A number of recent papers and books discuss theoretical efforts toward a scientific understanding of consciousness. Progress in imaging networks of brain areas active when people perform simple tasks may provide a useful empirical background for distinguishing conscious and unconscious information processing. Attentional networks include those involved in orienting to sensory stimuli, activating ideas from memory, and maintaining the alert state. This paper reviews recent findings in relation to classical issues in the study of attention and anatomical and physical theories of the nature of consciousness.

https://www.pnas.org/content/pnas/91/16/7398.full.pdf

Attention: the mechanisms of consciousness

From Discourse to Logic

This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input. A survey of NLG is timely in view of the changes that the field has undergone over the past two decades, especially in relation to new (usually data-driven) methods, as well as new applications of NLG technology. This survey therefore aims to (a) give an up-to-date synthesis of research on the core tasks in NLG and the architectures adopted in which such tasks are organised; (b) highlight a number of recent research topics that have arisen partly as a result of growing synergies between NLG and other areas of artifical intelligence; (c) draw attention to the challenges in NLG evaluation, relating them to similar challenges faced in other areas of nlp, with an emphasis on different evaluation methods and the relationships between them.

/pdf/survey-of-the-state-of-the-art-in-natural-language-26vdvzdbx0.pdf

Survey of the state of the art in natural language generation: core tasks, applications and evaluation

This paper reviews research on automatic summarising in the last decade. This work has grown, stimulated by technology and by evaluation programmes. The paper uses several frameworks to organise the review, for summarising itself, for the factors affecting summarising, for systems, and for evaluation.

The review examines the evaluation strategies applied to summarising, the issues they raise, and the major programmes. It considers the input, purpose and output factors investigated in recent summarising research, and discusses the classes of strategy, extractive and non-extractive, that have been explored, illustrating the range of systems built.

The conclusions drawn are that automatic summarisation has made valuable progress, with useful applications, better evaluation, and more task understanding. But summarising systems are still poorly motivated in relation to the factors affecting them, and evaluation needs taking much further to engage with the purposes summaries are intended to serve and the contexts in which they are used.

/pdf/automatic-summarising-the-state-of-the-art-2gd3hob6kg.pdf

Automatic summarising: The state of the art

We describe two newly developed computational tools for morphological processing: a program for analysis of English inflectional morphology, and a morphological generator, automatically derived from the analyser. The tools are fast, being based on finite-state techniques, have wide coverage, incorporating data from various corpora and machine readable dictionaries, and are robust, in that they are able to deal effectively with unknown words. The tools are freely available. We evaluate the accuracy and speed of both tools and discuss a number of practical applications in which they have been put to use.

/pdf/applied-morphological-processing-of-english-3mw6d22zq7.pdf

Applied morphological processing of English

We present the RAGS (Reference Architecture for Generation Systems) framework: a specification of an abstract Natural Language Generation (NLG) system architecture to support sharing, re-use, comparison and evaluation of NLG technologies. We argue that the evidence from a survey of actual NLG systems calls for a different emphasis in a reference proposal from that seen in similar initiatives in information extraction and multimedia interfaces. We introduce the framework itself, in particular the two-level data model that allows us to support the complex data requirements of NLG systems in a flexible and coherent fashion, and describe our efforts to validate the framework through a range of implementations.

/pdf/a-reference-architecture-for-natural-language-generation-3vyzotw0t2.pdf

A Reference Architecture for Natural Language Generation Systems

This is the second of a series of three papers that, taken together, will give an essentially complete account of inflection in standard German. In this paper we present that part of the account that covers nouns, one that captures all the regularities, subregularities and irregularities that are involved, but with a focus on the subregularities. Inflected forms are defined in terms of their syllable structure, as proposed in Cahill (1990a, b, 1993). The analysis is formulated as a DATR theory – a set of lexical axioms – from which all the relevant facts follow as theorems. DATR is a widely used formal lexical knowledge representation language developed for use in computational linguistics.

German noun inflection

This is the first of a series of papers that, taken together, will give an essentially complete account of inflection in standard German. In this paper we present that part of the account that covers adjectives, determiners, and third-person pronouns, one that captures all the regularities, subregularities, and irregularities that are involved. The forms are defined in terms of their syllable structure, as proposed in Cahill (1990a, 1990b, 1993). The morphological treatment is based on ideas originally set out by Zwicky (1985). The analysis is formulated as a DATR theory - a set of lexical axioms - from which all the relevant facts follow as theorems. DATR is a widely used formal lexical-knowledge-representation language developed for use in computational linguistics

The inflectional phonology of German adjectives determiners and pronouns.

Syllable-based morphology is an approach to morphology that considers syllables to be the primary concept in morphological description. The theory proposes that, other than simple affixation, morphological processes or operations are best defined in terms of the resulting syllabic structure, with syllable constituents (onset, peak, coda) being defined according to the morphosyntactic status of the form. Although most work in syllable-based morphology has addressed European languages (especially the Germanic languages) the theory was always intended to apply to all languages. One of the language groups that appears on the surface to offer the biggest challenge to this theory is the Semitic language group. In this chapter a syllable-based analysis of Arabic morphology is presented which demonstrates that, not only is such an analysis possible for Semitic languages, but the resulting analysis is not significantly different from syllable-based analyses of European languages such as English and German

A syllable based account of Arabic morphology

This paper presents a language for the description of morphological alternations which is based on syllable structure. The justification for such an approach is discussed with reference to examples from a variety of languages and the approach is compared to Koskenniemi's two-level account of morphonology.

Lynne Cahill

Papers

A Reference Architecture for Natural Language Generation Systems

German noun inflection

The inflectional phonology of German adjectives determiners and pronouns.

A syllable based account of Arabic morphology

Syllable-based morphology