In this thesis, we mainly investigate the influence of using unsupervised morphological segmentation as features on the dependency parsing of morphologically rich languages such as Finnish, Estonian, Hungarian, Turkish, Uyghur, and Kazakh. Studying the morphology of these languages is of great importance for the dependency parsing of morphologically rich languages since dependency relations in a sentence of these languages mostly rely on morphemes rather than word order. In order to investigate our research questions, we have conducted a large number of parsing experiments both on MaltParser and UDPipe. We have generated the supervised morphology and the predicted POS tags from UDPipe, and obtained the unsupervised morphological segmentation from Morfessor, and have converted the unsupervised morphological segmentation into features and added them to the UD treebanks of each language. We have also investigated the different ways of converting the unsupervised segmentation into features and studied the result of each method. We have reported the Labeled Attachment Score (LAS) for all of our experimental results. The main finding of this study is that dependency parsing of some languages can be improved simply by providing unsupervised morphology during parsing if there is no manually annotated or supervised morphology available for such languages. After adding unsupervised morphological information with predicted POS tags, we get improvement of 4.9%, 6.0%, 8.7%, 3.3%, 3.7%, and 12.0% on the test set of Turkish, Uyghur, Kazakh, Finnish, Estonian, and Hungarian respectively on MaltParser, and the parsing accuracies have been improved by 2.7%, 4.1%, 8.2%, 2.4%, 1.6%, and 2.6% on the test set of Turkish, Uyghur, Kazakh, Finnish, Estonian, and Hungarian respectively on UDPipe when comparing the results from the models which do not use any morphological information during parsing.

IsiXhosa language is one of the eleven official languages and the second most widely spoken language in South Africa. However, in terms of computational linguistics, the language did not get attention and natural language related work is almost non-existent. Document retrieval using unstructured queries requires some kind of language processing, and an efficient retrieval of documents can be achieved if we use a technique called stemming. The area that involves document storage and retrieval is called Information Retrieval (IR). Basically, IR systems make use of a Stemmer to index document representations and also terms in users’ queries to retrieve matching documents. In this dissertation, we present the developed Stemmer that can be used in both conditions. The Stemmer is used in IR systems, like Google to retrieve documents written in isiXhosa. In the Eastern Cape Province of South Africa many public schools take isiXhosa as a subject and also a number of Universities in South Africa teach isiXhosa. Therefore, for a language important such as this, it is important to make valuable information that is available online accessible to users through the use of IR systems. In our efforts to develop a Stemmer for the isiXhosa language, an investigation on how others have developed Stemmers for other languages was carried out. From the investigation we came to realize that the Porter stemming algorithm in particular was the main algorithm that many of other Stemmers make use of as a reference. We found that Porter’s algorithm could not be used in its totality in the development of the isiXhosa Stemmer because of the morphological complexity of the language. We developed an affix removal that is embedded with rules that determine which order should be followed in stripping the affixes. The rule is that, the word under consideration is checked against the exceptions, if it’s not in the exceptions list then the stripping continue in the following order; Prefix removal, Suffix removal and finally save the result as stem. The Stemmer was successfully developed and was tested and evaluated in a sample data that was randomly collected from the isiXhosa text books and isiXhosa dictionary. From the results obtained we concluded that the Stemmer can be used in IR systems as it showed 91 percent accuracy. The errors were 9 percent and therefore these results are within the accepted range and therefore the Stemmer can be used to help in retrieval of isiXhosa documents. This is only a noun Stemmer and in the future it can be extended to also stem verbs as well. The Stemmer can also be used in the development of spell-checkers of isiXhosa.

No description available.

No description available.

This thesis examines the intonation patterns of Modern Greek with regard to different interpretations of the sentence types (declarative, interrogative, imperative). 14 utterances are produced by Greek native speakers (2 men and 2 women) so as to express various speech acts: STATEMENT, QUESTION, COMMAND and REQUEST. The acquisition of the F0 curve for each utterance by means of the Wavesurfer tool leads to an analysis of the pitch movements and their alignments. After the F0 curves are analyzed and illustrated using the Excel program we are able to compare and group them. Thus, we come up with 5 different intonation patterns. After a second-level comparison based on the fact that some of the F0 curves were similar but they differed only as far as the final pitch movement is concerned, we ended up with 3 fundamental categories of intonation patterns: Category I whose main feature is the rising pitch movement aligned to the onset of the stressed syllables. This category includes only sentences that denote Statement so we can call it the STATEMENT category. Category II’s main characteristic is a dipping pitch movement aligned to the head of the utterance that is the stress of the verb or a particle that signifies negation (/min/, /den/). Sentences meaning Command or Request belong to this category. Lastly, Category III’s intonation pattern consists of peaking pitch movements aligned to the initial and final stressed syllables. Interrogative sentences belong to this category no matter their interpretation. A secondary goal of the thesis is to examine to which extent intonation can be a safe criterion for the “correct” interpretation of a sentence. A de facto presumption that since the ratio between the number of utterances (14) and the different intonation patterns (5) is not 1:1 there can always be misunderstandings among speakers, is basically verified by the results of our perception test conducted to Greek native speakers: Greek native speakers were able to identify most of the speech acts that were expressed by the most common (default) sentence type (i.e. imperative sentence for COMMAND and interrogative for QUESTION) however there were combinations that they had difficulties to identify, such as interrogative sentences that were denoting other than QUESTION, e.g. REQUEST or STATEMENT.Ending, a perception test conducted to Flemish speakers (subjects that were native speakers of another language than Greek) showed that they were more successful in sentences that meant STATEMENT and QUESTION but they could hardly identify an interrogative sentence that meant other than QUESTION and they also confused between COMMAND and REQUEST. This implies that the intonation used to convey different interpretations is basically language-dependent. Concluding, this study offers a description of the intonation patterns (based on pitch movements) regarding the 3 sentence types with 4 different interpretations. Our findings prove that the intonation for some cases (i.e. for sentences that express COMMAND or STATEMENT) seems to be structure-independent and for others structure-dependent (cf. the interrogative sentences). Additionally, the fact that the negation can play an important role for the choice of intonation pattern (as shown for the case of COMMAND and STATEMENT) could be considered as a structure-dependent feature of intonation. This approach contrasts the approach used for many years in the traditional Grammar according to which the structure alone (sentence type) defines the meaning that is to be conveyed.

No description available.

I denna rapport presenteras ett sätt att detektera handskrivna ordobjekt i inskannade dokument. Rapporten belyser också några av de problem som förekommer vid detektion av handskrivna ordobjekt. Detektionen görs med hjälp av en indelning av bilden i rektangulära regioner. Därefter används enmaskininlärningsalgoritm för att klassificera regionerna som antingen handskriven text eller övrigt. För att klassificera en region behövs mätvärden för en region, såsom area, som en algoritm kan använda. De flesta som testas och används i denna rapport har använts tidigare för att detektera handskriven text. En del är modifierade från tidigare använda mätvärden. Resultaten visar att att det går att detektera handskrivna ordobjekt med en föreslagna metoden. Resultaten är dock inte lika goda som flertalet andra inom området, några olika orsaker diskuteras. Rapporten visar även att klassificeringen av en region får ett statistiskt signifikant högre resultat om algoritmen som använts har tränats på andra regioner i samma dokument. Detta resultat är viktigt när en algoritm ska utvärderas. Att viktning av träningsdata kan användas för att manipulera precision och recall för de fyra algoritmer som används bekräftas. Detta gör det möjligt att skapa ett precision-recall-diagram för att jämföra olika maskininlärningsalgoritmer. En sådan jämförelse mellan fyra olika typer av algoritmer visar att det är liten skillnad mellan två beslutsträd och ett neuralt nätvärk. Den sista algoritmen, en stödvektormaskin, klarade uppgiften sämst.

På svenska myndigheter arbetar man aktivt med att erbjuda sina kunder möjligheter att göra ärenden via Internet. Försäkringskassans egna studier tyder dock på att personer som inte har svenska som modersmål är en grupp som i stället väljer att komma in på kontoren för att utföra sina ärenden, även om ärendena är relativt enkla. Den här studien undersöker hur språkteknologiska hjälpmedel skulle kunna underlätta för den här gruppen att använda tjänster på Internet. För att ta reda på hur nysvenskar själva ser på sin kontakt med myndigheter hölls fokusgrupper där deras erfarenheter diskuterades. Fokusgrupperna resulterade i tre scenarier som illustrerar hur situationer där en person med språksvårigheter försöker göra sina ärenden på Internet skulle kunna se ut. Några olika språkteknologiska verktyg och hur de skulle kunna användas på Internet diskuteras mot bakgrund av scenarierna. För ett av verktygen, automatisk sammanfattning, utfördes en användarundersökning där sammanfattningar framställda med ett automatiskt sammanfattningsprogram jämfördes. Användning av textsammanfattning som stöd för nysvenskars användning av e-tjänster analyseras och diskuteras.

The subject of this thesis covers a considerably varied multidisciplinary area which needs to be addressed to be able to achieve a text-to-speech synthesis system of high quality, in any language. This is the first time that such a system has been built for Maltese, and therefore, there was the additional problem of no computerised sources or corpora. However many problems and much of the system designs are common to all languages. This thesis focuses on two general problems. The first is that of automatic labelling of phonemic data, since this is crucial for the setting up of Maltese speech corpora, which in turn can be used to improve the system. A novel way of achieving such automatic segmentation was investigated. This uses a mixed parameter model with maximum likelihood training of the first derivative of the features across a set of phonetic class boundaries. It was found that this gives good results even for continuous speech provided that a phonemic labelling of the text is available. A second general problem is that of segment concatenation, since the end and beginning of subsequent diphones can have mismatches in amplitude, frequency, phase and spectral envelope. The use of-intermediate frames, build up from the last and first frames of two concatenated diphones, to achieve a smoother continuity was analysed. The analysis was done both in time and in frequency. The use of wavelet theory for the separation of the spectral envelope from the excitation was also investigated. The linguistic system modules have been built for this thesis. In particular a rule based grapheme to phoneme conversion system that is serial and not hierarchical was developed. The morphological analysis required the design of a system which allowed two dissimilar lexical structures, (semitic and romance) to be integrated into one overall morphological analyser. Appendices at the back are included with detailed rules of the linguistic modules developed. The present system, while giving satisfactory intelligibility, with capability of modifying duration, does not include as yet a prosodic module.

No description available.