De-Conflated Semantic Representations

By Mohammad Taher Pilehvar, Nigel Collier. 2016

96 citations recorded by the source corpus.

One major deficiency of most semantic representation techniques is that they usually model a word type as a single point in the semantic space, hence conflating all the meanings that the word can have. Addressing this issue by learning distinct representations for individual meanings of words has been the subject of several research studies in the past few years. However, the generated sense representations are either not linked to any sense inventory or are unreliable for infrequent word senses. We propose a technique that tackles these problems by de-conflating the representations of words based on the deep knowledge it derives from a semantic network. Our approach provides multiple advantages in comparison to the past work, including its high coverage and the ability to generate accurate representations even for infrequent word senses. We carry out evaluations on six datasets across two semantic similarity tasks and report state-of-the-art results on most of them.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations (2018, methodology): “DeConf 12 (Pilehvar and Collier, 2016) exploits the knowledge encoded in WordNet.”
WiC: 10, 000 Example Pairs for Evaluating Context-Sensitive Representations (2018, methodology): “DeConf (Pilehvar and Collier, 2016) exploits the knowledge encoded in WordNet.”
THINGS: A database of 1,854 object concepts and more than 26,000 naturalistic object images (2019, methodology): “A recent modeling approach [33] combined word2vec with knowledge about different senses based on WordNet synsets, providing separate vectors for different meanings of words.”
Embedding Words and Senses Together via Joint Knowledge-Enhanced Training (2016, background): “In order to obtain a representation for each sense of a word, a number of approaches have leveraged lexical resources to learn sense embeddings as a result of post-processing conventional word embeddings (Chen et al., 2014; Johansson and Pina, 2015; Jauhar et al., 2015; Rothe and Schütze, 2015; Pile”
From Word to Sense Embeddings: A Survey on Vector Representations of Meaning (2018, methodology): “The meaning conﬂation can have additional negative impacts on accurate semantic modeling, e.g., semantically unrelated words that are similar to diﬀerent senses of a word are pulled towards each other in the semantic space (Neelakantan, Shankar, Passos, & McCallum, 2014; Pilehvar & Collier, 2016).”
Towards a Seamless Integration of Word Senses into Downstream NLP Applications (2017, methodology): “We follow Pilehvar and Collier (2016) and set δ = 5.”