From the Publisher:
This book takes an empirical approach to language processing, based on applying statistical and other machine-learning algorithms to large corpora.Methodology boxes are included in each chapter. Each chapter is built around one or more worked examples to demonstrate the main idea of the chapter. Covers the fundamental algorithms of various fields, whether originally proposed for spoken or written language to demonstrate how the same algorithm can be used for speech recognition and word-sense disambiguation. Emphasis on web and other practical applications. Emphasis on scientific evaluation. Useful as a reference for professionals in any of the areas of speech and language processing.

/pdf/speech-and-language-processing-an-introduction-to-natural-atzaecqfem.pdf

Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

https://science.sciencemag.org/content/sci/5/110/206.full.pdf

The american psychological association.

Traditional mechanistic accounts of language processing derive almost entirely from the study of monologue. Yet, the most natural and basic form of language use is dialogue. As a result, these accounts may only offer limited theories of the mechanisms that un- derlie language processing in general. We propose a mechanistic account of dialogue, the interactive alignment account, and use it to de- rive a number of predictions about basic language processes. The account assumes that, in dialogue, the linguistic representations em- ployed by the interlocutors become aligned at many levels, as a result of a largely automatic process. This process greatly simplifies production and comprehension in dialogue. After considering the evidence for the interactive alignment model, we concentrate on three aspects of processing that follow from it. It makes use of a simple interactive inference mechanism, enables the development of local di- alogue routines that greatly simplify language processing, and explains the origins of self-monitoring in production. We consider the need for a grammatical framework that is designed to deal with language in dialogue rather than monologue, and discuss a range of implica- tions of the account.

/pdf/toward-a-mechanistic-psychology-of-dialogue-2jquck2ahu.pdf

Toward a mechanistic psychology of dialogue

http://www.cogsci.bme.hu/~ktkuser/PHD_iskola/docs/kgy/faceofconfigproc02.pdf

The many faces of configural processing

This article is a survey of methods for measuring agreement among corpus annotators. It exposes the mathematics and underlying assumptions of agreement coefficients, covering Krippendorff's alpha as well as Scott's pi and Cohen's kappa; discusses the use of coefficients in several annotation tasks; and argues that weighted, alpha-like coefficients, traditionally less used than kappa-like measures in computational linguistics, may be more appropriate for many corpus annotation tasks---but that their use makes the interpretation of the value of the coefficient even harder.

/pdf/inter-coder-agreement-for-computational-linguistics-2mpuyn1mc8.pdf

Inter-coder agreement for computational linguistics

This paper describes the reliability of a dialogue structure coding scheme based on utterance function, game structure, and higher-level transaction structure that has been applied to a corpus of spontaneous task-oriented spoken dialogues.

The reliability of a dialogue structure coding scheme

This article examined communication and task performance in face-to-face, copresent, and video-mediated communication (VMC) Study 1 showed that when participants in a collaborative problem-solving task could both see and hear each other, the structure of their dialogues differed compared with dialogues obtained when they only heard each other The audio-only conversations had more words, and these extra utterances often provided and elicited verbal feedback functions, which visual signals can deliver when available Study 2, however, showed that high-quality VMC did not appear to deliver the same benefits as face-to-face, copresent interaction It appears that novelty, attenuation, and remoteness all may have contributed to the effects found factors that should be considered by designers of remote video-conferencing systems

Face-to-face and video-mediated communication: A comparison of dialogue structure and task performance

Controlling the Intelligibility of Referring Expressions in Dialogue

When asked questions, adults and children often avert their gaze at certain points within the interaction, especially when questions are difficult (Doherty-Sneddon, Bruce, Bonner, Longbotham, & Doyle, 2002; Glenberg, Schroeder, & Robertson, 1998). Gaze aversion may be a way of managing the cognitive load associated with the processing of visual environmental information, or it may serve to alleviate a negative social-emotional experience, such as the self-consciousness associated with, for example, a fear of failure. In the present study, thirty-six 8-year-olds were questioned either face to face or across a live video link. Questions varied in type (arithmetic, verbal reasoning, and autobiographical and episodic memory) and in difficulty. Children averted their gaze more during face-to-face questioning than during video-mediated questioning; however, question difficulty had a very strong influence on aversion in both interview conditions. It is concluded that although social factors play a role in children's gaze aversion during pedagogical question-answer sequences, the primary function of averting gaze is to manage the cognitive load involved in the processing of environmental information.

https://link.springer.com/content/pdf/10.3758/BF03195338.pdf

Gaze aversion: a response to cognitive or social difficulty?

We describe a set of face processing tests suitable for use with children aged from 4 to 10 years, which include tests of expression, lipreading and gaze processing as well as identification. The tests can be administered on paper or using a computer, and comparisons between the performance on computer- and paper-based versions suggest that format of administration makes little difference. We present results obtained from small samples of children at four different age groups (Study 1, computer-based tests), and larger samples at three age groups (Study 2, paper-based tests) from preschool to 10 years of age. The tests were found to be developmentally sensitive. There were quite strong correlations between performance on different tests of the same face processing ability (e.g. gaze processing), and generally rather weaker correlations between tests of different abilities.

Gwyneth Doherty-Sneddon

Papers

The reliability of a dialogue structure coding scheme

Face-to-face and video-mediated communication: A comparison of dialogue structure and task performance

Controlling the Intelligibility of Referring Expressions in Dialogue

Gaze aversion: a response to cognitive or social difficulty?

Testing face processing skills in children