An Easier and Efficient Framework to Annotate Semantic Roles: Evidence from the Chinese AMR Corpus

Song, Li; Wen, Yinghong; Ge, Sijia; Li, Bin; Qu, Weiguang

doi:10.1007/978-3-030-38189-9_49

Cited by 3 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More details can be found in Appendix C.1. Another fact worth noting is that AMR can be used to improve downstream tasks, such as MRC (Sachan and Xing, 2016), TE (Lien and Kouylekov, 2015), RE (Garg et al, 2019) and SRL (Song et al, 2018). The benefits of QUASE QAM R on downstream tasks show that we can take advantage of AMR by learning from much cheaper QA signals dedicated to it.…”

Section: Comparison With Symbolic Meaning Representationsmentioning

confidence: 99%

QuASE: Question-Answer Driven Sentence Encoding

He¹,

Ning²,

Roth³

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Question-answering (QA) data often encodes essential information in many facets. This paper studies a natural question: Can we get supervision from QA data for other tasks (typically, non-QA ones)? For example, can we use QAMR to improve named entity recognition? We suggest that simply further pre-training BERT is often not the best option, and propose the questionanswer driven sentence encoding (QUASE) framework. QUASE learns representations from QA data, using BERT or other state-ofthe-art contextual language models. In particular, we observe the need to distinguish between two types of sentence encodings, depending on whether the target task is a single-or multisentence input; in both cases, the resulting encoding is shown to be an easy-to-use plugin for many downstream tasks. This work may point out an alternative way to supervise NLP tasks. 1

show abstract

Section: Comparison With Symbolic Meaning Representationsmentioning

confidence: 99%

QuASE: Question-Answer Driven Sentence Encoding

He¹,

Ning²,

Roth³

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…On the other hand, previous work on multi-sentence AMR primarily focuses on data annotation. Song et al (2019a) annotate dropped pronouns over Chinese AMR but only deals with implicit roles in specific constructions. Gerber and Chai (2012) provide implicit role annotations, but the resources were limited to a small inventory of 5-10 predicate types rather than all implicit arguments.…”

Section: Related Workmentioning

confidence: 99%

End-to-End AMR Corefencence Resolution

Fu¹,

Song²,

Du³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Although parsing to Abstract Meaning Representation (AMR) has become very popular and AMR has been shown effective on many sentence-level tasks, little work has studied how to generate AMRs that can represent multi-sentence information. We introduce the first end-to-end AMR coreference resolution model in order to build multi-sentence AMRs. Compared with the previous pipeline and rule-based approaches, our model alleviates error propagation and it is more robust for both in-domain and out-domain situations. Besides, the document-level AMRs obtained by our model can significantly improve over the AMRs generated by a rule-based method (Liu et al., 2015) on text summarization.

show abstract

QuASE: Question-Answer Driven Sentence Encoding

Ning

Roth

2019

Preprint

View full text Add to dashboard Cite

An Easier and Efficient Framework to Annotate Semantic Roles: Evidence from the Chinese AMR Corpus

Cited by 3 publications

References 7 publications

QuASE: Question-Answer Driven Sentence Encoding

QuASE: Question-Answer Driven Sentence Encoding

End-to-End AMR Corefencence Resolution

QuASE: Question-Answer Driven Sentence Encoding

Contact Info

Product

Resources

About