Neural Sequence Learning Models for Word Sense Disambiguation

By Alessandro Raganato, Claudio Delli Bovi, Roberto Navigli. 2017

201 citations recorded by the source corpus.

Word Sense Disambiguation models exist in many flavors. Even though supervised ones tend to perform best in terms of accuracy, they often lose ground to more flexible knowledge-based solutions, which do not require training by a word expert for every disambiguation target. To bridge this gap we adopt a different perspective and rely on sequence learning to frame the disambiguation problem: we propose and study in depth a series of end-to-end neural architectures directly tailored to the task, from bidirectional Long Short-Term Memory to encoder-decoder models. Our extensive evaluation over standard benchmarks and in multiple languages shows that sequence learning enables more versatile all-words models that consistently lead to state-of-the-art results, even against word experts with engineered features.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Deep Contextualized Word Representations (2018, methodology): “Table 5 compares WSD results using the evaluation framework from Raganato et al. (2017b) across the same suite of four test sets in Raganato et al. (2017a).”
Knowledge Enhanced Contextual Word Representations (2019, methodology): “…neighbor approach trained on the SemCor dataset, similar to the evaluation in Melamud et al. (2016), which has previously been shown to be competitive with task-speciﬁc architectures (Raganato et al., 2017 match the performance of KnowBert-WordNet despite incorporating both Wikipedia and WordNet.”
Findings of the Third Shared Task on Multimodal Machine Translation (2018, methodology): “The main idea is to have the cross-lingual WSD model select the translation candidate which correctly dis-ambiguates ambiguous words in the source sentence and the intuition is that the image could help in the disambiguation process.”
Multi-Task Learning for Sequence Tagging: An Empirical Study (2018, background): “Exceptions to this include the work of (Collobert et al., 2011), which considers four tasks: POS, CHUNK, NER, and SRL; (Raganato et al., 2017), which considers three: word sense disambiguation with POS and coarse-grained semantic tagging based on WordNet lexicographer files; (Hashimoto et al., 2017)”
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors (2018, methodology): “While current state-of-theart methods often use powerful recurrent models (Raganato et al., 2017), we will instead use a sim- ple similarity-based approach that heavily depends on the synset embedding itself and thus serves as a more useful indicator of representation quality.”
From Word to Sense Embeddings: A Survey on Vector Representations of Meaning (2018, methodology): “For a comprehensive historical overview of WSD we would recommend the survey of Navigli (2009), and a more recent analysis of current methods can be found in the empirical comparison of Raganato et al. (2017a).”