Abstract
Frame-semantic Parsing (FSP) is a challenging and critical task in Natural Language Processing (NLP). Most of the existing studies decompose the FSP task into frame identification (FI) and frame semantic role labeling (FSRL) subtasks, and adopt a pipeline model architecture that clearly causes error propagation problem. However, recent jointly learning models aim to address the above problem and generally treat FSP as a span-level structured prediction task, which, unfortunately, leads to cascading error propagation problem between roles and less-efficient solutions due to huge search space of roles. To address these problems, we reformulate the FSRL task into a target-aware relation classification task and propose a novel and lightweight jointly learning framework that simultaneously processes three subtasks of FSP, including frame identification, argument identification, and role classification. The novel task formulation and jointly learning with interaction mechanisms among subtasks can help improve the overall system performance and reduce the search space and time complexity, compared with existing methods. Extensive experimental results demonstrate that our proposed model significantly outperforms 10 state-of-the-art models in terms of F1 score across two benchmark datasets.
- [1] . 2007. SemEval-2007 task 19: Frame semantic structure extraction. In Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval’07). Association for Computational Linguistics, 99–104.Google Scholar
Cross Ref
- [2] . 1998. The Berkeley FrameNet project. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics. Association for Computational Linguistics, 86–90.
DOI: Google ScholarDigital Library
- [3] . 2021. Joint multi-decoder framework with hierarchical pointer network for frame semantic parsing. In Findings of the Association for Computational Linguistics. Association for Computational Linguistics, 2570–2578.
DOI: Google ScholarCross Ref
- [4] . 2014. Frame-semantic parsing. Comput. Ling. 40, 1 (2014), 9–56.
DOI: Google ScholarDigital Library
- [5] . 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 4171–4186.
DOI: Google ScholarCross Ref
- [6] . 2017. Deep biaffine attention for neural dependency parsing. ArXiv abs/1611.01734 (2017).Google Scholar
- [7] . 2019. Span-based joint entity and relation extraction with transformer pre-training. CoRR abs/1909.07755 (2019).Google Scholar
- [8] . 2001. Frame semantics for text understanding. In Proceedings of the NAACL WordNet and Other Lexical Resources Workshop. Association for Computational Linguistics, Pittsburgh.Google Scholar
- [9] . 1985. Frames and the semantics of understanding. Quaderni di Semantica 6, 2 (1985), 222–254.Google Scholar
- [10] . 2015. Semantic role labeling with neural network factors. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Lisbon, 960–970.
DOI: Google ScholarCross Ref
- [11] . 2002. Automatic labeling of semantic roles. Comput. Ling. 28, 3 (
Sept. 2002), 245–288.DOI: Google ScholarDigital Library
- [12] . 2021. Frame Semantics guided network for abstractive sentence summarization. Knowl.-based Syst. 221 (2021), 106973.
DOI: Google ScholarCross Ref
- [13] . 2020. Incorporating syntax and frame semantics in neural network for machine reading comprehension. In Proceedings of the 28th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Barcelona, 2635–2641.
DOI: Google ScholarCross Ref
- [14] . 2020. A frame-based sentence representation for machine reading comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 891–896.
DOI: Google ScholarCross Ref
- [15] . 2017. Out-of-domain FrameNet semantic role labeling. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics, 471–482.Google Scholar
Cross Ref
- [16] . 2014. Semantic frame identification with distributed word representations. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Valencia, 1448–1458.
DOI: Google ScholarCross Ref
- [17] . 2014. Semantic frame identification with distributed word representations. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics ACL 2014, June 22-27, 2014, Baltimore, MD, USA, Volume 1: Long Papers. The Association for Computer Linguistics, 1448–1458.
DOI: Google ScholarCross Ref
- [18] . 2021. A graph-based neural model for end-to-end frame semantic parsing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Punta Cana, 3864–3874.
DOI: Google ScholarCross Ref
- [19] . 2016. Leveraging FrameNet to improve automatic event detection. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Berlin, 2134–2143.
DOI: Google ScholarCross Ref
- [20] . 2018. A span selection model for semantic role labeling. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, 1630–1642.
DOI: Google ScholarCross Ref
- [21] . 2018. Learning joint semantic parsers from disjoint data. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, New Orleans, 1492–1502.
DOI: Google ScholarCross Ref
- [22] . 2014. GloVe: Global vectors for word representation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’14). Association for Computational Linguistics, Doha, 1532–1543.
DOI: Google ScholarCross Ref
- [23] . 2015. Context-aware frame-semantic role labeling. Trans. Assoc. Comput. Ling. 3 (2015), 449–460.
DOI: Google ScholarCross Ref
- [24] . 2016. FrameNet ii: Extended Theory and Practice. Retrieved from https://framenet2.icsi.berkeley.edu/docs/r1.7/book.pdf.Google Scholar
- [25] . 2020. Semantic role labeling as syntactic dependency parsing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’20). Association for Computational Linguistics, 7551–7571.
DOI: Google ScholarCross Ref
- [26] . 2021. A knowledge-guided framework for frame identification. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, 5230–5240.
DOI: Google ScholarCross Ref
- [27] . 2017. Frame-semantic parsing with softmax-margin segmental RNNs and a syntactic scaffold. CoRR abs/1706.09528 (2017).Google Scholar
- [28] . 2015. Efficient inference and structured learning for semantic role labeling. Trans. Assoc. Comput. Ling. 3 (2015), 29–41.Google Scholar
Cross Ref
- [29] . 2015. Efficient inference and structured learning for semantic role labeling. Trans. Assoc. Comput. Ling. 3 (2015), 29–41.
DOI: Google ScholarCross Ref
- [30] . 2021. UniRE: A unified label space for entity relation extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, 220–231.
DOI: Google ScholarCross Ref
- [31] . 2011. N.: Wsabie: Scaling up to large vocabulary image annotation. In Proceedings of the International Joint Conference on Artificial Intelligence.Google Scholar
- [32] . 2021. Learning span-level interactions for aspect sentiment triplet extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, 4755–4766.
DOI: Google ScholarCross Ref
- [33] . 2017. A joint sequential and relational model for frame-semantic parsing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 1247–1256.Google Scholar
Cross Ref
- [34] . 2020. Named entity recognition as dependency parsing. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 6470–6476.
DOI: Google ScholarCross Ref
- [35] . 2020. CFSRE: Context-aware based on frame-semantics for distantly supervised relation extraction. Knowl.-based Syst. 210 (2020), 106480.
DOI: Google ScholarCross Ref
- [36] . 2021. A frustratingly easy approach for entity and relation extraction. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 50–61.
DOI: Google ScholarCross Ref
Index Terms
A Span-based Target-aware Relation Model for Frame-semantic Parsing
Recommendations
A multilingual FrameNet-based grammar and lexicon for controlled natural language
Berkeley FrameNet is a lexico-semantic resource for English based on the theory of frame semantics. It has been exploited in a range of natural language processing applications and has inspired the development of framenets for many languages. We present ...
Frame-semantic web: a case study for Korean
ISWC-PD'14: Proceedings of the 2014 International Conference on Posters & Demonstrations Track - Volume 1272FrameNet itself can become a resource for the Semantic Web. It can be represented in RDF. However, mapping FrameNet to other resources such as Wikipedia for building a knowledge base becomes more common practice. By such mapping, FrameNet can be ...
Frame-semantic parsing
Frame semantics is a linguistic theory that has been instantiated for English in the FrameNet lexicon. We solve the problem of frame-semantic parsing using a two-stage statistical model that takes lexical targets i.e., content words and phrases in their ...






Comments