Entity-Centric Joint Modeling of Japanese Coreference Resolution and Predicate Argument Structure Analysis

Abstract

Predicate argument structure analysis is a task of identifying structured events. To improve this field, we need to identify a salient entity, which cannot be identified without performing coreference resolution and predicate argument structure analysis simultaneously. This paper presents an entity-centric joint model for Japanese coreference resolution and predicate argument structure analysis. Each entity is assigned an embedding, and when the result of both analyses refers to an entity, the entity embedding is updated. The analyses take the entity embedding into consideration to access the global information of entities. Our experimental results demonstrate the proposed method can improve the performance of the intersentential zero anaphora resolution drastically, which is a notoriously difficult task in predicate argument structure analysis.

Annotating a Driving Experience Corpus with Behavior and Subjectivity

“…Zero anaphora resolution is an active topic in NLP in Japanese (e.g., Shibata and Kurohashi 2018). With improvements in zero anaphora resolution, we expect to apply such results to the CRF models by adding these as one of the features, and to the BiLSTM-CRF models by adding the identified nominatives in the blog sentences in the future.…”

Machine Comprehension Improves Domain-Specific Japanese Predicate-Argument Structure Analysis

“…We conduct PAS analysis experiments of our MCsingle/merged/stepwise methods using the PAS-QA and RC-QA datasets. We also compare our methods with the neural network-based PAS analysis model (Shibata and Kurohashi, 2018) (hereafter, NN-PAS), which achieved the state-of-theart accuracy on Japanese PAS analysis.…”

“…We construct a PAS-QA dataset in which a question asks an omitted argument for a predicate. We focus on the ga case (nominative), the wo case (accusative), and the ni case (dative), which are targeted in the Japanese PAS analysis literature (Shibata et al, 2016;Shibata and Kurohashi, 2018;Kurita et al, 2018;Ouchi et al, 2017). As a source corpus, we use blog articles included in the Driving Experience Corpus (Iwai et al, 2019).…”

“…The state-of-the-art baseline PAS analyzer, NN-PAS, was trained using the existing PAS dataset, KWDLC 4 (Kyoto University Web Document Leads Corpus), as described in Shibata and Kurohashi (2018). We also trained an NN-PAS model using the PAS-QA dataset in addition to KWDLC (hereafter, NN-PAS ′ ).…”

Neural Japanese Zero Anaphora Resolution with Candidate Reduction Using Large-scale Case Frames

“…Shibata and Kurohashi 2018; Kurita, Kawahara, and Kurohashi 2018) NAIST (NTC) (Iida, Komachi, Inui, and Matsumoto 2007) 1 (BCCWJ) (Maekawa, Yamazaki, Ogiso, Maruyama, Ogura, Kashino, Koiso, Yamaguchi, Tanaka, and Imamura, Saito, and Izumi (2009) 40,000 Hangyo et al 20133,000 Ouchi, Shindo, Duh, and Matsumoto (2015) 40,000 Shibata et al (2016) 15,000 Iida, Torisawa, Oh, Kruengkrai, and Kloetzer (2016) 40,000 Ouchi et al (2017) 40,000 Matsubayashi and Inui (2017) 40,000 Shibata and Kurohashi (2018) 15,000 Kurita et al (2018) 15,000 Matsubayashi and Inui (2018) 40,000 Sasano and Kurohashi (2011) 1,000 60,000…”