The objective of this thesis is to reduce the training size for the Mandarin address inputting system and the Mandarin phrase recognition system. A set of two-word Mandarin phrases is developed by the balanced sieving and mixture training techniques. This greatly reduces the training data size for the systems. Hidden Markov model using both MFCC and LPCC features is proposed in this thesis. Speech-text alignment, frame overlapping and tone recognition are incorporated to increase the correct recognition rates. For the speaker-dependent case, any phrase in these two speech systems can be recognized within one second.

A system of Chinese resume by speech construction is developed by the use of a novel segmentation mechanism and the classical Hidden Markov Model. The recognition system is based on both mono-syllable HMM's and speech-text alignment schemes. Experimental results indicate that the amount of training materials used for feature extraction can be greatly reduced, and the text content of the recorded speech training data can be different from those of the recognition tasks as well. Each phrase in the resume can be identified within one second, that is approximately the same as the graduate did last year. Furthermore, the user interface of the resume system has been redesigned and polished by the GTK toolkit in order to enable event-driven X-window operations.

The majority of the world's languages are poorly represented in informational media like radio, television, newspapers, and the Internet. Translation into and out of these languages may offer a way for speakers of these languages to interact with the wider world, but current statistical machine translation models are only effective with a large corpus of parallel texts - texts in two languages that are translations of one another - which most languages lack. This thesis describes the Babylon project which attempts to alleviate this shortage by supplementing existing parallel texts with texts gathered automatically from the Web -- specifically targeting pages that contain text in a pair of languages. Results indicate that parallel texts gathered from the Web can be effectively used as a source of training data for machine translation and can significantly improve the translation quality for text in a similar domain. However, the small quantity of high-quality low-density language parallel texts on the Web remains a significant obstacle.

The usefulness of digitized documents is directly related to the quality of the extracted text. Optical Character Recognition (OCR) has reached a point where well-formatted and clean machine- printed documents are easily recognizable by current commercial OCR products; however, older or degraded machine-printed documents present problems to OCR engines resulting in word error rates (WER) that severely limit either automated or manual use of the extracted text. Major archives of historical machine-printed documents are being assembled around the globe, requiring an accurate transcription of the text for the automated creation of descriptive metadata, full-text searching, and information extraction. Given document images to be transcribed, ensemble recognition methods with multiple sources of evidence from the original document image and information sources external to the document have been shown in this and related work to improve output. This research introduces new methods of evidence extraction, feature engineering, and evidence combination to correct errors from state-of-the-art OCR engines. This work also investigates the success and failure of ensemble methods in the OCR error correction task, as well as the conditions under which these ensemble recognition methods reduce the Word Error Rate (WER), improving the quality of the OCR transcription, showing that the average document word error rate can be reduced below the WER of a state-of-the-art commercial OCR system by between 7.4% and 28.6% depending on the test corpus and methods. This research on OCR error correction contributes within the larger field of ensemble methods as follows. Four unique corpora for OCR error correction are introduced: The Eisenhower Communiqués, a collection of typewritten documents from 1944 to 1945; The Nineteenth Century Mormon Articles Newspaper Index from 1831 to 1900; and two synthetic corpora based on the Enron (2001) and the Reuters (1997) datasets. The Reverse Dijkstra Heuristic is introduced as a novel admissible heuristic for the A* exact alignment algorithm. The impact of the heuristic is a dramatic reduction in the number of nodes processed during text alignment as compared to the baseline method. From the aligned text, the method developed here creates a lattice of competing hypotheses for word tokens. In contrast to much of the work in this field, the word token lattice is created from a character alignment, preserving split and merged tokens within the hypothesis columns of the lattice. This alignment method more explicitly identifies competing word hypotheses which may otherwise have been split apart by a word alignment. Lastly, this research explores, in order of increasing contribution to word error rate reduction: voting among hypotheses, decision lists based on an in-domain training set, ensemble recognition methods with novel feature sets, multiple binarizations of the same document image, and training on synthetic document images.

Translation alignment is an essential task in Digital Humanities and Natural Language Processing, and it aims to link words/phrases in the source text with their translation equivalents in the translation. In addition to its importance in teaching and learning historical languages, translation alignment builds bridges between ancient and modern languages through which various linguistics annotations can be transferred. This thesis focuses on word-level translation alignment applied to historical languages in general and Ancient Greek and Latin in particular. As the title indicates, the thesis addresses four interdisciplinary aspects of translation alignment. The starting point was developing Ugarit, an interactive annotation tool to perform manual alignment aiming to gather training data to train an automatic alignment model. This effort resulted in more than 190k accurate translation pairs that I used for supervised training later. Ugarit has been used by many researchers and scholars also in the classroom at several institutions for teaching and learning ancient languages, which resulted in a large, diverse crowd-sourced aligned parallel corpus allowing us to conduct experiments and qualitative analysis to detect recurring patterns in annotators’ alignment practice and the generated translation pairs. Further, I employed the recent advances in NLP and language modeling to develop an automatic alignment model for historical low-resourced languages, experimenting with various training objectives and proposing a training strategy for historical languages that combines supervised and unsupervised training with mono- and multilingual texts. Then, I integrated this alignment model into other development workflows to project cross-lingual annotations and induce bilingual dictionaries from parallel corpora. Evaluation is essential to assess the quality of any model. To ensure employing the best practice, I reviewed the current evaluation procedure, defined its limitations, and proposed two new evaluation metrics. Moreover, I introduced a visual analytics framework to explore and inspect alignment gold standard datasets and support quantitative and qualitative evaluation of translation alignment models. Besides, I designed and implemented visual analytics tools and reading environments for parallel texts and proposed various visualization approaches to support different alignment-related tasks employing the latest advances in information visualization and best practice. Overall, this thesis presents a comprehensive study that includes manual and automatic alignment techniques, evaluation methods and visual analytics tools that aim to advance the field of translation alignment for historical languages.