mlsanityData to 7 Oct 2026

Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing

arXiv 2106.04814 ↗First posted 9 Jun 2021cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Abstract Meaning Representation (AMR) is a rooted, labeled, acyclic graph representing the semantics of natural language. As previous works show, although AMR is designed for English at first, it can also represent semantics in other languages. However, they find that concepts in their predicted AMR graphs are less specific. We argue that the misprediction of concepts is due to the high relevance between English tokens and AMR concepts. In this work, we introduce bilingual input, namely the translated texts as well as non-English texts, in order to enable the model to predict more accurate concepts. Besides, we also introduce an auxiliary task, requiring the decoder to predict the English sequences at the same time. The auxiliary task can help the decoder understand what exactly the corresponding English tokens are. Our proposed cross-lingual AMR parser surpasses previous state-of-the-art parser by 10.6 points on Smatch F1 score. The ablation study also demonstrates the efficacy of our proposed modules.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 37 references that are in the map. First posted on arXiv 9 Jun 2021.

Builds on

23 of 37 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  5. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  6. 2019Cross-lingual Language Model Pretrainingcited by 1,088
  7. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  8. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
  9. 2017Neural AMR: Sequence-to-Sequence Models for Parsing and Generationcited by 56
  10. 2019AMR Parsing as Sequence-to-Graph Transductioncited by 50
  11. 2020AMR Parsing via Graph-Sequence Iterative Inferencecited by 47
  12. 2018Toward Abstractive Summarization Using Semantic Representationscited by 43
11 more
  1. 2019Semantic Neural Machine Translation using AMRcited by 37
  2. 2018AMR Parsing as Graph Prediction with Latent Alignmentcited by 36
  3. 2018Abstract Meaning Representation for Multi-Document Summarizationcited by 35
  4. 2016An Incremental Parser for Abstract Meaning Representationcited by 34
  5. 2019Broad-Coverage Semantic Parsing as Transductioncited by 32
  6. 2020Improving AMR Parsing with Sequence-to-Sequence Pre-trainingcited by 30
  7. 2019Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learningcited by 25
  8. 2017Cross-lingual Abstract Meaning Representation Parsingcited by 19
  9. 2017Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representationscited by 18
  10. 2020Pushing the Limits of AMR Parsing with Self-Learningcited by 16
  11. 2018An AMR Aligner Tuned by Transition-based Parsercited by 12

Built on by

Cited by year

Citing papers per year: 2021: 1.

1 paper.

  1. 2021Maximum Bayes Smatch Ensemble Distillation for AMR Parsingcited by 27