基于无监督预训练的跨语言AMR解析  

Cross-lingual AMR parsing based on unsupervised pre-training

作　　者：范林雨 李军辉[1] 孔芳[1] FAN Lin-yu;LI Jun-hui;KONG Fang(School of Computer Science&Technology,Soochow University,Suzhou 215006,China)

机构地区：[1]苏州大学计算机科学与技术学院,江苏苏州215006

出　　处：《计算机工程与科学》2024年第1期170-178,共9页Computer Engineering & Science

摘　　要：抽象语义表示AMR是将给定文本的语义特征抽象成一个单根的有向无环图。由于缺乏非英文语言的AMR数据集,跨语言AMR解析通常指给定非英文目标语言文本,构建其英文翻译对应的AMR图。目前跨语言AMR解析的相关工作均基于大规模英文-目标语言平行语料或高性能英文-目标语言翻译模型,通过构建(英文,目标语言和AMR)三元平行语料进行目标语言的AMR解析。与该假设不同的是,本文探索在仅具备大规模单语英文和单语目标语言语料的情况下,实现跨语言AMR解析。为此,提出基于无监督预训练的跨语言AMR解析方法。具体地,在预训练过程中,融合无监督神经机器翻译任务、英文和目标语言AMR解析任务;在微调过程中,使用基于英文AMR 2.0转换的目标语言AMR数据集进行单任务微调。基于AMR 2.0和多语言AMR测试集的实验结果表明,所提方法在德文、西班牙文和意大利文上分别获得了67.89%,68.04%和67.99%的Smatch F1值。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 parallel 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 assumption,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 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]