Extending Multi-Text Sentence Fusion Resources via Pyramid Annotations
This work addresses a bottleneck for researchers in multi-document NLP tasks by providing a larger and more diverse dataset, though it is incremental.
The paper tackles the problem of limited datasets for sentence fusion in NLP by tripling the size of a previous dataset, resulting in more representative texts and improved model training.
NLP models that compare or consolidate information across multiple documents often struggle when challenged with recognizing substantial information redundancies across the texts. For example, in multi-document summarization it is crucial to identify salient information across texts and then generate a non-redundant summary, while facing repeated and usually differently-phrased salient content. To facilitate researching such challenges, the sentence-level task of \textit{sentence fusion} was proposed, yet previous datasets for this task were very limited in their size and scope. In this paper, we revisit and substantially extend previous dataset creation efforts. With careful modifications, relabeling and employing complementing data sources, we were able to triple the size of a notable earlier dataset. Moreover, we show that our extended version uses more representative texts for multi-document tasks and provides a larger and more diverse training set, which substantially improves model training.