Ron Zacharski

Cognitive Status and the Form of Referring Expressions in Discourse

In this paper the As propose six implicationally related cognitive statuses relevant for explicating the use of referring expressions in natural language discourse. These statuses are the conventional meanings signalled by determiners and pronouns, and interaction of the statuses with Grices maxim of Quantity accounts for the actual distribution and interpretation of forms when necessary conditions for the use of more than one form are met. This proposal is supported by an empirical study of the distribution of the referring expressions in naturally occuring discourse in five languages

Definite descriptions and cognitive status in English: why accommodation is unnecessary

A commonly held view of English definite articles is that they signal that the referent of an NP is familiar to the addressee. However, it is well known that not all definite article phrases meet this familiarity requirement. To account for such non-familiar uses, Heim (1982) invokes the mechanism of ‘accommodation’, which enables an addressee to remedy a violation of the familiarity requirement by adding assumptions to the ‘common ground’. In this paper we argue that the Givenness Hierarchy framework provides an insightful account of all uses of definite article phrases without requiring an appeal to accommodation. Such an account provides a unified treatment of definite article phrases, including demonstrative phrases and personal pronouns, while at the same time distinguishing among them in a principled way. This proposal is supported by results of a corpus-based examination of the use of definite articles and by an examination of cleft presuppositions.

Underspecification of Cognitive Status in Reference Production: Some Empirical Predictions

Within the Givenness Hierarchy framework of Gundel, Hedberg, and Zacharski (1993), lexical items included in referring forms are assumed to conventionally encode two kinds of information: conceptual information about the speakers intended referent and procedural information about the assumed cognitive status of that referent in the mind of the addressee, the latter encoded by various determiners and pronouns. This article focuses on effects of underspecification of cognitive status, establishing that, although salience and accessibility play an important role in reference processing, the Givenness Hierarchy itself is not a hierarchy of degrees of salience/accessibility, contrary to what has often been assumed. We thus show that the framework is able to account for a number of experimental results in the literature without making additional assumptions about form-specific constraints associated with different referring forms.

On the generation and interpretation of demonstrative expressions

This paper presents necessary and sufficient conditions for the use of demonstrative expressions in English and discusses implications for current discourse processing algorithms. We examine a broad range of texts to show how the distribution of demonstrative forms and functions is genre dependent. This research is part of a larger study of anaphoric expressions, the results of which will be incorporated into a natural language generation system.

Embedding Knowledge Elicitation and MT Systems within a Single Architecture

This paper describes Expedition, an environment designed to facilitate the quick ramp-up of MT systems from practically any alphabetic language (L) into English. The central component of Expedition is a knowledge-elicitation system that guides a linguistically naive bilingual speaker through the process of describing L in terms of its ecological, morphological, grammatical, lexical, and transfer information. Expedition also includes a module for converting the elicited information into the format expected by the underlying MT system and an MT engine that relies on both the elicited knowledge and resident knowledge about English. The Expedition environment is integrated using a configuration and control system. Expedition represents an innovative approach to answering the need for rapid-configuration MT by preparing an MT system in which the only missing link is information about L, which is elicited in a structured fashion such that it can be directly exploited by the system. In this paper we report on the current state of Expedition with an emphasis on the knowledge elicitation system.

Mood and modality: out of theory and into the fray

The topic of mood and modality (MOD) is a difficult aspect of language description because, among other reasons, the inventory of modal meanings is not stable across languages, moods do not map neatly from one language to another, modality may be realised morphologically or by free-standing words, and modality interacts in complex ways with other modules of the grammar, like tense and aspect. Describing MOD is especially difficult if one attempts to develop a unified approach that not only provides cross-linguistic coverage, but is also useful in practical natural language processing systems. This article discusses an approach to MOD that was developed for and implemented in the Boas Knowledge-Elicitation (KE) system. Boas elicits knowledge about any language, L, from an informant who need not be a trained linguist. That knowledge then serves as the static resources for an L-to-English translation system. The KE methodology used throughout Boas is driven by a resident inventory of parameters, value sets, and means of their realisation for a wide range of language phenomena. MOD is one of those parameters, whose values are the inventory of attested and not yet attested moods (e.g. indicative, conditional, imperative), and whose realisations include flective morphology, agglutinating morphology, isolating morphology, words, phrases and constructions. Developing the MOD elicitation procedures for Boas amounted to wedding the extensive theoretical and descriptive research on MOD with practical approaches to guiding an untrained informant through this non-trivial task. We believe that our experience in building the MOD module of Boas offers insights not only into cross-linguistic aspects of MOD that have not previously been detailed in the natural language processing literature, but also into KE methodologies that could be applied more broadly.

A discourse system for conversational characters

This paper describes a discourse system for conversational characters used for interactive stories. This system is part of an environment that allows learners to practice language skills by interacting with the characters, other learners, and native speakers using instant messaging and email. The dialogues are not purely task oriented and, as a result, are difficult to model using traditional AI planners. On the other hand the dialogues must move the story forward and, thus, systems for the meandering dialogues of chatterbots (for example, AliceBot) are not appropriate. Our approach combines two methods. We use the notion of dialogue game or speech act networks [1][2] to model the local coherence of dialogues. The story moves forward from one dialogue game to another by means of a situated activity planner [3].

MT and topic-based techniques to enhance speech recognition systems for professional translators

Our principle objective was to reduce the error rate of speech recognition systems used by professional translators. Our work concentrated on Spanish-to-English translation. In a baseline study we estimated the error rate of an off-the-shelf recognizer to be 9.98%. In this paper we describe two independent methods of improving speech recognizers: a machine translation (MT) method and a topic-based one. An evaluation of the MT method suggests that the vocabulary used for recognition cannot be completely restricted to the set of translations produced by the MT system and a more sophisticated constraint system must be used. An evaluation of the topic-based method showed significant error rate reduction, to 5.07%.

Improving the Accuracy of Speech Recognition Systems for Professional Translators

Our principal objective was to reduce the error rate of speech recognition systems used by professional translators. Our work concentrated on Spanish-to-English translation. In a baseline study we estimated the speech recognition error rate of an off-the-shelf recognizer to be 9.98% We describe two independent methods of improving speech recognition systems for translators: a word-for-word translation method and a topic-based method. The topic-based approach performed the best, reducing the error rate significantly, to 5.07%.