Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards. / Aralikatte, Rahul Rajendra; Abdou, Mostafa Hany Mohamed Anwar ; Lent, Heather Christine; Hershcovich, Daniel; Søgaard, Anders.
Proceedings of the AAAI-21 International Joint Conference on Artificial Intelligence. AAAI Press, 2021. (Proceedings of the International Joint Conference on Artificial Intelligence; Nr. 14, Bind 35).Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards
AU - Aralikatte, Rahul Rajendra
AU - Abdou, Mostafa Hany Mohamed Anwar
AU - Lent, Heather Christine
AU - Hershcovich, Daniel
AU - Søgaard, Anders
PY - 2021
Y1 - 2021
N2 - 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 to semantics in NLP.
AB - 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 to semantics in NLP.
M3 - Article in proceedings
T3 - Proceedings of the International Joint Conference on Artificial Intelligence
BT - Proceedings of the AAAI-21 International Joint Conference on Artificial Intelligence
PB - AAAI Press
Y2 - 2 February 2021 through 9 February 2021
ER -
ID: 287187332