A Mention-Ranking Model for Abstract Anaphora Resolution

Ana Marasovic, Leo Born, Juri Opitz, Anette Frank

Abstract: Resolving abstract anaphora is an important, but difficult task for text understanding. With recent advances in representation learning this task becomes a tangible aim. A central property of abstract anaphora is that it establishes a relation between the anaphor embedded in the anaphoric sentence and its (typically non-nominal) antecedent. We propose an LSTM-based mention-ranking model that learns how abstract anaphors relate to their antecedents with a Siamese Net. We overcome the lack of training data by generating artificial anaphoric sentence-antecedent pairs. Our model outperforms state-of-the-art results on shell noun resolution. We also report first benchmark results on an abstract anaphora subset of the ARRAU corpus. This corpus presents a greater challenge due to a greater range of confounders. Our model is able to select syntactically plausible candidates and - if disregarding syntax - discriminates candidates using deeper features. Deeper inspection shows that the model is able to learn a relation between the anaphor in the anaphoric sentence and its antecedent.