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 lupginz-jlm. This work develops a wide coverage taxonomy for question/question sequences observable in corpora including the BNC, CHILDES, and BEE, as well as formal modeling 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, Maptask and CornellMovie with include 506, 262, 467, and 678 question/response pairs respectively. We compare the data for English with data from Polish using the Spokes corpus (694 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.

Readers adopt their domain knowledge to make inferences about information that is left implicit in the text. The present research investigates the role of domain knowledge in discourse relation interpretation, as this has not been examined experimentally in previous work. We compare interpretations of experts from the field of economics and biomedical sciences in texts from within and outside of their domain of expertise. The results show that high-knowledge readers are better at inferring the correct relation interpretation compared to low-knowledge readers. This effect was stronger in relations that contained a connective in the original text than in relations that were originally implicit. The study provides insight on the impact of background knowledge on discourse relation inferencing and how readers interpret discourse relations when they lack the required domain knowledge.

A dialogue is successful when there is alignment between the speakers, at different linguistic levels. In this work, we consider the dialogue occurring between interlocutors engaged in a collaborative learning task, where they are evaluated on how well they performed and how much they learnt. Our main contribution is to propose new automatic measures to study alignment; focusing on lexical alignment, and a new alignment context that we introduce termed as behavioural alignment (when an instruction given by one interlocutor was followed with concrete actions in a physical environment by another). Thus we propose methodologies to create a link between what was said, and what was done as a consequence. To do so, we focus on expressions related to the task in the situated activity. These expressions are minimally required by the interlocutors to make progress in the task. We then observe how these local alignment contexts build to dialogue level phenomena; success in the task. What distinguishes our approach from other works, is the treatment of alignment as a procedure that occurs in stages. Since we utilise a dataset of spontaneous speech dialogues elicited from children, a second contribution of our work is to study how spontaneous speech phenomena (such as when interlocutors say "uh", "oh" ...) are used in the process of alignment. Lastly, we make public the dataset to study alignment in educational dialogues. Our results show that all teams lexically and behaviourally align to some degree regardless of their performance and learning, and our measures capture that teams that did not succeed in the task were simply slower to collaborate. Thus we find that teams that performed better, were faster to align. Furthermore, our methodology captures a productive, collaborative period that includes the time where the interlocutors came up with their best solutions. We also find that well-performing teams verbalise the marker "oh" more when they are behaviourally aligned, compared to other times in the dialogue; showing that this marker is an important cue in alignment. To the best of our knowledge, we are the first to study the role of "oh" as an information management marker in a behavioural context (i.e. in connection to actions taken in a physical environment), compared to only a verbal one. Our measures contribute to the research in the field of educational dialogue and the intersection between dialogue and collaborative learning research.

We have been addressing the problem of acquiring attributes of unknown terms through dialogues and previously proposed an approach using the implicit confirmation process. It is crucial for dialogue systems to ask questions that do not diminish the user’s willingness to talk. In this paper, we conducted a user study to investigate user impression for several question types, including explicit and implicit, to acquire lexical knowledge. We clarified the order among the types and found that repeating the same question type annoys the user and degrades user impression even when the content of the questions is correct. We also propose a method for determining whether an estimated attribute is correct, which is included in an implicit question. The method exploits multiple-user responses to implicit questions about the attribute of the same unknown term. Experimental results revealed that the proposed method exhibited a higher precision rate for determining the correctly estimated attributes than when only single-user responses were considered.

Researchers studying human interaction, such as conversation analysts, psychologists, and linguists, all rely on detailed transcriptions of language use. Ideally, these should include so-called paralinguistic features of talk, such as overlaps, prosody, and intonation, as they convey important information. However, creating conversational transcripts that include these features by hand requires substantial amounts of time by trained transcribers. There are currently no Speech to Text (STT) systems that are able to integrate these features in the generated transcript. To reduce the resources needed to create detailed conversation transcripts that include representation of paralinguistic features, we developed a program called GailBot. GailBot combines STT services with plugins to automatically generate first drafts of transcripts that largely follow the transcription standards common in the field of Conversation Analysis. It also enables researchers to add new plugins to transcribe additional features, or to improve the plugins it currently uses. We describe GailBot’s architecture and its use of computational heuristics and machine learning. We also evaluate its output in relation to transcripts produced by both human transcribers and comparable automated transcription systems. We argue that despite its limitations, GailBot represents a substantial improvement over existing dialogue transcription software.

Current work on automatic coreference resolution has focused on the OntoNotes benchmark dataset, due to both its size and consistency. However many aspects of the OntoNotes annotation scheme are not well understood by NLP practitioners, including the treatment of generic NPs, noun modifiers, indefinite anaphora, predication and more. These often lead to counterintuitive claims, results and system behaviors. This opinion piece aims to highlight some of the problems with the OntoNotes rendition of coreference, and to propose a way forward relying on three principles: 1. a focus on semantics, not morphosyntax; 2. cross-linguistic generalizability; and 3. a separation of identity and scope, which can resolve old problems involving temporal and modal domain consistency.

With the aim of designing a spoken dialogue system which has the ability to adapt to the user’s communication idiosyncrasies, we investigate whether it is possible to carry over insights from the usage of communication styles in human-human interaction to human-computer interaction. In an extensive literature review, it is demonstrated that communication styles play an important role in human communication. Using a multi-lingual data set, we show that there is a significant correlation between the communication style of the system and the preceding communication style of the user. This is why two components that extend the standard architecture of spoken dialogue systems are presented: 1) a communication style classifier that automatically identifies the user communication style and 2) a communication style selection module that selects an appropriate system communication style. We consider the communication styles elaborateness and indirectness as it has been shown that they influence the user’s satisfaction and the user’s perception of a dialogue. We present a neural classification approach based on supervised learning for each task. Neural networks are trained and evaluated with features that can be automatically derived during an ongoing interaction in every spoken dialogue system. It is shown that both components yield solid results and outperform the baseline in form of a majority-class classifier.