Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards


  • Rahul Aralikatte University of Copenhagen
  • Mostafa Abdou University of Copenhagen
  • Heather C Lent University of Copenhagen
  • Daniel Hershcovich University of Copenhagen
  • Anders Søgaard University of Copenhagen



Discourse, Pragmatics & Argument Mining


Coreference resolution and semantic role labeling are NLP tasks that capture different aspects of semantics, indicating respectively, which expressions refer to the same entity, and what semantic roles expressions serve in the sentence. However, they are often closely interdependent, and both generally necessitate natural language understanding. Do they form a coherent abstract representation of documents? We present a neural network architecture for joint coreference resolution and semantic role labeling for English, and train graph neural networks to model the 'coherence' of the combined shallow semantic graph. Using the resulting coherence score as a reward for our joint semantic analyzer, we use reinforcement learning to encourage global coherence over the document and between semantic annotations. This leads to improvements on both tasks in multiple datasets from different domains, and across a range of encoders of different expressivity, calling, we believe, for a more holistic approach for semantics in NLP.




How to Cite

Aralikatte, R., Abdou, M., Lent, H. C., Hershcovich, D., & Søgaard, A. (2021). Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14), 12516-12525.



AAAI Technical Track on Speech and Natural Language Processing I