• Corpus ID: 61395878

A classification scheme for annotating speech acts in a business email corpus

@article{Felice2013ACS,
  title={A classification scheme for annotating speech acts in a business email corpus},
  author={Rachele De Felice and John Darby and Alison Fisher and David Peplow},
  journal={ICAME Journal},
  year={2013}
}
This paper reports on the process of manual annotation of speech acts in a corpus of business emails, in the context of the PROBE project (PRagmatics of Business English). The project aims to bring together corpus, computational, and theoretical linguistics by drawing on the insights made available by the annotated corpus. The corpus data sheds light on the linguistic and discourse structures of speech act use in business email communication. This enhanced linguistic description can be… 

Figures and Tables from this paper

Identifying speech acts in a corpus of historical migrant correspondence

The findings show the potential for carrying out this type of analysis across larger digital archives allowing for different datasets to be compared, taking into consideration sociobiographic variables such as the author’s sex, class and role within the notional familial hierarchy.

Exploring Digital Conversation Corpora with Process Mining

This work develops a fine-grained, corpus-independent classification of speech acts, and suggests that speech act theory could be extended to include typicality conditions for sequences of utterances.

Annotating dialogue acts in speech data

  • D. Verdonik
  • Philosophy
    International Journal of Corpus Linguistics
  • 2022
The aims of this paper are to detect the most problematic issues related to dialogue act annotation in speech corpora and to define basic categories of dialogue acts. I critically examine and test

Speech acts in the Dutch COVID-19 Press Conferences

An open source corpus of all Dutch COVID-19 Press Conferences with sentences annotated on the basis of John Searle’s Speech Act taxonomy was created. It contains all 58 press conferences held between

A corpus-based classification of commitments in Business English

This chapter presents a corpus-based study of commitments in Business English emails using a speech act-annotated corpus of emails and demonstrates how corpus linguistics can contribute to the authors' understanding of the pragmatics of workplace communication.

ADVICE IN CONVERSATION Corpus Pragmatics Meets Mixed Methods

: This Element is a contribution to a new generation of corpus pragmatics research by taking as its starting point the multifaceted nature of speech acts in conversation, and by adopting a

The Pragmatic Annotation Scheme of the SPICE-Ireland Corpus

It is argued that annotation is part of transcription, and the enhancement of transcriptions with pragmatic and prosodic annotation overcomes that paradox and captures the original utterance more objectively.

Using Speech Act Theory to Apply Automated Communications Analysis to Distributed Sensemaking

In this paper, computational linguistics is applied to define and capture Speech Acts in distributed sensemaking in a military map-exercise. The exercise was performed by teams of three participants

Speech acts in corpus pragmatics

In corpus pragmatics, most of the research into speech acts still tends to be limited to working with the original, highly abstract, speech-act taxonomies devised by ordinary language philosophers

Advice in Conversation

This Element is a contribution to a new generation of corpus pragmatics research by taking as its starting point the multifaceted nature of speech acts in conversation, and by adopting a

References

SHOWING 1-10 OF 47 REFERENCES

Pragmatic Annotation of an Academic Spoken Corpus for Pedagogical Purposes

This project reports on ongoing efforts to annotate the Michigan Corpus of Academic Spoken English in order to make pragmatic information more readily accessible, thereby enhancing the value of the corpus for teachers.

Using Speech Acts to Categorize Email and Identify Email Genres

This work defines genres of email as well as a subset of "speech acts" relevant to email enhanced for email specific discourse and compares the performance of two classifiers in identifying the primary communicative intent of the email and its corresponding genre.

Coding Dialogs with the DAMSL Annotation Scheme

The slight revisions to DAMSL discussed here should increase accuracy on the next set of tests and produce a reliable, exible, and comprehensive utterance annotation scheme.

A corpus-based classification of commitments in Business English

This chapter presents a corpus-based study of commitments in Business English emails using a speech act-annotated corpus of emails and demonstrates how corpus linguistics can contribute to the authors' understanding of the pragmatics of workplace communication.

Automatic annotation of context and speech acts for dialogue corpora

This work explores how existing dialogue corpora can be automatically processed to yield new corpora where dialogue context and speech acts are accurately represented and presents an automatic annotation system which builds ‘Information State Update’ (ISU) representations of dialogue context for the Communicator (2000 and 2001) corpora.

CCGbank: A Corpus of CCG Derivations and Dependency Structures Extracted from the Penn Treebank

This article presents an algorithm for translating the Penn Treebank into a corpus of Combinatory Categorial Grammar (CCG) derivations augmented with local and long-range word-word dependencies, and discusses the implications of the findings for the extraction of other linguistically expressive grammars from the Treebank, and for the design of future treebanks.

The nature of requests and commitments in email messages

This paper presents precise definitions for classifying requests and commitments in email, based on concepts from Speech Act Theory, and informed by the results of two independent manual annotation experiments using data from the Enron email corpus.

Improving “Email Speech Acts” Analysis via N-gram Selection

It is demonstrated that exploiting the contextual information in the messages can noticeably improve email-act classification, and a combination of n-gram sequence features with careful message preprocessing that is highly effective for this task.

Dialogue act modeling for automatic tagging and recognition of conversational speech

A probabilistic integration of speech recognition with dialogue modeling is developed, to improve both speech recognition and dialogue act classification accuracy.

IDENTIFYING SPEECH ACTS IN E-MAILS: TOWARD AUTOMATED SCORING OF THE TOEIC® E-MAIL TASK

This study developed a computational model for automated speech act identification and tested it on a corpus of TOEIC responses, achieving up to 79.28% accuracy.