A Synset Relation-enhanced Framework with a Try-again Mechanism for Word Sense Disambiguation

Abstract Contextual embeddings are proved to be overwhelmingly effective to the task of Word Sense Disambiguation (WSD) compared with other sense representation techniques. However, these embeddings fail to embed sense knowledge in semantic networks. In this paper, we propose a Synset Relation-Enhanced Framework (SREF) that leverages sense relations for both sense embedding enhancement and a try-again mechanism that implements WSD again, after obtaining basic sense embeddings from augmented WordNet glosses. Experiments on all-words and lexical sample datasets show that the proposed system achieves new state-of- the-art results, defeating previous knowledge-based systems by at least 5.5 F1 measure. When the system utilizes sense embeddings learned from SemCor, it outperforms all previous supervised systems with only 20% SemCor data. 1 Introduction Word Sense Disambiguation (WSD) is an ongoing research area in Natural Language Processing community. It is aimed at determining the correct meaning (sense) of a word in its context given a list of potential or competing senses in a sense inventory. According to Navigli (2009), most of WSD solutions can be categorized into supervised and knowledge-based approaches. For supervised systems, they rely on sense-annotated data to train either word experts (Zhong and Ng, 2010) or a neural language model (Raganato et al., 2017a) for disambiguation and thus perform better than their * corresponding author knowledge-based counterparts (Banerjee and Pedersen, 2002; Basile et al., 2014; Agirre et al., 2014), which merely utilize sense knowledge in a sense inventory. However, knowledge-based approaches can better scale to a multilingual scenario or a specific domain where sense annotation is limited. Contextual representations learned from neural language models (Peters et al., 2018) are proved to be beneficial to the task of WSD. Many recent systems (Loureiro and Jorge, 2019; Vial et al., 2019; Scarlini et al., 2020) utilize language models, especially BERT (Devlin et al., 2019), as a feature extraction tool to obtain contextual sense representations and outperform previous approaches by large margins. There are also systems (Luo et al., 2018; Kumar et al., 2019) that incorporate sense definitions into language models and achieve state-of-the-art performance. However, most of the systems are implemented in a supervised manner using a widely exploited sense-annotated corpus, SemCor (Miller et al., 1994), and merging knowledge from the sense inventory as a supplement. There is much space to explore regarding how to better exploit knowledge in a sense inventory such as different WordNet relations and super-sense categorizes WordNet senses into 45 clusters. that In this paper, we present SREF, a knowledge- enhanced WSD approach that effectively exploits the sense definitions and relations in an inventory. First, we design a gloss augmentation for those synsets that have a short definition in WordNet so that each synset can learn a reliable sense embedding with features from BERT. Then, based on these embeddings, we explore the contribution of different synset relations in WordNet (Miller, 1995) to learn relation-enhanced sense embeddings. After the first WSD is conducted with a nearest neighbor approach against an A Synset Relation-enhanced Framework with a Try-again Mechanism for Word Sense …

Content truncated to 500 words