Projects per year
Modern state-of-the-art Semantic Role Labeling (SRL) methods rely on expressive sentence encoders (e.g., multi-layer LSTMs) but tend to model only local (if any) interactions between individual argument labeling decisions. This contrasts with earlier work and also with the intuition that the labels of individual arguments are strongly interdependent. We model interactions between argument labeling decisions through iterative refinement. Starting with an output produced by a factorized model, we iteratively refine it using a refinement network. Instead of modeling arbitrary interactions among roles and words, we encode prior knowledge about the SRL problem by designing a restricted network architecture capturing non-local interactions. This modeling choice prevents overfitting and results in an effective model, outperforming strong factorized baseline models on all 7 CoNLL-2009 languages, and achieving state-of-the-art results on 5 of them, including English.
|Title of host publication||Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)|
|Place of Publication||Hong Kong, China|
|Publisher||Association for Computational Linguistics|
|Number of pages||12|
|Publication status||Published - 3 Nov 2019|
|Event||2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing - Hong Kong, Hong Kong|
Duration: 3 Nov 2019 → 7 Nov 2019
|Conference||2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing|
|Abbreviated title||EMNLP-IJCNLP 2019|
|Period||3/11/19 → 7/11/19|
FingerprintDive into the research topics of 'Semantic Role Labeling with Iterative Structure Refinement'. Together they form a unique fingerprint.
- 1 Active
1/05/17 → 30/04/22