Paraphrasing vs Coreferring: Two Sides of the Same Coin

Abstract

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.

Generalizing Cross-Document Event Coreference Resolution Across Multiple Corpora

“…In recent years, new CDCR corpora such as the Gun Violence Corpus (GVC) (Vossen et al 2018) and Football Coreference Corpus (FCC) (Bugert et al 2020) have been developed, and the state-of-the-art performance on the most commonly used corpus ECB+ (Cybulska and Vossen 2014b) has risen steadily (Meged et al 2020;Barhom et al 2019;Kenyon-Dean, Cheung, and Precup 2018). We believe that CDCR can play a vital role for downstream multi-document tasks, and so do other authors in this area (Bejan and Harabagiu 2014;Yang, Cardie, and Frazier 2015;Upadhyay et al 2016;Choubey and Huang 2017;Choubey, Raju, and Huang 2018;Choubey and Huang 2018;Kenyon-Dean, Cheung, and Precup 2018;Barhom et al 2019).…”

“…Yet, despite the progress made so far, we are not aware of a study which demonstrates that employing a recent CDCR system is indeed helpful downstream. We make the key observation that all existing CDCR systems (Meged et al 2020;Cremisini and Finlayson 2020;Barhom et al 2019;Kenyon-Dean, Cheung, and Precup 2018;Mirza, Darari, and Mahendra 2018;Vossen 2018) were designed, trained, and evaluated on a single corpus respectively. This points to a risk of systems overspecializing on their target corpus instead of learning to solve the overall task, rendering such systems unsuitable for downstream applications where generality and robustness is required.…”

“…Table 3 shows a comparison of the core principles of several CDCR systems in terms of their mention distance computation, learning approach and more. We compare the systems of Cremisini and Finlayson 2020 (CR2020), Meged et al 2020, Barhom et al 2019, Kenyon-Dean, Cheung, and Precup Computational Linguistics Just Accepted MS.…”

“…https://doi.org/10.1162/coli_a_00407.pdf © 2021 Association for Computational Linguistics Published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license Meged et al (2020), a cluster-pair approach in which a multi-layer perceptron is trained to jointly resolve entity and event coreference. It is an extension of Barhom et al (2019), adding paraphrasing 8 Computational Linguistics Just Accepted MS.…”

“…With respect to the two steps a CDCR system needs to perform (event mention detection and event coreference resolution), several authors have decided to omit the first step and work on gold mentions alone (Cybulska and Vossen 2015;Kenyon-Dean, Cheung, and Precup 2018;Barhom et al 2019;Meged et al 2020) which simplifies the task and system development. Systems which include a mention detection step (Lee et al 2012;Yang, Cardie, and Frazier 2015;Vossen and Cybulska 2016;Choubey and Huang 2017;Vossen 2018;Cremisini and Finlayson 2020) are more faithful to the task but risk introducing another source of error.…”