Anaphora Resolution in Dialogue: System Description (CODI-CRAC 2022 Shared Task)
Tatiana Anikina | Natalia Skachkova | Joseph Renner | Priyansh Trivedi
Proceedings of the CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue
We describe three models submitted for the CODI-CRAC 2022 shared task. To perform identity anaphora resolution, we test several combinations of the incremental clustering approach based on the Workspace Coreference System (WCS) with other coreference models. The best result is achieved by adding the “cluster merging” version of the coref-hoi model, which brings up to 10.33% improvement1 over vanilla WCS clustering. Discourse deixis resolution is implemented as multi-task learning: we combine the learning objective of coref-hoi with anaphor type classification. We adapt the higher-order resolution model introduced in Joshi et al. (2019) for bridging resolution given gold mentions and anaphors.
An End-to-End Approach for Full Bridging Resolution
Joseph Renner | Priyansh Trivedi | Gaurav Maheshwari | Rémi Gilleron | Pascal Denis
Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue
Message Passing for Hyper-Relational Knowledge Graphs
Mikhail Galkin | Priyansh Trivedi | Gaurav Maheshwari | Ricardo Usbeck | Jens Lehmann
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Hyper-relational knowledge graphs (KGs) (e.g., Wikidata) enable associating additional key-value pairs along with the main triple to disambiguate, or restrict the validity of a fact. In this work, we propose a message passing based graph encoder - StarE capable of modeling such hyper-relational KGs. Unlike existing approaches, StarE can encode an arbitrary number of additional information (qualifiers) along with the main triple while keeping the semantic roles of qualifiers and triples intact. We also demonstrate that existing benchmarks for evaluating link prediction (LP) performance on hyper-relational KGs suffer from fundamental flaws and thus develop a new Wikidata-based dataset - WD50K. Our experiments demonstrate that StarE based LP model outperforms existing approaches across multiple benchmarks. We also confirm that leveraging qualifiers is vital for link prediction with gains up to 25 MRR points compared to triple-based representations.
- Joseph Renner 2
- Gaurav Maheshwari 2
- Rémi Gilleron 1
- Pascal Denis 1
- Mikhail Galkin 1
- show all...