DeepAI AI Chat
Log In Sign Up

Enhancing Word Embeddings with Knowledge Extracted from Lexical Resources

by   Magdalena Biesialska, et al.
Universitat Politècnica de Catalunya

In this work, we present an effective method for semantic specialization of word vector representations. To this end, we use traditional word embeddings and apply specialization methods to better capture semantic relations between words. In our approach, we leverage external knowledge from rich lexical resources such as BabelNet. We also show that our proposed post-specialization method based on an adversarial neural network with the Wasserstein distance allows to gain improvements over state-of-the-art methods on two tasks: word similarity and dialog state tracking.


page 1

page 2

page 3

page 4


Integrating Lexical Knowledge in Word Embeddings using Sprinkling and Retrofitting

Neural network based word embeddings, such as Word2Vec and GloVe, are pu...

Lexical semantics enhanced neural word embeddings

Current breakthroughs in natural language processing have benefited dram...

LexSubCon: Integrating Knowledge from Lexical Resources into Contextual Embeddings for Lexical Substitution

Lexical substitution is the task of generating meaningful substitutes fo...

SenseFitting: Sense Level Semantic Specialization of Word Embeddings for Word Sense Disambiguation

We introduce a neural network-based system of Word Sense Disambiguation ...

Enhanced word embeddings using multi-semantic representation through lexical chains

The relationship between words in a sentence often tells us more about t...

Derivational Morphological Relations in Word Embeddings

Derivation is a type of a word-formation process which creates new words...

Using meaning instead of words to track topics

The ability to monitor the evolution of topics over time is extremely va...