To read the full-text of this research, you can request a copy directly from the author.
... Dialogue acts (also referred to as speech act or illocutionary act) refers to the act of communicating the intention of the speaker to the tener (receiver or addressee)(Austin, 1962)(Searle, 1969)(Searle, 1975). Dialogue acts represents the communicative function (illocutionary force and user intent) of an utterance in a dialogue (Austin, 1962)(Searle, 1969)(Searle, 1975). ...
... Dialogue acts (also referred to as speech act or illocutionary act) refers to the act of communicating the intention of the speaker to the tener (receiver or addressee)(Austin, 1962)(Searle, 1969)(Searle, 1975). Dialogue acts represents the communicative function (illocutionary force and user intent) of an utterance in a dialogue (Austin, 1962)(Searle, 1969)(Searle, 1975). Requesting (for example the utterance: could you please send me the information) or asking is an example of directive speech act where as promising (for example the utterance: I will send you the information by tomorrow) is an example of commisive speech act. ...
... Requesting (for example the utterance: could you please send me the information) or asking is an example of directive speech act where as promising (for example the utterance: I will send you the information by tomorrow) is an example of commisive speech act. Searle et al. suggests multiple classes of speech acts such as Assertives (suggesting , concluding), Directives (asking, requesting ), Commisives (promising, vowing), Expressives (thanking, apologizing) and Declarations (Searle, 1969)(Searle, 1975). Automatic dialog act recognition in free-form text has several practical applications such as: intelligent assistance for email data management, deception detection in online communication, information retrieval based on dialog acts and user intentions, user profiling and identifying roles and relationships between people based on their interactive conversations, email thread and online threaded discussion summarization. ...
The paper presents empirical results, illus-trative examples and insights on the topic of domain transferability of dialog-act cue phrases. We analyze four publicly avail-able dialog act tagged corpora (Switch-board, ICSI MRDA, BC3 Email and NPS Chat) belonging to different communi-cation domains and modality and study the extent to which corpus-derived n-gram word cue-phrases from one domain can be transferred or ported as discriminatory features for dialog act recognition belong-ing to other domains. The transferabil-ity of cue-phrases is studied with respect to cross-domain (discussion on general topics, official meetings), cross-modality (transcribed phone conversation, email, online chat) and cross-dialog-acts (ques-tions and action directive mapping to re-quests). We describe a dialog act clas-sifier for categorizing sentences in Email domain based on a model trained on pre-annotated data belonging to transcribed spoken conversation. The precision and recall of the proposed method for cross-domain dialog act labeling shows that the method is effective.
... The term speech act is generally used to describe the illocutionary aspect of an utterance. Searle [83,84] improved on Austin's classification of illocutionary acts by modifying the taxonomy. He proposes five major classes, including assertives, directives, commissives, expressives and declarations. ...
In this paper we propose a platform for developing dialogue man- agement applications supporting the information state update approach which uses agent-based techniques and a hierarchical blackboard architecture to provide concur- rency, runtime exibility and the inclusion of heuristic control.
This study investigates health-promoting messages in British and Saudi officials’ social-media discourse during the Coronavirus Disease 2019 (COVID-19) Pandemic. Taking discourse as a constructivist conception, we examined the crisis-response strategies employed by these officials on social media, and the role of such strategies in promoting healthy behaviors and compliance with health regulations. The study presents a corpus-assisted discourse analysis of the tweets of a Saudi health official and a British health official that focuses on keyness, speech acts, and metaphor. We found that both officials utilized clear communication and persuasive rhetorical tactics to convey the procedures suggested by the World Health Organization. However, there were some differences in how the two officials used speech acts and metaphors to achieve their goals. The British official used empathy as the primary communication strategy, while the Saudi official emphasized health literacy. The British official also used conflict-based metaphors such as war and gaming, whereas the Saudi official used metaphors that reflected life as a journey interrupted by the pandemic. Despite these differences, both officials utilized directive speech acts to tell audiences the procedures they should follow to achieve the desired conclusion of healing patients and ending the pandemic. In addition, rhetorical questions and assertions were used to direct people to perform certain behaviors favored. Interestingly, the discourse used by both officials contained characteristics of both health communication and political discourse. War metaphors, which were utilized by the British Health official, are a common feature in political discourse as well as in health-care discourse. Overall, this study highlights the importance of effective communication strategies in promoting healthy behaviors and compliance with health regulations during a pandemic. By analyzing the discourse of health officials on social media, we can gain insights into the strategies employed to manage a crisis and effectively communicate with the public.
Smart service chatbot, aiming to provide efficient, reliable and natural customer service, has grown rapidly in recent years. The understanding of human-agent conversation, especially modeling the conversational behavior, is essential to enhance the machine intelligence during the customer-chatbot interaction. However, there is a gap between qualitative behavior description and the corresponding technical application. In this paper, we developed a novel fine-grained dialogue act framework specific to smartphone customer service to tackle this problem. First of all, following a data-driven process, we defined a two-level classification to capture the most common conversational behavior during smartphone customer service such as affirm, deny, gratitude etc., and verified it by tagging chatlog generated by human agent. Then, using this framework, we designed a series of technically feasible dialogue policies to output human-like response. As an example, we realized a smart service chatbot for a smartphone customer using the dialogue-act-based policy. Finally, a user study was conducted to verify its efficiency and naturalness. Since the dialogue acts are meaningful abstraction of conversational behavior, the dialogue-act-based chatbot could be more explainable and flexible than the end-to-end solution.
To know natural objects, it is necessary to give them names. This has always been done, from antiquity up to modern times. Today, the nomenclature system invented by Linnaeus in the eighteenth century is still in use, even if the philosophical principles underlying it have changed. Naming living objects still means giving them a sort of existence, since without a name they cannot be referred to, just as if they did not exist. Therefore, naming a living object is a process close to creating it. Naming is performed by means of a particular kind of text: original description written by specialists, and more often accompanied by other, ancillary texts whose purpose is to gain the acceptance and support of fellow zoologists. It is noteworthy that the actions performed by these texts are called “nomenclatural acts”. These texts and acts, together with related scientific and social relationships, are examined here in the frame of speech act theory.
Since Convention appeared in 1969, David Lewis’ concept1 has been discussed from different points of view.2 Partisans seem to have been attracted, partly by the bounty of consequences which flow from the assumption that a behavioral regularity is a convention in a population, partly by the beautiful picture of man becoming social by acting rationally. Critiques have concentrated on well-defined points without, however, shaking the overall picture.3 This is what I shall attempt to do: I shall argue that if the background ideas of Lewis’ analysis are taken seriously, being party to a convention is beyond the average human’s reach.