Neural Baselines for Word Alignment
Word alignments identify translational correspondences between words in a parallel sentence pair and is used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems , or to perform quality estimation. In most areas of natural language processing, neural network models nowadays constitute the preferred approach, a situation that might also apply to word alignment models. In this work, we study and comprehensively evaluate neural models for unsupervised word alignment for four language pairs, contrasting several variants of neural models. We show that in most settings, neural versions of the IBM-1 and hidden Markov models vastly outperform their discrete counterparts. We also analyze typical alignment errors of the baselines that our models overcome to illustrate the benefits-and the limitations-of these new models for morphologically rich languages.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationSentenceTranslationWord AlignmentSimilar Papers 제목 키워드 기반
Accurate Word Alignment Induction from Neural Machine Translation
Despite its original goal to jointly learn to align and translate, prior researches suggest that Transformer captures poor word alignments through its attention mechanism. In this paper, we show that attention weights DO…
DecoderMachine TranslationMulti-Task LearningTranslation+1Word Rotator's Distance
A key principle in assessing textual similarity is measuring the degree of semantic overlap between two texts by considering the word alignment. Such alignment-based approaches are intuitive and interpretable; however, t…
Semantic SimilaritySemantic Textual SimilaritySentenceWord Alignment+1Table-based Fact Verification with Self-labeled Keypoint Alignment
Table-based fact verification aims to verify whether a statement sentence is trusted or fake. Most existing methods rely on graph feature or data augmentation but fail to investigate evidence correlation between the stat…
AttributeContrastive LearningData AugmentationFact Verification+3A Discriminative Neural Model for Cross-Lingual Word Alignment
We introduce a novel discriminative word alignment model, which we integrate into a Transformer-based machine translation model. In experiments based on a small number of labeled examples (~1.7K-5K sentences) we evaluate…
Machine TranslationNERTranslationWord AlignmentBetter Together: Modern Methods Plus Traditional Thinking in NP Alignment
We study a typical intermediary task to Machine Translation, the alignment of NPs in the bitext. After arguing that the task remains relevant even in an end-to-end paradigm, we present simple, dictionary- and word vector…
LemmatizationMachine TranslationTranslation