Meaningful Clustering of Senses Helps Boost Word Sense Disambiguation Performance

By Roberto Navigli. 2006

192 citations recorded by the source corpus.

Fine-grained sense distinctions are one of the major obstacles to successful Word Sense Disambiguation. In this paper, we present a method for reducing the granularity of the WordNet sense inventory based on the mapping to a manually crafted dictionary encoding sense hierarchies, namely the Oxford Dictionary of English. We assess the quality of the mapping and the induced clustering, and evaluate the performance of coarse WSD systems in the Senseval-3 English all-words task.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Natural Language Processing

Citations in the corpus

WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations (2018, background): “WordNet is known to be a ﬁne-grained resource (Navigli, 2006).”
Towards a Seamless Integration of Word Senses into Downstream NLP Applications (2017, methodology): “The issue can be tackled by grouping together similar senses of the same word, either using automatic clustering techniques (Navigli, 2006; Agirre and Lopez, 2003; Snow et al., 2007) or with the help of WordNet’s lexicographer”
From Word to Sense Embeddings: A Survey on Vector Representations of Meaning (2018, background): “It has been pointed out that sense distinctions in WordNet might be too ﬁne-grained to be useful for many NLP applications (Navigli, 2006; Snow et al., 2007; Hovy et al., 2013).”
BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network (2012, result): “the discussion in [86,87]); second, the meanings of Wikipages are intuitively coarser than those in WordNet.”
Align, Disambiguate and Walk: A Unified Approach for Measuring Semantic Similarity (2013, unknown): “In addition, we show in Table 7 the F-score results provided by Snow et al. (2007) for their SVM-based system and for the mapping-based approach of Navigli (2006), denoted by ODE.”
Learning to Merge Word Senses (2007, methodology): “(Navigli, 2006) presents an automatic approach for mapping between sense inventories; here similarities in gloss deﬁnition and structured relations be-tween the two sense inventories are exploited in order to map between WordNet senses and distinctions made within the coarser-grained Oxford English…”
Coarse Word-Sense Disambiguation Using Common Sense (2010, methodology): “The senses were created semi-automatically using a clustering algorithm developed by the task administrators (Navigli 2006), and then manually verified.”
WiC: 10, 000 Example Pairs for Evaluating Context-Sensitive Representations (2018, background): “WordNet is known to be a fine-grained resource (Navigli, 2006).”