Professor i datorlingvistik vid Institutionen för lingvistik, Stockholms universitet.
I urval från Stockholms universitets publikationsdatabas
Zero-shot cross-lingual identification of direct speech using distant supervision
2020. Murathan Kurfali, Mats Wirén. The 4th Joint SIGHUM Workshopon Computational Linguistics for Cultural Heritage,Social Sciences, Humanities and Literature, 105-111Konferens
Annotation Guideline No. 7: Guidelines for annotation of narrative structure
2020. Mats Wirén, Adam Ek. Journal of Cultural AnalyticsArtikel
Analysis of narrative structure can be said to answer the question “Who tells what, and how?”. The first part of the question thus concerns aspects such as who is narrating, whether it is a character in the story or not, and if it is a first-person or third-person narrator. The second part is related to the story and its basic elements: characters and events, and how the sequence of events forms a plot. The third part concerns how the narrative text is constructed: ordering of the events, the perspective from which the story is seen, how much information the narrator has access to, etc.
SVALA: Annotation of Second-Language Learner Text Based on Mostly Automatic Alignment of Parallel Corpora
2019. Mats Wirén (et al.). Selected papers from the CLARIN Annual Conference 2018, Pisa, 8-10 October 2018, 222-234Konferens
Annotation of second-language learner text is a cumbersome manual task which in turn requires interpretation to postulate the intended meaning of the learner’s language. This paper describes SVALA, a tool which separates the logical steps in this process while providing rich visual support for each of them. The first step is to pseudonymize the learner text to fulfil the legal and ethical requirements for a distributable learner corpus. The second step is to correct the text, which is carried out in the simplest possible way by text editing. During the editing, SVALA automatically maintains a parallel corpus with alignments between words in the learner source text and corrected text, while the annotator may repair inconsistent word alignments. Finally, the actual labelling of the corrections (the postulated errors) is performed. We describe the objectives, design and workflow of SVALA, and our plans for further development.
Distinguishing Narration and Speech in Prose Fiction Dialogues
2019. Adam Ek, Mats Wirén. Proceedings of the Digital Humanities in the Nordic Countries 4th Conference, 124-132Konferens
This paper presents a supervised method for a novel task, namely, detecting elements of narration in passages of dialogue in prose fiction. The method achieves an F1-score of 80.8%, exceeding the best baseline by almost 33 percentage points. The purpose of the method is to enable a more fine-grained analysis of fictional dialogue than has previously been possible, and to provide a component for the further analysis of narrative structure in general.