Text segmentation on multilabel documents: A distant-supervised approach
This addresses the challenge of expensive labeled data for text segmentation, offering a more efficient solution for applications in information retrieval and text summarization, though it is incremental as it builds on existing distant supervision methods.
The paper tackles the problem of text segmentation without segment-level ground truth by using distant supervision from multilabel document labels, resulting in improved segmentation performance that beats competing approaches on four out of five datasets and matches on the fifth, while also matching in multilabel classification with less computation time.
Segmenting text into semantically coherent segments is an important task with applications in information retrieval and text summarization. Developing accurate topical segmentation requires the availability of training data with ground truth information at the segment level. However, generating such labeled datasets, especially for applications in which the meaning of the labels is user-defined, is expensive and time-consuming. In this paper, we develop an approach that instead of using segment-level ground truth information, it instead uses the set of labels that are associated with a document and are easier to obtain as the training data essentially corresponds to a multilabel dataset. Our method, which can be thought of as an instance of distant supervision, improves upon the previous approaches by exploiting the fact that consecutive sentences in a document tend to talk about the same topic, and hence, probably belong to the same class. Experiments on the text segmentation task on a variety of datasets show that the segmentation produced by our method beats the competing approaches on four out of five datasets and performs at par on the fifth dataset. On the multilabel text classification task, our method performs at par with the competing approaches, while requiring significantly less time to estimate than the competing approaches.