We present an extensive empirical comparison of several smoothing techniques in the domain of language modeling, including those described by Jelinek and Mercer (1980), Katz (1987), and Church and Gale (1991). We investigate for the first time how factors such as training data size, corpus (e.g., Brown versus Wall Street Journal), and n-gram order (bigram versus trigram) affect the relative performance of these methods, which we measure through the cross-entropy of test data. In addition, we introduce two novel smoothing techniques, one a variation of Jelinek-Mercer smoothing and one a very simple linear interpolation technique, both of which outperform existing methods. 1

Many multilingual NLP applications need to translate words between different languages, but cannot afford the computational expense of inducing or applying a full translation model. For these applications, we have designed a fast algorithm for estimating a partial translation model, which accounts for translational equivalence only at the word level . The model's precision /recall trade-off can be directly controlled via one threshold parameter. This feature makes the model more suitable for applications that are not fully statistical. The model's hidden parameters can be easily conditioned on information extrinsic to the model, providing an easy way to integrate pre-existing knowledge such as part-of-speech, dictionaries, word order, etc.. Our model can link word tokens in parallel texts as well as other translation models in the literature. Unlike other translation models, it can automatically produce dictionarysized translation lexicons, and it can do so with over 99% accuracy.

This article advances the state of the art ofbitext mapping by formulating the problem in terms of pattern recognition. From this point of view, the success of a bitext mapping algorithm hinges on how well it performs three tasks: signal generation, noise filtering, and search. The Smooth Injective Map Recognizer (SIMR) algorithm presented here integrates innovative approaches to each of these tasks. Objective evaluation has shown that SIMR's accuracy is consistently high for language pairs as diverse as French/English and Korean/English. If necessary, S IMR's bitext maps can be efficiently converted into segment alignments using the Geometric Segment Alignment (GSA) algorithm, which is also presented here. SIMR has produced bitext maps for over 200 megabytes of French-English bitexts. GSA has converted these maps into alignments. Both the maps and the alignments are available from the Linguistic Data Consortium) 1.

In this work, we describe the first public version of the Morfessor software, which is a program that takes as input a corpus of unannotated text and produces a segmentation of the word forms observed in the text. The segmentation obtained often resembles a linguistic morpheme segmentation. Morfessor is not language-dependent. The number of segments per word is not restricted to two or three as in some other existing morphology learning models. The current version of the software essentially implements two morpheme segmentation models presented earlier by us (Creutz and Lagus, 2002; Creutz, 2003). The document contains user’s instructions, as well as the mathematical formulation of the model and a description of the search algorithm used. Additionally, a few experiments on Finnish and English text corpora are reported in order to give the user some ideas of how to apply the program to his own data sets and how to evaluate the results. 1

This work has been motivated by two long term goals: to understand how humans learn language and to build programs that can understand language. Using a representation that makes the relevant features explicit is a prerequisite for successful learning and understanding. Therefore, I chose to represent relations between individual words explicitly in my model. Lexical attraction is defined as the likelihood of such relations. I introduce a new class of probabilistic language models named lexical attraction models which can represent long distance relations between words and I formalize this new class of models using information theory. Within the

This work presents an algorithm for the unsupervised learning, or induction, of a simple morphology of a natural language. A probabilistic maximum a posteriori model is utilized, which builds hierarchical representations for a set of morphs, which are morpheme-like units discovered from unannotated text corpora. The induced morph lexicon stores parameters related to both the “meaning ” and “form ” of the morphs it contains. These parameters affect the role of the morphs in words. The model is implemented in a task of unsupervised morpheme segmentation of Finnish and English words. Very good results are obtained for Finnish and almost as good results are obtained in the English task. 1.

Several methods for classifying and segmenting text are described. These are based on ranking text sequences by their cross-entropy calculated using a fixed order character-based Markov model adapted from the PPM text compression algorithm. Experimental results show that the methods are a signi cant improvement over previously used methods in a number of areas. For example, text can be classified with a very high degree of accuracy by authorship, language, dialect and genre. Highly accurate text segmentation is also possible -- the accuracy of the PPM-based Chinese word segmenter is close to 99% on Chinese news text; similarly, a PPM-based method of segmenting text by language achieves an accuracy of over 99%.

Morphological disambiguation is the process of assigning one set of morphological features to each individual word in a text. When the word is ambiguous (there are several possible analyses for the word), a disambiguation procedure based on the word context must be applied. This paper deals with morphological disambiguation of the Hebrew language, which combines morphemes into a word in both agglutinative and fusional ways. We present an unsupervised stochastic model – the only resource we use is a morphological analyzer – which deals with the data sparseness problem caused by the affixational morphology of the Hebrew language. We present a text encoding method for languages with affixational morphology in which the knowledge of word formation rules (which are quite restricted in Hebrew) helps in the disambiguation. We adapt HMM algorithms for learning and searching this text representation, in such a way that segmentation and tagging can be learned in parallel in one step. Results on a large scale evaluation indicate that this learning improves disambiguation for complex tag sets. Our method is applicable to other languages with affix morphology. 1

Semantic entropy is a measure of semantlc ambiguity anduninformativehess.

This paper describes a method for correcting English text using a PPM model. A method that segments words in English text is introduced and is shown to be a significant improvement over previously used methods. A similar technique is also applied as a post-processing stage after pages have been recognized by a state-of-theart commercial OCR system. We show that the accuracy of the OCR system can be increased from 96.3% to 96.9%, a decrease of about 14 errors per page.