Semantically Driven Sentence Fusion: Modeling and Evaluation
Abstract
Sentence fusion is the task of joining related sentences into coherent text. Current training
and evaluation schemes for this task are based on single reference ground-truths and do not
account for valid fusion variants. We show that this hinders models from robustly capturing
the semantic relationship between input sentences. To alleviate this, we present an approach
in which ground-truth solutions are automatically expanded into multiple references
via curated equivalence classes of connective phrases. We apply this method to a large-scale
dataset and use the augmented dataset for both model training and evaluation. To improve
the learning of semantic representation using multiple references, we enrich the model with
auxiliary discourse classification tasks under a multi-tasking framework. Our experiments
highlight the improvements of our approach over state-of-the-art models.
and evaluation schemes for this task are based on single reference ground-truths and do not
account for valid fusion variants. We show that this hinders models from robustly capturing
the semantic relationship between input sentences. To alleviate this, we present an approach
in which ground-truth solutions are automatically expanded into multiple references
via curated equivalence classes of connective phrases. We apply this method to a large-scale
dataset and use the augmented dataset for both model training and evaluation. To improve
the learning of semantic representation using multiple references, we enrich the model with
auxiliary discourse classification tasks under a multi-tasking framework. Our experiments
highlight the improvements of our approach over state-of-the-art models.
Research Areas
