SECTOR: A Neural Model for Coherent Topic Segmentation and Classification
Preprint
Abstract
When searching for information, a human reader first glances over a document, spots relevant sections and then focuses on a few sentences for resolving her intention. However, the high variance of document structure complicates to identify the salient topic of a given section at a glance. To tackle this challenge, we present SECTOR, a model to support machine reading systems by segmenting documents into coherent sections and assigning topic labels to each section. Our deep neural network architecture learns a latent topic embedding over the course of a document. This can be leveraged to classify local topics from plain text and segment a document at topic shifts. In addition, we contribute WikiSection, a publicly available dataset with 242k labeled sections in English and German from two distinct domains: diseases and cities. From our extensive evaluation of 20 architectures, we report a highest score of 71.6% F1 for the segmentation and classification of 30 topics from the English city domain, scored by our SECTOR LSTM model with bloom filter embeddings and bidirectional segmentation. This is a significant improvement of 29.5 points F1 compared to state-of-the-art CNN classifiers with baseline segmentation.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Topic detection and tracking for conversational content by using conceptual dynamic latent Dirichlet allocationNeurocomputing, 2016
- Head/Tail Breaks: A New Classification Scheme for Data with a Heavy-Tailed DistributionThe Professional Geographer, 2013
- Supervised Sequence Labelling with Recurrent Neural Networks2012
- Automatically classifying sentences in full-text biomedical articles into Introduction, Methods, Results and DiscussionBioinformatics, 2009
- Applying Machine Learning to Text Segmentation for Information RetrievalInformation Retrieval Journal, 2003
- Learning to Forget: Continual Prediction with LSTMNeural Computation, 2000
- Statistical Models for Text SegmentationMachine Learning, 1999
- The vocabulary problem in human-system communicationCommunications of the ACM, 1987