Importance-Aware Data Augmentation for Document-Level Neural Machine Translation
Document-level neural machine translation (DocNMT) aims to generate translations that are both coherent and cohesive, in contrast to its sentence-level counterpart. However, due to its longer input length and limited availability of training data, DocNMT often faces the challenge of data sparsity. To overcome this issue, we propose a novel Importance-Aware Data Augmentation (IADA) algorithm for DocNMT that augments the training data based on token importance information estimated by the norm of hidden states and training gradients. We conduct comprehensive experiments on three widely-used DocNMT benchmarks. Our empirical results show that our proposed IADA outperforms strong DocNMT baselines as well as several data augmentation approaches, with statistical significance on both sentence-level and document-level BLEU.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationMachine TranslationSentenceTranslationSimilar Papers 제목 키워드 기반
Discourse-Aware Unsupervised Summarization of Long Scientific Documents
We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents. Our method assumes a two-level hierarchical graph representation of the source document, and exploits asymme…
ArticlesExtractive SummarizationSentenceUnsupervised Extractive SummarizationDiscourse-Aware Unsupervised Summarization for Long Scientific Documents
We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents. Our method assumes a two-level hierarchical graph representation of the source document, and exploits asymme…
ArticlesExtractive SummarizationSentenceUnsupervised Document Embedding via Contrastive Augmentation
We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image …
Contrastive LearningData AugmentationDocument ClassificationDocument Embedding+3Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character Augmentation
We propose a new character-based text classification framework for non-alphabetic languages, such as Chinese and Japanese. Our framework consists of a variational character encoder (VCE) and character-level text classifi…
ClassificationData AugmentationGeneral ClassificationSentence+2Improving Document-Level Sentiment Classification Using Importance of Sentences
Previous researchers have considered sentiment analysis as a document classification task, in which input documents are classified into predefined sentiment classes. Although there are sentences in a document that suppor…
ClassificationDocument ClassificationGeneral ClassificationSentence+4