Data Augmentation for Machine Translation via Dependency Subtree Swapping

• URL: http://arxiv.org/abs/2307.07025v1
• Date: Thu, 13 Jul 2023 19:00:26 GMT
• Title: Data Augmentation for Machine Translation via Dependency Subtree Swapping
• Authors: Attila Nagy, Dorina Petra Lakatos, Botond Barta, Patrick Nanys, Judit \'Acs
• Abstract summary: We present a generic framework for data augmentation via dependency subtree swapping. We extract corresponding subtrees from the dependency parse trees of the source and target sentences and swap these across bisentences to create augmented samples. We conduct resource-constrained experiments on 4 language pairs in both directions using the IWSLT text translation datasets and the Hunglish2 corpus.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a generic framework for data augmentation via dependency subtree swapping that is applicable to machine translation. We extract corresponding subtrees from the dependency parse trees of the source and target sentences and swap these across bisentences to create augmented samples. We perform thorough filtering based on graphbased similarities of the dependency trees and additional heuristics to ensure that extracted subtrees correspond to the same meaning. We conduct resource-constrained experiments on 4 language pairs in both directions using the IWSLT text translation datasets and the Hunglish2 corpus. The results demonstrate consistent improvements in BLEU score over our baseline models in 3 out of 4 language pairs. Our code is available on GitHub.

Related papers

• TreeSwap: Data Augmentation for Machine Translation via Dependency Subtree Swapping [0.0]
  We introduce a novel augmentation method, which generates new sentences by swapping objects and subjects across bisentences. TreeSwap achieves consistent improvements over baseline models in 4 language pairs in both directions on resource-constrained datasets. We also explore domain-specific corpora, but find that our method does not make significant improvements on law, medical and IT data.
  arXiv  Detail & Related papers  (2023-11-04T09:27:40Z)
• Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction [92.84968716013783]
  Cross-lingual relation extraction (XRE) aggressively leverage the language-consistent structural features from the universal dependency (UD) resource. We investigate an unbiased UD-based XRE transfer by constructing a type of code-mixed UD forest. With such forest features, the gaps of UD-based XRE between the training and predicting phases can be effectively closed.
  arXiv  Detail & Related papers  (2023-05-20T18:24:06Z)
• TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding [56.794981024301094]
  We propose a compositional data augmentation approach for natural language understanding called TreeMix. Specifically, TreeMix leverages constituency parsing tree to decompose sentences into constituent sub-structures and the Mixup data augmentation technique to recombine them to generate new sentences. Compared with previous approaches, TreeMix introduces greater diversity to the samples generated and encourages models to learn compositionality of NLP data.
  arXiv  Detail & Related papers  (2022-05-12T15:25:12Z)
• Coordinate Constructions in English Enhanced Universal Dependencies: Analysis and Computational Modeling [1.9950682531209154]
  We address the representation of coordinate constructions in Enhanced Universal Dependencies (UD) We create a large-scale dataset of manually edited syntax graphs. We identify several systematic errors in the original data, and propose to also propagate adjuncts.
  arXiv  Detail & Related papers  (2021-03-16T10:24:27Z)
• Multilingual Irony Detection with Dependency Syntax and Neural Models [61.32653485523036]
  It focuses on the contribution from syntactic knowledge, exploiting linguistic resources where syntax is annotated according to the Universal Dependencies scheme. The results suggest that fine-grained dependency-based syntactic information is informative for the detection of irony.
  arXiv  Detail & Related papers  (2020-11-11T11:22:05Z)
• GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction [107.8262586956778]
  We introduce graph convolutional networks (GCNs) with universal dependency parses to learn language-agnostic sentence representations. GCNs struggle to model words with long-range dependencies or are not directly connected in the dependency tree. We propose to utilize the self-attention mechanism to learn the dependencies between words with different syntactic distances.
  arXiv  Detail & Related papers  (2020-10-06T20:30:35Z)
• pyBART: Evidence-based Syntactic Transformations for IE [52.93947844555369]
  We present pyBART, an easy-to-use open-source Python library for converting English UD trees to Enhanced UD graphs or to our representation. When evaluated in a pattern-based relation extraction scenario, our representation results in higher extraction scores than Enhanced UD, while requiring fewer patterns.
  arXiv  Detail & Related papers  (2020-05-04T07:38:34Z)
• Extractive Summarization as Text Matching [123.09816729675838]
  This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems. We formulate the extractive summarization task as a semantic text matching problem. We have driven the state-of-the-art extractive result on CNN/DailyMail to a new level (44.41 in ROUGE-1)
  arXiv  Detail & Related papers  (2020-04-19T08:27:57Z)
• Cross-Lingual Adaptation Using Universal Dependencies [1.027974860479791]
  We show that models trained using UD parse trees for complex NLP tasks can characterize very different languages. Based on UD parse trees, we develop several models using tree kernels and show that these models trained on the English dataset can correctly classify data of other languages.
  arXiv  Detail & Related papers  (2020-03-24T13:04:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.