arXiv 2408.094812024-08cs.CLcs.AI

PanoSent：用于多模态对话式基于方面情感分析的全景六元组抽取基准

PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis

National University of Singapore（新加坡国立大学）；Wuhan University（武汉大学）；The University of Auckland（奥克兰大学）；Singapore University of Technology and Design（新加坡科技设计大学）；Nanyang Technological University（南洋理工大学）

Meng Luo, Hao Fei, Bobo Li, Shengqiong Wu, Qian Liu, Soujanya Poria, Erik Cambria, Mong-Li Lee, Wynne Hsu

备注：: Accepted by ACM MM 2024 (Oral)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出多模态对话式 ABSI 任务与 PanoSent 基准，通过 Chain-of-Sentiment、Sentica 和复述验证实现全景情感六元组抽取及情感翻转分析。

摘要：

尽管现有的基于方面情感分析（ABSA）已获得大量投入与进展，但在定义更整体的研究目标方面仍存在空白：该目标需要无缝整合多模态、对话语境和细粒度，同时覆盖不断变化的情感动态以及认知因果理据。本文通过引入多模态对话式 ABSA 来弥合这些空白，并提出两个新颖子任务：1）全景情感六元组抽取，从多轮、多方多模态对话中全景式识别持有者、目标、方面、观点、情感和理据；2）情感翻转分析，检测贯穿对话的动态情感转变及其因果原因。为对这些任务进行基准测试，我们构建了 PanoSent，这是一个同时采用人工与自动标注的数据集，具有高质量、大规模、多模态、多语言、多场景特点，并覆盖隐式与显式情感元素。为有效解决这些任务，我们设计了新颖的 Chain-of-Sentiment 推理框架，并结合新颖的多模态大语言模型（名为 Sentica）和基于复述的验证机制。大量评估表明，我们的方法优于强基线，验证了所提全部方法的有效性。该工作有望为 ABSA 社区开启新时代，因此所有代码和数据均已在 https://PanoSent.github.io/ 开放。

英文摘要：

While existing Aspect-based Sentiment Analysis (ABSA) has received extensive effort and advancement, there are still gaps in defining a more holistic research target seamlessly integrating multimodality, conversation context, fine-granularity, and also covering the changing sentiment dynamics as well as cognitive causal rationales. This paper bridges the gaps by introducing a multimodal conversational ABSA, where two novel subtasks are proposed: 1) Panoptic Sentiment Sextuple Extraction, panoramically recognizing holder, target, aspect, opinion, sentiment, rationale from multi-turn multi-party multimodal dialogue. 2) Sentiment Flipping Analysis, detecting the dynamic sentiment transformation throughout the conversation with the causal reasons. To benchmark the tasks, we construct PanoSent, a dataset annotated both manually and automatically, featuring high quality, large scale, multimodality, multilingualism, multi-scenarios, and covering both implicit and explicit sentiment elements. To effectively address the tasks, we devise a novel Chain-of-Sentiment reasoning framework, together with a novel multimodal large language model (namely Sentica) and a paraphrase-based verification mechanism. Extensive evaluations demonstrate the superiority of our methods over strong baselines, validating the efficacy of all our proposed methods. The work is expected to open up a new era for the ABSA community, and thus all our codes and data are open at https://PanoSent.github.io/

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。