SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.09590 · 2019

Rethinking Attribute Representation and Injection for Sentiment Classification

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Text attributes, such as user and product information in product reviews, have been used to improve the performance of sentiment classification models. The de facto standard method is to incorporate them as additional biases in the attention mechanism, and more performance gains are achieved by extending the model architecture. In this paper, we show that the above method is the least effective way to represent and inject attributes. To demonstrate this hypothesis, unlike previous models with complicated architectures, we limit our base model to a simple BiLSTM with attention classifier, and instead focus on how and where the attributes should be incorporated in the model. We propose to represent attributes as chunk-wise importance weight matrices and consider four locations in the model (i.e., embedding, encoding, attention, classifier) to inject attributes. Experiments show that our proposed method achieves significant improvements over the standard approach and that attention mechanism is the worst location to inject attributes, contradicting prior work. We also outperform the state-of-the-art despite our use of a simple base model. Finally, we show that these representations transfer well to other tasks. Model implementation and datasets are released here: https://github.com/rktamplayo/CHIM.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1908.09590")
get_code_for_paper("1908.09590")
have("1908.09590")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1908.09590.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1908.09590.svg)](https://syntology.ai/paper/1908.09590)

Connect an agent — have() is free.