Speech Genres and Other Late Essays

In this article we propose a strategy for the summarization of scientific articles that concentrates on the rhetorical status of statements in an article: Material for summaries is selected in such a way that summaries can highlight the new contribution of the source article and situate it with respect to earlier work. We provide a gold standard for summaries of this kind consisting of a substantial corpus of conference articles in computational linguistic annotated with human judgments of the rhetorical status and relevance of each sentence in the articles. We present several experiments measuring our judges' agreement on theses annotations. We also present an algorithm that, on the basis of the annoted training material, selects content from unseen articles and classifies it into a fixed set of seven rhetorical categories. The output of this extraction and classification system can be viewed as a single-document summary in its own right; alternatively, it provides starting material for the generation of task-oriented and user-tailored summaries designed to give users an overview of a scientific field.

Summarizing scientific articles: Experiments with relevance and rhetorical status : Summarization

The finite-state paradigm of computer sciences has provided a basis for natural-language applications that are efficient, elegant and robust. This volume is a practical guide to finite-state theory and the affiliated programming languages lexc and xfst. Readers will learn how to write tokenizers, spelling checkers, and especially morphological analyzer/generators for words in English, French, Finnish, Hungarian and other languages. Included are graded introductions, examples, and exercises suitable for individual study as well as formal courses. These take advantage of widely tested lexc and xfst applications that are just becoming available for noncommercial use via the Internet.

Finite State Morphology

Modern grammar development platforms often support multiple devices for representing properties of a natural language, giving the grammar writer some freedom in implementing analyses of linguistic phenomena. These design alternatives can have dramatic consequences for efficiency both in processing and in grammar building. In this paper I report on three experiments in making systematic modifications to a broad-coverage grammar of English in order to gain efficiency without loss of linguistic elegance. While the experiments are to some degree both platform-dependant and theory-bound, the kinds of modifications reported should be applicable to any unification-based grammar which makes use of types. The results make a strong case for a more visible role for the linguist in the collaborative effort to achieve greater processing efficiency.

On building a more efficient grammar by exploiting types

An extension to finite state transducers is presented, in which atomic symbols are replaced by arbitrary predicates over symbols. The extension is motivated by applications in natural language processing (but may be more widely applicable) as well as by the observation that transducers with predicates generally have fewer states and fewer transitions. Although the extension is fairly trivial for finite state acceptors, the introduction of predicates is more interesting for transducers. It is shown how various operations on transducers (e.g., composition) can be implemented, as well as how the transducer determinization algorithm can be generalized for predicate-augmented finite state transducers.

/pdf/finite-state-transducers-with-predicates-and-identities-4f2umk9izi.pdf

Finite State Transducers with Predicates and Identities

Finite-state techniques are widely used in various areas of Natural Language Processing (NLP). As Kaplan and Kay [12] have argued, regular expressions are the appropriate level of abstraction for thinking about finite-state languages and finite-state relations. More complex finite-state operations (such as contexted replacement) are defined on the basis of basic operations (such as Kleene closure, complementation, composition). In order to be able to experiment with such complex finite-state operations the FSA Utilities (version 5) provides an extendible regular expression compiler. The paper discusses the regular expression operations provided by the compiler, and the possibilities to create new regular expression operators. The benefits of such an extendible regular expression compiler are illustrated with a number of examples taken from recent publications in the area of finite-state approaches to NLP.

An Extendible Regular Expression Compiler for Finite-State Approaches in Natural Language Processing

Previous work (Frank and Satta 1998; Karttunen, 1998) has shown that Optimality Theory with gradient constraints generally is not finite state. A new finite-state treatment of gradient constraints is presented which improves upon the approximation of Karttunen (1998). The method turns out to be exact, and very compact, for the syllabification analysis of Prince and Smolensky (1993).

Approximation and Exactness in Finite State Optimality Theory

Context sensitive rewrite rules have been widely used in several areas of natural language processing, including syntax, morphology, phonology and speech processing. Kaplan and Kay, Karttunen, and Mohri & Sproat have given various algorithms to compile such rewrite rules into finite-state transducers. The present paper extends this work by allowing a limited form of backreferencing in such rules. The explicit use of backreferencing leads to more elegant and general solutions.

Transducers from rewrite rules with backreferences

Emotion analysis (EA) is a rapidly developing area in computational linguistics. An EA system can be extremely useful in fields such as information retrieval and emotion-driven computer animation. For most EA systems, the number of emotion classes is very limited and the text units the classes are assigned to are discrete and predefined. The question we address in this paper is whether the set of emotion categories can be enriched and whether the units to which the categories are assigned can be more flexibly defined. We present an experiment showing how an annotation task can be set up so that untrained participants can perform emotion analysis with high agreement even when not restricted to a predetermined annotation unit and using a rich set of emotion categories. As such it sets the stage for the development of more complex EA systems which are closer to the actual human emotional perception of text.

Dale Gerdemann

Papers

Finite State Transducers with Predicates and Identities

An Extendible Regular Expression Compiler for Finite-State Approaches in Natural Language Processing

Approximation and Exactness in Finite State Optimality Theory

Transducers from rewrite rules with backreferences

Emotional Perception of Fairy Tales: Achieving Agreement in Emotion Annotation of Text