Papers with word embedding algorithm

2 papers
Word-Node2Vec: Improving Word Embedding with Document-Level Non-Local Word Co-occurrences (N19-1)

Copied to clipboard

Challenge: Existing word embedding algorithms make a strong assumption that words are semantically related only if they co-occur locally within a window of fixed size.
Approach: They propose a graph-based word embedding method that relies on locality to capture the semantic association between words that co-occur frequently but non-locally within documents.
Outcome: The proposed method outperforms word2vec and glove on a range of different tasks, such as predicting word-pair similarity, word analogy and concept categorization.
MGAD: Multilingual Generation of Analogy Datasets (L18-1)

Copied to clipboard

Challenge: Existing methods for word embedding evaluation are computationally expensive and task-specific.
Approach: They propose a minimally supervised method for generating word embedding evaluation datasets for a large number of languages using existing dependency treebanks and parsers.
Outcome: The proposed method evaluates three popular word embedding algorithms against these datasets and shows that their performance varies between syntactic categories.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations