SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.00169 · 2020

Understanding Pre-trained BERT for Aspect-based Sentiment Analysis

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

This paper analyzes the pre-trained hidden representations learned from reviews on BERT for tasks in aspect-based sentiment analysis (ABSA). Our work is motivated by the recent progress in BERT-based language models for ABSA. However, it is not clear how the general proxy task of (masked) language model trained on unlabeled corpus without annotations of aspects or opinions can provide important features for downstream tasks in ABSA. By leveraging the annotated datasets in ABSA, we investigate both the attentions and the learned representations of BERT pre-trained on reviews. We found that BERT uses very few self-attention heads to encode context words (such as prepositions or pronouns that indicating an aspect) and opinion words for an aspect. Most features in the representation of an aspect are dedicated to the fine-grained semantics of the domain (or product category) and the aspect itself, instead of carrying summarized opinions from its context. We hope this investigation can help future research in improving self-supervised learning, unsupervised learning and fine-tuning for ABSA. The pre-trained model and code can be found at https://github.com/howardhsu/BERT-for-RRC-ABSA.

For agents

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

get_harvested_code_for_paper("2011.00169")
get_code_for_paper("2011.00169")
have("2011.00169")

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

curl https://syntology.ai/api/ran/2011.00169.json

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

[![Syntology run record](https://syntology.ai/api/ran/2011.00169.svg)](https://syntology.ai/paper/2011.00169)

Connect an agent — have() is free.