@InProceedings{wang-EtAl:2017:EMNLP20172,
  author    = {Wang, Liang  and  Li, Sujian  and  Lv, Yajuan  and  WANG, Houfeng},
  title     = {Learning to Rank Semantic Coherence for Topic Segmentation},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {1340--1344},
  abstract  = {Topic segmentation plays an important role for discourse parsing and
	information retrieval. Due to the absence of training data, previous work
	mainly adopts unsupervised methods to rank semantic coherence between
	paragraphs for topic segmentation. In this paper, we present an intuitive and
	simple idea to automatically create a "quasi" training dataset, which includes
	a large amount of text pairs from the same or different documents with
	different semantic coherence. With the training corpus, we design a symmetric
	CNN neural network to model text pairs and rank the semantic coherence within
	the learning to rank framework. Experiments show that our algorithm is able to
	achieve competitive performance over strong baselines on several real-world
	datasets.},
  url       = {https://www.aclweb.org/anthology/D17-1139}
}