Current computational models for humour recognition and laughter generation in dialogue systems face significant limitations in explainability, context consideration and adaptability. This paper approaches these challenges by investigating how humour recognition develops in its earliest forms—during the first year of life. Drawing on developmental psychology and cognitive science, we propose a formal model incorporated within the KoS dialogue framework. This model captures how infants evaluate potential humour through knowledge-based appraisal and context-dependent modulation, including safety, emotional state, and social cues. Our model formalises dynamic knowledge updates during the dyadic interaction. We believe that this formal model can serve as the basis for developing more natural humour appreciation capabilities in dialogue systems and can be implemented in a robotic platform.

Indirect answers, crucial in human communication, serve to maintain politeness, avoid conflicts, and align with social customs.Although there has been a substantial number of studies on recognizing and understanding indirect answers to polar questions (often known as yes/no questions), there is a dearth of such work regarding wh-questions.This study takes up the challenge by constructing what is, to our knowledge, the first corpus of indirect answers to wh-questions.We analyze and interpret indirect answers to different wh-questions based on our carefully compiled corpus.In addition, we conducted a pilot study on generating indirect answers to wh-questions by fine-tuning the pre-trained generative language model DialoGPT (Zhang et al., 2020).Our results suggest this is a task that GPT finds difficult.

In this paper, we introduce a carefully designed and collected language resource: UgChDial – a Uyghur dialogue corpus based on a chatroom environment. The Uyghur Chat-based Dialogue Corpus (UgChDial) is divided into two parts: (1). Two-party dialogues and (2). Multi-party dialogues. We ran a series of 25, 120-minutes each, two-party chat sessions, totaling 7323 turns and 1581 question-response pairs. We created 16 different scenarios and topics to gather these two-party conversations. The multi-party conversations were compiled from chitchats in general channels as well as free chats in topic-oriented public channels, yielding 5588 unique turns and 838 question-response pairs. The initial purpose of this corpus is to study query-response pairs in Uyghur, building on an existing fine-grained response space taxonomy for English. We provide here initial annotation results on the Uyghur response space classification task using UgChDial.

Laughter is a crucial signal for communication and managing interactions. Until now no consensual approach has emerged for classifying laughter. We propose a new framework for laughter analysis and classification, based on the pivotal assumption that laughter has propositional content. We propose an annotation scheme to classify the pragmatic functions of laughter taking into account the form, the laughable, the social, situational, and linguistic context. We apply the framework and taxonomy proposed in a multilingual corpus study (French, Mandarin Chinese, and English), involving a variety of situational contexts. Our results give rise to novel generalizations about the range of meanings laughter exhibits, the placement of the laughable, and how placement and arousal relate to the functions of laughter. We have tested and refuted the validity of the commonly accepted assumption that laughter directly follows its laughable. In the concluding section, we discuss the implications our work has for spoken dialogue systems. We stress that laughter integration in spoken dialogue systems is not only crucial for emotional and affective computing aspects, but also for aspects related to natural language understanding and pragmatic reasoning. We formulate the emergent computational challenges for incorporating laughter in spoken dialogue systems.

The main aim of this paper is to provide a characterization of the response space for questions using a taxonomy grounded in a dialogical formal semantics.As a starting point we take the typology for responses in the form of questions provided in (Łupkowski and Ginzburg, 2016).This work develops a wide coverage taxonomy for question/question sequences observable in corpora including the BNC, CHILDES, and BEE, as well as formal modelling of all the postulated classes.Our aim is to extend this work to cover all responses to questions.We present the extended typology of responses to questions based on a corpus studies of BNC, BEE and Maptask with include 506, 262, and 467 question/response pairs respectively.We compare the data for English with data from Polish using the Spokes corpus (205 question/response pairs).We discuss annotation reliability and disagreement analysis.We sketch how each class can be formalized using a dialogical semantics appropriate for dialogue management.

Studies on laughter in dialogue have proposed resolving what laughter is about by looking at what laughter follows.This paper investigates the sequential relation between the laughter and the laughable.We propose a semantic/pragmatic account treating laughter as a gestural event anaphor referring to a laughable.Data from a French and Chinese dialogue corpus suggest a rather free time alignment between laughter and laughable.Laughter can occur (long) before, during, or (long) after the laughable.Our results challenge the assumption that what laughter follows is what it is about, and thus question claims which rely on this assumption.

In this article we use well-known machine learning methods to tackle a novel task, namely the classification of non-sentential utterances (NSUs) in dialogue. We introduce a fine-grained taxonomy of NSU classes based on corpus work, and then report on the results of several machine learning experiments. First, we present a pilot study focused on one of the NSU classes in the taxonomy—bare wh-phrases or “sluices”—and explore the task of disambiguating between the different readings that sluices can convey. We then extend the approach to classify the full range of NSU classes, obtaining results of around an 87% weighted F-score. Thus our experiments show that, for the taxonomy adopted, the task of identifying the right NSU class can be successfully learned, and hence provide a very encouraging basis for the more general enterprise of fully processing NSUs.

The paper considers how to scale up dialogue protocols to multilogue, settings with multiple conversationalists. We extract two benchmarks to evaluate scaled up protocols based on the long distance resolution possibilities of non-sentential utterances in dialogue and multilogue in the British National Corpus. In light of these benchmarks, we then consider three possible transformations to dialogue protocols, formulated within an issue-based approach to dialogue management. We show that one such transformation yields protocols for querying and assertion that fulfill these benchmarks.

The paper develops a semantics for natural language interrogatives which identifies questions—the denotations of interrogatives—with propositional abstracts. The paper argues that a theory of Questions as Propositional Abstracts (QPA), is a simple, transparently implementable theory that has significant empirical coverage. However, until recently QPA has been abandoned in formal semantic treatments of questions, due to a number of significant problems QPA encountered when formulated within the type system of Montague Semantics. In recent work, Ginzburg and Sag provided a a situation theoretic implementation of QPA that succeeded in overcoming certain of the original problems for QPA. However, Ginzburg and Sag's proposal relied on a special purpose account of λ-abstraction, raising the question to what extent QPA can be sustained using standard notions of abstraction. In this paper such doubts are allayed by implementing QPA in a version of Type Theory that provides record types. These latter allow one to develop notions of simultaneous/vacuous abstraction with restrictions and an ontology with various ‘informational entities’. Moreover, the intrinsic polymorphism of this theory plays a crucial role in enabling the definition of a general type for questions, one of the main stumbling blocks for earlier versions of QPA.

We offer a computational analysis of the resolution of ellipsis in certain cases of dialogue clarification. We show that this goes beyond standard techniques used in anaphora and ellipsis resolution and requires operations on highly structured, linguistically heterogeneous representations. We characterize these operations and the representations on which they operate. We offer an analysis couched in a version of Head-Driven Phrase Structure Grammar combined with a theory of information states (IS) in dialogue. We sketch an algorithm for the process of utterance integration in ISs which leads to grounding or clarification.