1. Identifying communicative functions in discourse with content types
- Author
-
Rachele Sprugnoli, Tommaso Caselli, and Giovanni Moretti
- Subjects
Linguistics and Language ,Computer science ,Library and Information Sciences ,computer.software_genre ,Security token ,Language and Linguistics ,Education ,Annotation ,across genre ,Level of analysis ,discourse processing ,Original Paper ,business.industry ,across time ,corpus annotation ,content types ,Neural network ,Identification (information) ,Information extraction ,Text types ,Artificial intelligence ,Computational linguistics ,F1 score ,business ,computer ,Natural language processing ,Neural networks - Abstract
Texts are not monolithic entities but rather coherent collections of micro illocutionary acts which help to convey a unitary message of content and purpose. Identifying such text segments is challenging because they require a fine-grained level of analysis even within a single sentence. At the same time, accessing them facilitates the analysis of the communicative functions of a text as well as the identification of relevant information. We propose an empirical framework for modelling micro illocutionary acts at clause level, that we call content types, grounded on linguistic theories of text types, in particular on the framework proposed by Werlich in 1976. We make available a newly annotated corpus of 279 documents (for a total of more than 180,000 tokens) belonging to different genres and temporal periods, based on a dedicated annotation scheme. We obtain an average Cohen’s kappa of 0.89 at token level. We achieve an average F1 score of 74.99% on the automatic classification of content types using a bi-LSTM model. Similar results are obtained on contemporary and historical documents, while performances on genres are more varied. This work promotes a discourse-oriented approach to information extraction and cross-fertilisation across disciplines through a computationally-aided linguistic analysis.
- Published
- 2022