@inproceedings{RehbeinRuppenhoferSchmidt2020,
  author    = {Ines Rehbein and Josef Ruppenhofer and Thomas Schmidt},
  title     = {Improving Sentence Boundary Detection for Spoken Language Transcripts},
  series = {Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC), May 11-16, 2020, Palais du Pharo, Marseille, France},
  editor    = {Nicoletta Calzolari and Fr{\´e}d{\´e}ric B{\´e}chet and Philippe Blache and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and H{\´e}l{\`e}ne Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis},
  publisher = {European Language Resources Association},
  address   = {Paris},
  isbn      = {979-10-95546-34-4},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-98382},
  pages     = {7102 -- 7111},
  year      = {2020},
  abstract  = {This paper presents experiments on sentence boundary detection in transcripts of spoken dialogues. Segmenting spoken language into sentence-like units is a challenging task, due to disfluencies, ungrammatical or fragmented structures and the lack of punctuation. In addition, one of the main bottlenecks for many NLP applications for spoken language is the small size of the training data, as the transcription and annotation of spoken language is by far more time-consuming and labour-intensive than processing written language. We therefore investigate the benefits of data expansion and transfer learning and test different ML architectures for this task. Our results show that data expansion is not straightforward and even data from the same domain does not always improve results. They also highlight the importance of modelling, i.e. of finding the best architecture and data representation for the task at hand. For the detection of boundaries in spoken language transcripts, we achieve a substantial improvement when framing the boundary detection problem as a sentence pair classification task, as compared to a sequence tagging approach.},
  language  = {en}
}