, including automatically creating and evaluating translation lexicons and semantically tagged texts. The output of this project will enable researchers to take advantage of parallel translations across a wider number of languages than previously available, providing, with relatively little effort, a corpus that contains careful translations and reliable alignment at the near-sentence level. We discuss the nature of the text, our annotation process, preliminary and planned uses for the corpus, and relevant aspects of the Corpus Encoding Standard (CES) with respect to this corpus. We also present a quantitative comparison with dictionary and corpus resources for modern-day English, confirming the relevance of this corpus for research on present day language.

Accessing historical texts is often a challenge because readers either do not know the historical language, or they are challenged by the technological hurdle when such texts are available digitally. Merging corpus linguistic methods and digital technology can provide novel ways of representing historical texts digitally and providing a simpler access. In this paper, we describe a  multi-dimensional parallel Old Occitan-English corpus, in which word alignment serves as the basis for search capabilities as well as for the transfer of annotations.  We show how parallel alignment can help overcome some challenges of historical manuscripts.  Furthermore, we apply a resource-light method of building an emotion annotation via parallel alignment, thus showing that such annotations are possible without speaking the historical language. Finally, using visualization tools, such as ANNIS and GoogleViz, we demonstrate how the emotion analysis can be queried  and visualized dynamically in our parallel corpus, thus showing that such information can be made accessible with low technological barriers.

The sentences in the RNC are aligned sentence -by -sentence. The texts kindly offered for the use in the RNC by Adrian Barentsen and included into the Amsterdam Slavic Parallel Aligned Corpus multilingual corpus are already aligned paragraph -by -paragraph. This segmentation has been additionally refined by us semi -automatically, introducing boundaries between the sentences within these pre -defined paragraphs. For the majority of the texts the alignment is undertaken completely by the RNC team. The original text's sentence segmentation overrides the segmentation in the translation. So, each single element of parallel tagging corresponds to the original sentence, whilst its translated counterpart(s) may well be either a part of a sentence starting with a space or a comma, or more than one sentence.

Contrastive methods have long been employed in lexicography, in particular in bi-and multilingual dictionary projects. The main rationale for this is the necessity to comprehensively study, i.e. compare and contrast, two or more linguistic systems that are to be presented in one way or another in respective dictionaries. Similarly, the contrastive approach is of paramount importance in terminographic undertakings, on account of the need to draw a distinction between terminological (conceptual) systems existing in various languages and across cultures. It must be emphasised, however, that the contrastive element is not only a part of terminographic practice, but also of the theory of terminography. This article aims to present the role of contrastive research across various spheres of specialised (=LSP) lexicography.

The ACTRES Parallel Corpus (P-ACTRES 2.0) is a bidirectional English-Spanish corpus developed by ACTRES research group. P-ACTRES 2.0 contains over 4 million words both directions. From original English texts to their Spanish translations, the former P-ACTRES 1.0 (Izquierdo, Hofland & Reigem, 2008), is about 2,5 million, and from original Spanish texts to their English translations, 1.5 million words. P-ACTRES includes 5 subcorpora: books-fiction, books-nonfiction, newspaper articles, magazine articles and miscellaneous. P-ACTRES 2.0 allows users to carry out corpus-based linguistic and textual contrast as well as Translation Studies projects either independently or jointly. It has proved to be a useful tool for studies at both lexico-grammatical and rhetorical level. Technically, P-ACTRES 2.0 was designed by Knut Holland (University of Bergen). It employs Corpus Workbench (CWB) (Stefan & Hardie, 2011) for managing and querying and Treetagger for POS annotation (Schmid, 1995). Textual pairs were aligned employing TCA2 (Hofland & Johansson, 1998) and subsequently checked manually. P-ACTRES 2.0 is an upgrade from P-ACTRES 1.0 developed by Hugo Sanjurjo-González (University of León) in collaboration with Knut Hofland to house new repositories. It has been designed using HTML5 ("HTML5", 2014) technology as well as JavaScript and Perl script files in order to show results of corpus queries and related statistics. Further work on the P-ACTRES 2.0 features new annotation layers, supporting of n-grams queries and more sophisticated statistics based on R programming language ("R Core Team", 2013).

Automatic extraction of bilingual lexicons from parallel corpora has been recently exploited to overcome the knowledge acquisition bottleneck in a number of research areas in natural language processing, such as machine translation (MT) and cross-language information retrieval. In this paper the author presents a method for automatic extraction of bilingual lexicons from a parallel Arabic-English corpus annotated with part-of-speech tags for potential use in a full-scale MT system. The extraction method, which does not make use of an initial bilingual dictionary, is based on the statistical technique of co-occurrence frequency in the parallel corpus. In addition, dependency relations for some parallel syntactic constructions are made use of to automatically extract head-dependent translation pairs which are then filtered to obtain one-word translation seeds. These seeds are used as anchor points to resegment the parallel corpus in order to bootstrap the lexicon extraction process. Experimental results show that the accuracy of the extracted lexicons was improved after applying the bootstrapping techniques.

This paper describes the first phase of the CEXI project at the University of Bologna in Forlì, involving the selection of the texts to be included in the corpus and decisions about the processing of these texts. The aim of the project is to create a resource which can be used by both students and researchers to learn about translation and translating. The English Italian Translational Corpus can be described as a bi-directional, parallel, translation-driven corpus, which in its core component will consist of about 4.6 million words, or 368 text samples of 10 to 15 thousand words each, from Italian original texts and their translations into English and vice versa, published between 1975 and 2000. The core corpus will subsequently be flanked with additional unidirectional parallel collections which will better reflect the specific characteristics of the two very different translation populations sampled, as well as expanded to include full texts and text types excluded from the core component. The paper deals with issues such as representativeness, balance and directionality with respect to the Italian and English language book publishing sector, detailing the composition of the different sub-components of CEXI, and showing that the creation of a corpus involves a series of compromises between what is ideally desirable and what is possible given practical and theoretical limitations.

The paper describes semantic properties of Perfect forms in European languages exemplified by a massive parallel corpus. A NeighbourNet distance graph for European Perfects is built. In a separate section, the English Perfect in the Russian-English parallel texts is discussed.

This study will examine the prefixed derivates from the verb of motion (VoM) ходить and analyse their translations to German by focusing on the problem of determining the correct meaning of individual forms and possible irregularities in the translation.

The study shows that prefixed verbs that are otherwise identical can be homonyms with meanings that are independent from each other. This is because of the different grammatical and lexical processes that have accordingly led to an ambiguous form.

The goal of this thesis is to begin by illustrating the problem of homonymy of forms caused by aspect and aktionsart. After having done so, the issue will be considered in light of the problems that can arise in the comprehension and translation of homonymous forms by analysing actual text material from Russian text corpora. I will endeavour to locate regularities in their translation and thereby examine the demands on theory and corpora.

The analysis will also investigate how effectively the theoretical background of Isačenko’s theory on aspect and aktionsart can be applied to corpus linguistics.

This paper presents a comparison between Russian prefixed verbs of memory and their Italian equivalent. In particular, analysing a Russian-Italian parallel corpus, we observed the strategies used for the translation of these verbs from Russian into Italian, expecting that in some cases a certain loss of information might be registered.

Research in the Humanities is predominantly text-based. For centuries scholars have studied documents such as historical manuscripts, literary works, legal contracts, diaries of important personalities, old tax records etc. Manual analysis of such documents is still the dominant research paradigm in the Humanities. However, with the advent of the digital age this is increasingly complemented by approaches that utilise digital resources. More and more corpora are made available in digital form (theatrical plays, contemporary novels, critical literature, literary reviews etc.). This has a potentially profound impact on how research is conducted in the Humanities. Digitised sources can be searched more easily than traditional, paper-based sources, allowing scholars to analyse texts quicker and more systematically. Moreover, digital data can also be (semi-)automatically mined: important facts, trends and interdependencies can be detected, complex statistics can be calculated and the results can be visualised and presented to the scholars, who can then delve further into the data for verification and deeper analysis. Digitisation encourages empirical research, opening the road for completely new research paradigms that exploit `big data' for humanities research. This has also given rise to Digital Humanities (or E-Humanities) as a new research area. Digitisation is only a first step, however. In their raw form, electronic corpora are of limited use to humanities researchers. The true potential of such resources is only unlocked if corpora are enriched with different layers of linguistic annotation (ranging from morphology to semantics). While corpus annotation can build on a long tradition in (corpus) linguistics and computational linguistics, corpus and computational linguistics on the one side and the Humanities on the other side have grown apart over the past decades. We believe that a tighter collaboration between people working in the Humanities and the research community involved in developing annotated corpora is now needed because, while annotating a corpus from scratch still remains a labor-intensive and time-consuming task, today this is simplified by intensively exploiting prior experience in the field. Indeed, such a collaboration is still quite far from being achieved, as a gap still holds between computational linguists (who sometimes do not involve humanists in The ACRH-2 Co-Chairs and Organisers

In this paper we describe an alignment system that aligns English-Hindi texts at the sentence and word level in parallel corpora. We describe a simple sentence length approach to sentence alignment and a hybrid, multi-feature approach to perform word alignment. We use regression techniques in order to learn parameters which characterise the relationship between the lengths of two sentences in parallel text. We use a multi-feature approach with dictionary lookup as a primary technique and other methods such as local word grouping, transliteration similarity (edit-distance) and a nearest aligned neighbours approach to deal with many-to-many word alignment. Our experiments are based on the EMILLE (Enabling Minority Language Engineering) corpus. We obtained 99.09% accuracy for many-to-many sentence alignment and 77% precision and 67.79% recall for many-to-many word alignment.

The present Ph. D. thesis deals with the so-called grey areas that can be found within the Spanish modal
system. In these areas, two different types of modality (modal meanings) can occur. We study
the relationship that can be found between potentiality and reality, potentiality and evaluation,
evaluation and volition, volition and question, question and potentiality, potentiality and volition.
We analyse the different types of interaction between modal meanings inside the Spanish modality
and study the consequences of those interactions.