Papers
Topics
Authors
Recent
Detailed Answer
Quick Answer
Concise responses based on abstracts only
Detailed Answer
Well-researched responses based on abstracts and relevant paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses
Gemini 2.5 Flash
Gemini 2.5 Flash 88 tok/s
Gemini 2.5 Pro 52 tok/s Pro
GPT-5 Medium 12 tok/s Pro
GPT-5 High 19 tok/s Pro
GPT-4o 110 tok/s Pro
GPT OSS 120B 470 tok/s Pro
Kimi K2 197 tok/s Pro
2000 character limit reached

Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy (2403.00354v2)

Published 1 Mar 2024 in cs.CL

Abstract: In the task of aspect sentiment quad prediction (ASQP), generative methods for predicting sentiment quads have shown promising results. However, they still suffer from imprecise predictions and limited interpretability, caused by data scarcity and inadequate modeling of the quadruplet composition process. In this paper, we propose Self-Consistent Reasoning-based Aspect-sentiment quadruple Prediction (SCRAP), optimizing its model to generate reasonings and the corresponding sentiment quadruplets in sequence. SCRAP adopts the Extract-Then-Assign reasoning strategy, which closely mimics human cognition. In the end, SCRAP significantly improves the model's ability to handle complex reasoning tasks and correctly predict quadruplets through consistency voting, resulting in enhanced interpretability and accuracy in ASQP.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (18)
  1. Aspect-category based sentiment analysis with hierarchical graph convolutional network. In International Conference on Computational Linguistics.
  2. Aspect-category-opinion-sentiment quadruple extraction with implicit aspects and opinions. In Annual Meeting of the Association for Computational Linguistics.
  3. Mvp: Multi-view prompting improves aspect sentiment tuple prediction. In Annual Meeting of the Association for Computational Linguistics.
  4. Large language models are reasoning teachers. In Annual Meeting of the Association for Computational Linguistics.
  5. Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. ArXiv, abs/2305.02301.
  6. Lora: Low-rank adaptation of large language models. ArXiv, abs/2106.09685.
  7. Improving aspect sentiment quad prediction via template-order data augmentation. In Conference on Empirical Methods in Natural Language Processing.
  8. Large language models are zero-shot reasoners. ArXiv, abs/2205.11916.
  9. Symbolic chain-of-thought distillation: Small models can also “think” step-by-step. ArXiv, abs/2306.14050.
  10. Teaching small language models to reason. ArXiv, abs/2212.08410.
  11. Semeval-2014 task 4: Aspect based sentiment analysis. In International Workshop on Semantic Evaluation.
  12. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21:140:1–140:67.
  13. Yi Chern Tan and Elisa Celis. 2019. Assessing social and intersectional biases in contextualized word representations. ArXiv, abs/1911.01485.
  14. Target-aspect-sentiment joint detection for aspect-based sentiment analysis. In AAAI Conference on Artificial Intelligence.
  15. Self-consistency improves chain of thought reasoning in language models. ArXiv, abs/2203.11171.
  16. Chain of thought prompting elicits reasoning in large language models. ArXiv, abs/2201.11903.
  17. Aspect sentiment quad prediction as paraphrase generation. In Conference on Empirical Methods in Natural Language Processing.
  18. Towards generative aspect-based sentiment analysis. In Annual Meeting of the Association for Computational Linguistics.
Citations (4)
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

Summary

We haven't generated a summary for this paper yet.

Ai Generate Text Spark Streamline Icon: https://streamlinehq.com

Paper Prompts

Sign up for free to create and run prompts on this paper using GPT-5.

Dice Question Streamline Icon: https://streamlinehq.com

Follow-up Questions

We haven't generated follow-up questions for this paper yet.