AutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemes

Abstract

We present \textit{AutoExtend}, a system to learn embeddings for synsets and lexemes. It is flexible in that it can take any word embeddings as input and does not need an additional training corpus. The synset/lexeme embeddings obtained live in the same vector space as the word embeddings. A sparse tensor formalization guarantees efficiency and parallelizability. We use WordNet as a lexical resource, but AutoExtend can be easily applied to other resources like Freebase. AutoExtend achieves state-of-the-art performance on word similarity and word sense disambiguation tasks.

References in corpus (1)

• Natural Language Processing (almost) from Scratch

Cited by in corpus (22)

• Leveraging Pre-trained Checkpoints for Sequence Generation Tasks
• Ultradense Word Embeddings by Orthogonal Transformation
• Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings
• Semi-supervised Word Sense Disambiguation with Neural Models
• Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection
• Multi-sense embeddings through a word sense disambiguation process
• An Ensemble Method to Produce High-Quality Word Embeddings (2016)
• LMMS Reloaded: Transformer-based Sense Embeddings for Disambiguation and Beyond
• Bilingual Embeddings with Random Walks over Multilingual Wordnets
• An Analysis on the Learning Rules of the Skip-Gram Model
• MUSE: Modularizing Unsupervised Sense Embeddings
• Knowledge Fusion via Embeddings from Text, Knowledge Graphs, and Images
• Sense representations for Portuguese: experiments with sense embeddings and deep neural language models
• Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy
• Leveraging Lexical Resources for Learning Entity Embeddings in Multi-Relational Data
• Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings
• A Comparison of Word Embeddings for English and Cross-Lingual Chinese Word Sense Disambiguation
• Building domain specific lexicon based on TikTok comment dataset
• Embedding Words and Senses Together via Joint Knowledge-Enhanced Training
• SenseFitting: Sense Level Semantic Specialization of Word Embeddings for Word Sense Disambiguation
• Using Multi-Sense Vector Embeddings for Reverse Dictionaries
• Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation