← All sources · 返回文献列表

15. A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges

基于方面的情感分析综述:任务、方法与挑战 · Literature survey in natural language processing (NLP). We read the arXiv v2 version (22 PDF pages, dated 6 Nov 2022); page numbers below are PDF pages 1–22, not the journal pages 11019–11038. 自然语言处理(natural language processing, NLP)领域的文献综述。我们读的是 arXiv v2 版本(共 22 页 PDF,日期 6 Nov 2022);下文页码均为 PDF 页码 1–22,而非期刊页码 11019–11038。 · Ch 2, 8, 13 · 40 min

Zhang, W., Li, X., Deng, Y., Bing, L., & Lam, W. (2023). A survey on aspect-based sentiment analysis: Tasks, methods, and challenges. IEEE Transactions on Knowledge and Data Engineering, 35(11), 11019–11038. https://doi.org/10.1109/TKDE.2022.3230975

The paper in 60 seconds · 60 秒读懂

Why we read it · 为什么要读

20-minute reading path · 20 分钟阅读路线

Pages 页码What to read读什么
1–2Introduction and the four sentiment elements with Figure 1.引言,以及配合图 1 的四个情感要素。
7Table 3: every task shown on one sentence.表 3:用同一句话展示所有任务。
9–10Section 4.3 on ACSA and Figure 4: the task our method matches.第 4.3 节 ACSA 与图 4:与我们方法对应的任务。
12–13Section 5 on pre-trained models, including the robustness warning.第 5 节预训练模型,包括稳健性警告。
14Section 7.1 on small datasets and the cross-lingual gap in 6.2.第 7.1 节关于小数据集,以及第 6.2 节的跨语言缺口。

Abstract and 1. Introduction · 摘要与 1. 引言

Pages · 页码 1–2

2. Background (2.1 Four sentiment elements, 2.2 Definition, 2.3 Modeling paradigms, 2.4 Datasets and evaluations) · 2. 背景(2.1 四个情感要素、2.2 定义、2.3 建模范式、2.4 数据集与评估)

Pages · 页码 2–5

3. Single ABSA tasks (3.1 ATE, 3.2 ACD, 3.3 OTE, 3.4 ASC) · 3. 单一 ABSA 任务(3.1 ATE、3.2 ACD、3.3 OTE、3.4 ASC)

Pages · 页码 6–8

4. Compound ABSA tasks (4.1 AOPE, 4.2 E2E-ABSA, 4.3 ACSA, 4.4 ASTE, 4.5 ACSD, 4.6 ASQP) · 4. 复合 ABSA 任务(4.1 AOPE、4.2 E2E-ABSA、4.3 ACSA、4.4 ASTE、4.5 ACSD、4.6 ASQP)

Pages · 页码 8–12

5. ABSA with pre-trained language models · 5. 基于预训练语言模型的 ABSA

Pages · 页码 12–13

6. Transferable ABSA (6.1 Cross-domain, 6.2 Cross-lingual) · 6. 可迁移的 ABSA(6.1 跨领域、6.2 跨语言)

Pages · 页码 13–14

7. Challenges and future directions, and 8. Conclusions · 7. 挑战与未来方向,以及 8. 结论

Pages · 页码 14–15

Figures and tables · 图表解读

Exhibit 图表How to read it怎么看
Figure 1 (p. 2)One sentence, "The pizza is delicious", broken into its four sentiment elements. Read it as the template for any coded review.把一句“The pizza is delicious”拆成四个情感要素。可把它当作任何评论编码的模板。
Figure 2 (p. 3)Tree of all ABSA tasks with representative models. The top branch is single tasks; the bottom branch is compound tasks.全部 ABSA 任务的分类树,附代表性模型。上半部分是单一任务,下半部分是复合任务。
Table 1 (p. 4)Which modelling paradigm (SeqClass, TokenClass, MRC, Seq2Seq, pipeline) has been used for each task. A dash means no representative work.每个任务用过哪种建模范式(SeqClass、TokenClass、MRC、Seq2Seq、流水线)。短横线表示没有代表性研究。
Table 2 (p. 5)Common benchmark datasets with language, domain and which elements are labelled (a, c, p, o). Only ASC-QA and ASAP are Chinese.常用基准数据集,列出语言、领域和标注的要素(a、c、p、o)。其中只有 ASC-QA 和 ASAP 是中文。
Table 3 (p. 7)Input and output for every task on one sentence: "The pizza is delicious, but the service is terrible". The clearest page for telling tasks apart.用同一句“The pizza is delicious, but the service is terrible”展示每个任务的输入和输出。这是区分各任务最清楚的一页。
Figure 3 (p. 8)Map linking the four elements to the tasks that predict them. ACSA sits between aspect category and sentiment polarity.把四个要素与预测它们的任务连起来的关系图。ACSA 位于方面类别与情感极性之间。
Table 4 (p. 9)Joint versus unified tagging for E2E-ABSA on one laptop-processor sentence. Each word carries a boundary tag and a polarity tag.以一句关于笔记本处理器的句子,对比 E2E-ABSA 的联合标注与统一标注。每个词都带边界标签和极性标签。
Figure 4 (p. 10)Four unified ways to do ACSA, including the extra "N/A" column for categories not mentioned. Panel (4) generates the answer as a sentence.ACSA 的四种统一做法,包括为未提及类别加一列“N/A”。第 (4) 格直接把答案生成为一句话。
Figure 5 (p. 11)The same triplet task solved four ways: pipeline, tagging, MRC and Seq2Seq. Shows how framing changes the model.同一个三元组任务的四种解法:流水线、标注、MRC 和 Seq2Seq。展示问题框架如何改变模型。

Key terms · 关键术语

Term 术语Meaning解释
aspect-based sentiment analysis (ABSA)
基于方面的情感分析
Finding sentiment towards each part or feature of a product, not the review as a whole.分析用户对产品每个部分或特性的情感,而不是整条评论的总体情感。
aspect term
方面词
The target word that actually appears in the text, such as "pizza".文本中实际出现的评价对象词,例如“pizza”。
aspect category
方面类别
A label from a fixed list chosen for the domain, such as food or service.从该领域预先定好的类别清单中选出的标签,例如食物或服务。
opinion term
观点词
The words that carry the feeling, such as "delicious" or "terrible".承载感受的词,例如“delicious”或“terrible”。
sentiment polarity
情感极性
The direction of feeling: positive, negative or neutral.情感的方向:正面、负面或中性。
implicit aspect
隐含方面
A target that is meant but not named; the term is recorded as "null".评论所指但没有明说的对象;方面词记为“null”。
single vs compound ABSA task
单一与复合 ABSA 任务
Single tasks predict one element; compound tasks predict linked pairs, triplets or quads.单一任务只预测一个要素;复合任务预测相互关联的二元组、三元组或四元组。
aspect category sentiment analysis (ACSA)
方面类别情感分析
Detect which predefined categories a text discusses and the polarity of each.识别文本谈到哪些预定义类别,以及每个类别的情感极性。
aspect sentiment quad prediction (ASQP)
方面情感四元组预测
Predict category, term, polarity and opinion together; the hardest task.同时预测类别、方面词、极性和观点词;是最难的任务。
pre-trained language model (PLM)
预训练语言模型
A model such as BERT trained on huge text first, then fine-tuned for a task.像 BERT 这样先在海量文本上训练、再针对具体任务微调的模型。
Seq2Seq (sequence-to-sequence)
序列到序列
A model that reads text and writes an answer as new text.读入文本并以新文本形式写出答案的模型。
exact-match F1
完全匹配 F1
A prediction counts as correct only if every element equals the human label; F1 balances precision and recall.只有所有要素都与人工标注一致才算正确;F1 综合了精确率和召回率。
zero-shot / few-shot
零样本/少样本
Working with no, or only a few, labelled training examples.在没有或只有很少标注训练样本的情况下完成任务。
cross-lingual ABSA (XABSA)
跨语言 ABSA
Applying a model trained in one language to another language.把用一种语言训练的模型用到另一种语言上。

Numbers we can cite · 可引用的数字

Value 数值What it measures含义Page 页
2203.01054v2arXiv identifier of the version we read我们所读版本的 arXiv 编号p. 1
6 Nov 2022Date stamped on the arXiv v2 versionarXiv v2 版本标注的日期p. 1
2016The earliest ABSA survey covered studies before 2016 only最早的 ABSA 综述只覆盖 2016 年前的研究p. 2
SemEval-2014First of the three most-used benchmark datasets (laptops, restaurants)三个最常用基准数据集中的第一个(笔记本电脑、餐厅)p. 5
SemEval-2016The only multilingual SemEval benchmark in Table 2表 2 中唯一的多语言 SemEval 基准p. 5
18Predefined aspect categories in the Chinese ASAP dataset中文 ASAP 数据集的预定义方面类别数p. 5
fourNumber of single ABSA tasks, one per sentiment element单一 ABSA 任务的数量(four),每个要素一个p. 6
80%Approximate F1 of supervised aspect term extraction on benchmarks有监督方面词抽取在基准上的 F1 约为 80%p. 6
70%Approximate F1 of current E2E-ABSA methods on benchmarks目前 E2E-ABSA 方法在基准上的 F1 约为 70%p. 9
40%Approximate F1 of the best quad-prediction (ASQP) models最佳四元组预测(ASQP)模型的 F1 约为 40%p. 12
25%Performance drop (more than) of PLM-based models on adversarial ASC testsPLM 模型在对抗性 ASC 测试中的性能下降(超过 25%)p. 13
hundreds of sentencesTypical size of existing ABSA benchmark datasets现有 ABSA 基准数据集的典型规模(几百句)p. 14
fiveRandom seeds usually averaged when reporting results (often five or ten)报告结果时通常取平均的随机种子数(often five or ten,常为五或十个)p. 14

What it means for our report · 对报告的意义

Limits and where it does not fit · 局限与不适用之处

Questions for the group · 小组讨论问题

← Selling secondhand products through an online platform with blockchainPop Mart China Sales Tracker: Deceleration in offline growth and productivity; risks in 2026 →

Written by the group from the full text. Numbers and page references were checked against the source. Licensed cases and reports are summarised, not reproduced.
由小组根据全文整理,数字与页码已对照原文核对。授权案例与报告只作摘要,不转载原文。