Entity-Centric Coreference Resolution with Model Stacking

Abstract

Mention pair models that predict whether or not two mentions are coreferent have historically been very effective for coreference resolution, but do not make use of entity-level information. However, we show that the scores produced by such models can be aggregated to define powerful entity-level features between clusters of mentions. Using these features, we train an entity-centric coreference system that learns an effective policy for building up coreference chains incrementally. The mention pair scores are also used to prune the search space the system works in, allowing for efficient training with an exact loss function. We evaluate our system on the English portion of the 2012 CoNLL Shared Task dataset and show that it improves over the current state of the art.

Different German and English Coreference Resolution Models for Multi-domain Content Curation Scenarios

“…There is a large body of work for coreference resolution in English. While the sieve-based approach (Raghunathan et al 2010) is a prime example of rule-based coreference resolution, other approaches such as the Mention-Rank model (Clark and Manning 2015) and Neural model (Clark and Manning 2016) have been shown to outperform it.…”

“…While we developed the rule-based approach (CoRefGer-rule), we also adapted the Stanford CoreNLP statistical system based on the Mention Ranking model (Clark and Manning 2015). We trained our coreference system on the TüBa-D/Z (Telljohann et al 2004), and evaluated on the same dataset as SemEval 2010 Task 1 (Recasens et al 2010).…”

“…In this paper, we describe our forays into developing a German coreference resolution system. We attempt to adapt the Stanford CoreNLP (Manning et al 2014) Deterministic (rule-based) Coreference Resolution approach (Raghunathan et al 2010;Lee et al 2013) as well as the Stanford CoreNLP Mention Ranking (statistical) model (Clark and Manning 2015) to German. We also experiment with projection-based implementation, i.e., using Machine Translation and English coreference models to achieve German coreference resolution.…”

Using Coreference Links to Improve Spanish-to-English Machine Translation

“…Interpolation between the best and worse candidate is considered (Wiseman et al, 2015;Bengtson and Roth, 2008). Finally, the clustering approach considers the features of a complete cluster of mentions to decide whether a mention belongs or not to a cluster (Clark and Manning, 2015;Fernandes et al, 2012).…”

“…The automatic translation comes from a commercial online MT system, while the human translation was done by the authors of this paper. The Stanford Statistical Coreference Resolution system (Clark and Manning, 2015) 2 was applied to both translations, and the resulting coreference chains are indicated in the table with numbers and colors. We observe that the chains in the human translation match well those in the source, but this is less the case for the automatic translation, in particular due to wrong pronoun translations.…”