DisMo: A Morphosyntactic, Disfluency and Multi-Word Unit Annotator. An Evaluation on a Corpus of French Spontaneous and Read Speech
This work addresses the need for automated annotation tools for linguists and researchers analyzing spontaneous and read speech in French, though it is incremental as it builds on existing methods like CRFs.
The authors tackled the problem of multi-level annotation for spoken French by developing DisMo, a hybrid system that integrates part-of-speech tagging, disfluency detection, and multi-word unit recognition, achieving a precision of 95% to 96.8% in POS-tagging on a 57k-token corpus.
We present DisMo, a multi-level annotator for spoken language corpora that integrates part-of-speech tagging with basic disfluency detection and annotation, and multi-word unit recognition. DisMo is a hybrid system that uses a combination of lexical resources, rules, and statistical models based on Conditional Random Fields (CRF). In this paper, we present the first public version of DisMo for French. The system is trained and its performance evaluated on a 57k-token corpus, including different varieties of French spoken in three countries (Belgium, France and Switzerland). DisMo supports a multi-level annotation scheme, in which the tokenisation to minimal word units is complemented with multi-word unit groupings (each having associated POS tags), as well as separate levels for annotating disfluencies and discourse phenomena. We present the system's architecture, linguistic resources and its hierarchical tag-set. Results show that DisMo achieves a precision of 95% (finest tag-set) to 96.8% (coarse tag-set) in POS-tagging non-punctuated, sound-aligned transcriptions of spoken French, while also offering substantial possibilities for automated multi-level annotation.