Browse > Methodology > Representation Learning > Document Embedding

Document Embedding

8 papers with code · Methodology

Leaderboards

No evaluation results yet. Help compare methods by submit evaluation metrics.

Greatest papers with code

An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation

WS 2016 jhlau/doc2vec

Recently, Le and Mikolov (2014) proposed doc2vec as an extension to word2vec (Mikolov et al., 2013a) to learn document-level embeddings.

DOCUMENT EMBEDDING WORD EMBEDDINGS

Document Embedding with Paragraph Vectors

29 Jul 2015inejc/paragraph-vectors

Paragraph Vectors has been recently proposed as an unsupervised method for learning distributed representations for pieces of texts.

DOCUMENT EMBEDDING SENTIMENT ANALYSIS WORD EMBEDDINGS

Word Mover's Embedding: From Word2Vec to Document Embedding

EMNLP 2018 IBM/WordMoversEmbeddings

While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised sentences or documents embeddings.

DOCUMENT EMBEDDING SENTENCE EMBEDDING TEXT CLASSIFICATION WORD EMBEDDINGS

Crosslingual Document Embedding as Reduced-Rank Ridge Regression

8 Apr 2019epfl-dlab/Cr5

Finally, although not trained for embedding sentences and words, it also achieves competitive performance on crosslingual sentence and word retrieval tasks.

DOCUMENT EMBEDDING

Learning Outside the Box: Discourse-level Features Improve Metaphor Identification

NAACL 2019 jayelm/broader-metaphor

Most current approaches to metaphor identification use restricted linguistic contexts, e. g. by considering only a verb's arguments or the sentence containing a phrase.

DOCUMENT EMBEDDING

Can x2vec Save Lives? Integrating Graph and Language Embeddings for Automatic Mental Health Classification

4 Jan 2020AlexMRuch/Can-x2vec-Save-Lives

Visualizing graph embeddings annotated with predictions of potentially suicidal individuals shows the integrated model could classify such individuals even if they are positioned far from the support group.

ACTION CLASSIFICATION ACTIVITY PREDICTION DOCUMENT EMBEDDING FEATURE ENGINEERING GRAPH EMBEDDING

Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks

22 Apr 2020CRIPAC-DIG/TextING

However, the existing graph-based works can neither capture the contextual word relationships within each document nor fulfil the inductive learning of new words.

DOCUMENT EMBEDDING TEXT CLASSIFICATION