CLJul 26, 2017

Strawman: an Ensemble of Deep Bag-of-Ngrams for Sentiment Analysis

arXiv:1707.08939v11087 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental contribution for participants in a specific NLP workshop shared task.

The paper tackled the problem of creating an automated sentiment analyzer for a shared task, resulting in a system named 'strawman' that uses an ensemble of deep bag-of-ngrams models.

This paper describes a builder entry, named "strawman", to the sentence-level sentiment analysis task of the "Build It, Break It" shared task of the First Workshop on Building Linguistically Generalizable NLP Systems. The goal of a builder is to provide an automated sentiment analyzer that would serve as a target for breakers whose goal is to find pairs of minimally-differing sentences that break the analyzer.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes