Semantic Regularities in Document Representations

by   Fei Sun, et al.
Institute of Computing Technology, Chinese Academy of Sciences

Recent work exhibited that distributed word representations are good at capturing linguistic regularities in language. This allows vector-oriented reasoning based on simple linear algebra between words. Since many different methods have been proposed for learning document representations, it is natural to ask whether there is also linear structure in these learned representations to allow similar reasoning at document level. To answer this question, we design a new document analogy task for testing the semantic regularities in document representations, and conduct empirical evaluations over several state-of-the-art document representation models. The results reveal that neural embedding based document representations work better on this analogy task than conventional methods, and we provide some preliminary explanations over these observations.


page 1

page 2

page 3

page 4


Efficient Vector Representation for Documents through Corruption

We present an efficient document representation learning framework, Docu...

Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec

Distributed dense word vectors have been shown to be effective at captur...

Contextualized Word Representations for Reading Comprehension

Reading a document and extracting an answer to a question about its cont...

Semantic Graphs for Generating Deep Questions

This paper proposes the problem of Deep Question Generation (DQG), which...

Semantic Document Distance Measures and Unsupervised Document Revision Detection

In this paper, we model the document revision detection problem as a min...

Proof of the tree module property for exceptional representations of the quiver 𝔼_6

This document (together with the ancillary file e6_proof.pdf) is an appe...

Simple Search Algorithms on Semantic Networks Learned from Language Use

Recent empirical and modeling research has focused on the semantic fluen...

Please sign up or login with your details

Forgot password? Click here to reset