AMR(Abstract Meaning Representation)abstracts the semantic features of a given text into a single-root directed acyclic graph.Due to the lack of non-English language AMR datasets,cross-lingual AMR parsing aims to parse non-English text into the corresponding AMR graph of its English translation.Current cross-lingual AMR parsing methods rely on large-scale English-target language par-allel corpora or high-performance English-target language translation models to build(English,target language,AMR)triplet parallel corpora for target language AMR parsing.In contrast to this assump-tion,this paper explores the possibility of achieving cross-lingual AMR parsing with only large-scale monolingual English and target language corpora.To this end,we propose cross-lingual AMR parsing based on unsupervised pretraining.Specifically,during pretraining,we integrate unsupervised neural machine translation tasks,English AMR parsing tasks,and target language AMR parsing tasks.During fine-tuning,we use an English AMR2.0-based target language AMR dataset for single-task fine-tuning.Experimental results on AMR2.0 and a multilingual AMR test set show that our method achieves Smatch F1 scores of 67.89,68.04,and 67.99 in German,Spanish,and Italian,respectively.
关键词
跨语言AMR语义解析/序列到序列模型/预训练模型
Key words
cross-lingual AMR parsing/seq2seq model/pre-trained model
维普
万方数据