Work

Building a robust sentiment lexicon with (almost) no resource

Year: 2016

Type: preprint

Abstract: Creating sentiment polarity lexicons is labor intensive. Automatically translating them from resourceful languages requires in-domain machine translation systems, which rely on large quantities of bi-texts. In this paper, we propose to replace machine translation by transferring words from the lexicon through word embeddings aligned across languages with a simple linear transform. The approach leads to no degradation, compared to machine translation, when tested on sentiment polarity classification on tweets from four languages.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1612.05202

Authors: Rouvier, Mickael, Favre, Benoit

Institutions: Centre National de la Recherche Scientifique, Aix-Marseille Université, Laboratoire d’Informatique Fondamentale de Marseille

Language: English

Topic: Sentiment Analysis and Opinion Mining

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: European Commission

Awards: G3207356259, G393177772, G5702163051, Making Sense of Human-Human Conversation Data

OpenAlex ID: W2585266243

Cites: 14

Cited by:

Related to: 20