Paraphrasing vs Coreferring: Two Sides of the Same Coin
This work addresses predicate variability for NLP researchers, offering incremental improvements by leveraging cross-task data and models.
The paper tackled the problem of predicate lexical variability in NLP by exploring synergy between predicate paraphrasing and event coreference resolution. It achieved over 18 points gain in average precision for paraphrase ranking and modest improvements in coreference model performance.
We study the potential synergy between two different NLP tasks, both confronting predicate lexical variability: identifying predicate paraphrases, and event coreference resolution. First, we used annotations from an event coreference dataset as distant supervision to re-score heuristically-extracted predicate paraphrases. The new scoring gained more than 18 points in average precision upon their ranking by the original scoring method. Then, we used the same re-ranking features as additional inputs to a state-of-the-art event coreference resolution model, which yielded modest but consistent improvements to the model's performance. The results suggest a promising direction to leverage data and models for each of the tasks to the benefit of the other.