Any-gram Kernels for Sentence Classification: A Sentiment Analysis Case Study

12/19/2017
by   Rasoul Kaljahi, et al.
0

Any-gram kernels are a flexible and efficient way to employ bag-of-n-gram features when learning from textual data. They are also compatible with the use of word embeddings so that word similarities can be accounted for. While the original any-gram kernels are implemented on top of tree kernels, we propose a new approach which is independent of tree kernels and is more efficient. We also propose a more effective way to make use of word embeddings than the original any-gram formulation. When applied to the task of sentiment classification, our new formulation achieves significantly better performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/10/2019

Better Word Embeddings by Disentangling Contextual n-Gram Information

Pre-trained word vectors are ubiquitous in Natural Language Processing a...
research
07/27/2017

Analysis of Italian Word Embeddings

In this work we analyze the performances of two of the most used word em...
research
07/20/2020

Morphological Skip-Gram: Using morphological knowledge to improve word representation

Natural language processing models have attracted much interest in the d...
research
11/13/2017

Convolutional Neural Network with Word Embeddings for Chinese Word Segmentation

Character-based sequence labeling framework is flexible and efficient fo...
research
02/04/2018

Smooth q-Gram, and Its Applications to Detection of Overlaps among Long, Error-Prone Sequencing Reads

We propose smooth q-gram, the first variant of q-gram that captures q-gr...
research
07/05/2021

On Bi-gram Graph Attributes

We propose a new approach to text semantic analysis and general corpus a...
research
05/17/2016

Word2Vec is a special case of Kernel Correspondence Analysis and Kernels for Natural Language Processing

We show Correspondence Analysis (CA) is equivalent to defining Gini-inde...

Please sign up or login with your details

Forgot password? Click here to reset