Reducing Disambiguation Biases in NMT by Leveraging Explicit Word Sense Information
Recent studies have shed some light on a common pitfall of Neural Machine Translation (NMT) models, stemming from their struggle to disambiguate polysemous words without lapsing into their most frequently occurring senses in the training corpus.In this paper, we first provide a novel approach for automatically creating high-precision sense-annotated parallel corpora, and then put forward a specifically tailored fine-tuning strategy for exploiting these sense annotations during training without introducing any additional requirement at inference time.The use of explicit senses proved to be beneficial to reduce the disambiguation bias of a baseline NMT model, while, at the same time, leading our system to attain higher BLEU scores than its vanilla counterpart in 3 language pairs.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationNMTTranslationSimilar Papers 제목 키워드 기반
Quantum Visual Word Sense Disambiguation: Unraveling Ambiguities Through Quantum Inference Model
Visual word sense disambiguation focuses on polysemous words, where candidate images can be easily confused. Traditional methods use classical probability to calculate the likelihood of an image matching each gloss of th…
Word Sense DisambiguationQuantum Machine LearningImage MatchingLeveraging Word-Formation Knowledge for Chinese Word Sense Disambiguation
In parataxis languages like Chinese, word meanings are constructed using specific word-formations, which can help to disambiguate word senses. However, such knowledge is rarely explored in previous word sense disambiguat…
Word Sense DisambiguationDetecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks
Word sense disambiguation is a well-known source of translation errors in NMT. We posit that some of the incorrect disambiguation choices are due to models' over-reliance on dataset artifacts found in training data, spec…
Adversarial AttackMachine TranslationNMTTranslation+1ConSeC: Word Sense Disambiguation as Continuous Sense Comprehension
Supervised systems have nowadays become the standard recipe for Word Sense Disambiguation (WSD), with Transformer-based language models as their primary ingredient. However, while these systems have certainly attained un…
Word Sense DisambiguationOne Classifier for All Ambiguous Words: Overcoming Data Sparsity by Utilizing Sense Correlations Across Words
Most supervised word sense disambiguation (WSD) systems build word-specific classifiers by leveraging labeled data. However, when using word-specific classifiers, the sparseness of annotations leads to inferior sense dis…
AllWord EmbeddingsWord Sense Disambiguation