Embedding Words and Senses Together via Joint Knowledge-Enhanced Training
Word embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora. However, their creation process does not allow the different meanings of a word to be automatically separated, as it conflates them into a single vector. We address this issue by proposing a new model which learns word and sense embeddings jointly. Our model exploits large corpora and knowledge from semantic networks in order to produce a unified vector space of word and sense embeddings. We evaluate the main features of our approach both qualitatively and quantitatively in a variety of tasks, highlighting the advantages of the proposed method in comparison to state-of-the-art word- and sense-based models.
Code (0)
등록된 구현이 없습니다.
Tasks
Word EmbeddingsSimilar Papers 제목 키워드 기반
Neural Embedding Language Models in Semantic Clustering of Web Search Results
In this paper, a new approach towards semantic clustering of the results of ambiguous search queries is presented. We propose using distributed vector representations of words trained with the help of prediction-based ne…
ClusteringTogether We Make Sense -- Learning Meta-Sense Embeddings from Pretrained Static Sense Embeddings
Sense embedding learning methods learn multiple vectors for a given ambiguous word, corresponding to its different word senses. For this purpose, different methods have been proposed in prior work on sense embedding lear…
Word Sense DisambiguationA Differentiable Self-disambiguated Sense Embedding Model via Scaled Gumbel Softmax
We present a differentiable multi-prototype word representation model that disentangles senses of polysemous words and produces meaningful sense-specific embeddings without external resources. It jointly learns how to di…
Hard AttentionSentenceWord SimilarityMoving Down the Long Tail of Word Sense Disambiguation with Gloss-Informed Biencoders
A major obstacle in Word Sense Disambiguation (WSD) is that word senses are not uniformly distributed, causing existing models to generally perform poorly on senses that are either rare or unseen during training. We prop…
Word Sense DisambiguationMoving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders
A major obstacle in Word Sense Disambiguation (WSD) is that word senses are not uniformly distributed, causing existing models to generally perform poorly on senses that are either rare or unseen during training. We prop…
Word Sense Disambiguation