Articles

This paper describes the basic philosophy and implementation of MPLUS (M+), a robust medical text analysis tool that uses a semantic model based on Bayesian Networks (BNs). BNs provide a concise and useful formalism for representing semantic patterns in medical text, and for recognizing and reasoning over those patterns. BNs …...

We propose two internal methods for ac- centing unknown words, which both learn on a reference set of accented words the contexts of occurrence of the various ac- cented forms of a given letter. One method is adapted from POS tagging, the other is based on finite state transducers. We …...

We studied contrast and variability in a corpus of gene names to identify potential heuristics for use in performing entity identification in the molecular biology domain. Based on our findings, we developed heuristics for mapping weakly matching gene names to their official gene names. We then tested these heuristics against …...

Current information extraction efforts in the biomedical domain tend to focus on finding entities and facts in structured databases or MEDLINE abstracts. We apply a gene and protein name tagger trained on Medline abstracts (ABGene) to a randomly selected set of full text journal articles in the biomedical domain. We …...

We explore the use of Support Vector Ma- chines (SVMs) for biomedical named en- tity recognition. To make the SVM train- ing with the available largest corpus – the GENIA corpus – tractable, we propose to split the non-entity class into sub-classes, using part-of-speech information. In ad- dition, we explore …...

This paper describes an approach to Machine Translation that places linguistic information at its foundation. The difficulty of translation from English to Japanese is illustrated with data that shows the influence of various linguistic contextual factors. Next, a method for natural language transfer is presented that integrates translation examples (represented …...

In automatic speech recognition (ASR) enabled applications for medical dictations, corpora of literal transcriptions of speech are critical for training both speaker independent and speaker adapted acoustic models. Obtaining these transcriptions is both costly and time consuming. Non-literal transcriptions, on the other hand, are easy to obtain because they are …...

We present a simple architecture for parsing transcribed speech in which an edited-word de- tector first removes such words from the sen- tence string, and then a standard statistical parser trained on transcribed speech parses the remaining words. The edit detector achieves a misclassification rate on edited words of 2.2%. …...

I present a method of identifying cognates in the vo- cabularies of related languages. I show that a mea- sure of phonetic similarity based on multivalued fea- tures performs better than “orthographic” measures, such as the Longest Common Subsequence Ratio (LCSR) or Dice’s coefficient. I introduce a proce- dure for …...

Using finite-state automata for the text analysis component in a text-to-speech system is problem- atic in several respects: the rewrite rules from which the automata are compiled are difficult to write and maintain, and the resulting automata can become very large and therefore inefficient. Converting the knowledge represented explicitly in …...

In this paper we investigate polysemous adjectives whose meaning varies depending on the nouns they modify (e.g., fast). We acquire the meanings of these adjectives from a large corpus and propose a probabilistic model which provides a ranking on the set of possible interpre- tations. We identify lexical semantic information …...

We present two methods for learning the struc- ture of personal names from unlabeled data. The first simply uses a few implicit constraints governing this structure to gain a toehold on the problem — e.g., descriptors come before first names, which come before middle names, etc. The second model also …...

Sentence planning is a set of inter-related but distinct tasks, one of which is sentence scoping, i.e. the choice of syntactic structure for elementary speech acts and the decision of how to combine them into one or more sentences. In this paper, we present SPoT, a sentence planner, and a …...

Developing dialogue systems is a complex pro- cess. In particular, designing efficient dialogue management strategies is often difficult as there are no precise guidelines to develop them and no sure test to validate them. Several suggestions have been made recently to use reinforcement learning to search for the optimal management …...

We apply Support Vector Machines (SVMs) to identify English base phrases (chunks). SVMs are known to achieve high generalization perfor- mance even with input data of high dimensional feature spaces. Furthermore, by the Kernel princi- ple, SVMs can carry out training with smaller com- putational overhead independent of their dimen- …...

We propose an algorithm to automatically induce the morphology of inflectional languages using only text corpora and no human input. Our algorithm combines cues from orthography, semantics, and syntactic distributions to induce morphological relationships in German, Dutch, and English. Using CELEX as a gold standard for evaluation, we show our …...

We propose a novel Co-Training method for statistical parsing. The algorithm takes as input a small corpus (9695 sentences) annotated with parse trees, a dictionary of possible lexicalized structures for each word in the training set and a large pool of unlabeled text. The algo- rithm iteratively labels the entire …...

In human sentence processing, cognitive load can be defined many ways. This report considers a defini- tion of cognitive load in terms of the total probability of structural options that have been disconfirmed at some point in a sentence: the surprisal of word wi given its prefix w0...i−1 on a …...

This paper proposes a three-tier prosodic hierarchy, including prosodic word, intermediate phrase and intonational phrase tiers, for Mandarin that emphasizes the use of the prosodic word instead of the lexical word as the basic prosodic unit. Both the surface difference and perceptual difference show that this is helpful for achieving …...

Cluster-based n-gram modeling is a variant of normal word-based n-gram modeling. It attempts to make use of the similarities between words. In this paper, we present an empirical study of clustering techniques for Asian language modeling. Clustering is used to improve the performance (i.e. perplexity) of language models as well …...