Pengfei Liu, Tianxiang Sun, Xipeng Qiu, Hang Yan, Junqi Dai
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Aspect-Based Sentiment Analysis (ABSA), aiming at predicting the polarities for aspects, is a fine-grained task in the field of sentiment analysis. Previous work showed syntactic information, e.g. dependency trees, can effectively improve the ABSA performance. Recently, pre-trained models (PTMs) also have shown their effectiveness on ABSA. Therefore, the question naturally arises whether PTMs contain sufficient syntactic information for ABSA so that we can obtain a good ABSA model only based on PTMs. In this paper, we firstly compare the induced trees from PTMs and the dependency parsing trees on several popular models for the ABSA task, showing that the induced tree from finetuned RoBERTa (FT-RoBERTa) outperforms the parser-provided tree. The further analysis experiments reveal that the FT-RoBERTa Induced Tree is more sentiment-word-oriented and could benefit the ABSA task. The experiments also show that the pure RoBERTa-based model can outperform or approximate to the previous SOTA performances on six datasets across four languages since it implicitly incorporates the task-oriented syntactic information. 1 * Equal contribution. † Corresponding author. 1 Our code will be released at https://github.com/ ROGERDJQ/RoBERTaABSA.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.04986")
get_code_for_paper("2104.04986")
have("2104.04986")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.04986.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.04986)
Connect an agent — have() is free.