--- title: "汉语被动结构解析及其在CAMR中的应用研究 — 胡康 2025" description: "The paper addresses the automatic analysis of the internal makeup of Chinese passive sentences." authors: ["胡康", "曲维光", "魏庭新", "周俊生", "李斌", "顾彦慧"] year: 2025 venue: "中文信息学报 (Journal of Chinese Information Processing)" source: "http://jcip.cipsc.org.cn/article/id/zwxxxb_3976" licence: "Free access (jcip.cipsc.org.cn), no open licence stated — readonly; © 中文信息学报" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/papers/hu-2025-parsing-passive-structure/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/hu-2025-parsing-passive-structure/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2025](https://md.research.elamur.ai/free/papers/2025/page/3/) / 汉语被动结构解析及其在CAMR中的应用研究 # 汉语被动结构解析及其在CAMR中的应用研究 **Authors:** 胡康, 曲维光, 魏庭新, 周俊生, 李斌, 顾彦慧 · **Year:** 2025 · **Venue:** 中文信息学报 (Journal of Chinese Information Processing) · **Licence:** Free access (jcip.cipsc.org.cn), no open licence stated — readonly; © 中文信息学报 **Links:** [Publisher's page](http://jcip.cipsc.org.cn/article/id/zwxxxb_3976) · [PDF](http://jcip.cipsc.org.cn/cn/article/pdf/preview/zwxxxb_3976.pdf) ## Summary The paper addresses the automatic analysis of the internal makeup of Chinese passive sentences. Earlier work could only flag whether a sentence was passive. The authors treat the problem as a specialised form of semantic role labeling. Each passive structure is a tuple of verb (V), patient-like argument (A1), optional agent (A0) and optional marker (M), which can be a preposition such as 被 or a "suffering" verb such as 遭到. They sampled sentences from an existing passive-sentence corpus and labelled them at the word level. The scheme uses BIO tags plus an index that links each component to its verb. Their model, PS-CRF, has three parts: - BERT-wwm-ext embeddings - biaffine attention scoring over a tree in which each verb heads its components - a TreeCRF output layer with Viterbi decoding PS-CRF reaches an F1 of 97.31%. The parser's output was also used to post-process CAMR graphs produced by SPRING on primary-school Chinese texts, which raised both Smatch and Align-Smatch. This shows that targeted structural parsing can improve broader semantic graph parsing. ## Key points - **Dataset:** 3,839 passive sentences were annotated with 4,814 passive structures, about 1.25 per sentence. - 2,711 are marked: 2,465 with a prepositional marker, 190 with a suffering-verb marker, and 56 attributive cases. - 2,103 are unmarked, including a small number of attributive cases. - The data was split 6:2:2 into train, dev and test. - **Results:** PS-CRF scores P 98.46 / R 96.18 / F1 97.31. Baselines: - plain CRF with GloVe: F1 77.59 - Biaffine+TreeCRF: F1 80.47 - BERT+Biaffine+TreeCRF: F1 96.44 - **Why the tree helps:** Modelling each passive structure as its own dependency tree lets the model handle sentences with several, possibly nested, passive structures. A flat CRF cannot do this. - **Remaining errors:** Most come from attributive (定中) passive structures, which are under 2% of the data. Others come from words with several senses that get mistaken for passive verbs. - **CAMR post-processing with SPRING:** - Without alignment: Align-Smatch rose from 45.2 to 47.6 and Smatch from 69.8 to 70.74. - With manually added concept alignment: Align-Smatch rose from 62.3 to 65.8. - The Smatch gains are smaller because markers are encoded inside relation labels rather than as separate nodes. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/) · [Natural language processing](https://md.research.elamur.ai/free/shelves/nlp/) Topics: [Dependency parsing](https://md.research.elamur.ai/free/topics/dependency-parsing/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @article{2025, title = {{汉语被动结构解析及其在CAMR中的应用研究}}, author = {胡康 and 曲维光 and 魏庭新 and 周俊生 and 李斌 and 顾彦慧}, journal = {中文信息学报 (Journal of Chinese Information Processing)}, year = {2025}, url = {http://jcip.cipsc.org.cn/article/id/zwxxxb_3976} } ``` - [← previous 检索增强生成在软件工程中的应用综述](https://md.research.elamur.ai/free/papers/zhang-2025-application-retrieval-augmented/) - [next → 玲珑：一个小规模的高质量中文预训练语言模型](https://md.research.elamur.ai/free/papers/li-2025-linglong-high-quality/) - [↑ back to papers of 2025](https://md.research.elamur.ai/free/papers/2025/page/3/) ## References 6 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. [ 1] 宋文 辉,罗 政 静,于 景 超 . 现 代 汉 语 被 动 句 施 事 隐 现 的计量分析[ J]. 中国语文, 2007( 2):113 - 124. [find](https://scholar.google.com/scholar?q=%5B+1%5D+%E5%AE%8B%E6%96%87+%E8%BE%89%2C%E7%BD%97+%E6%94%BF+%E9%9D%99%2C%E4%BA%8E+%E6%99%AF+%E8%B6%85+%2E+%E7%8E%B0+%E4%BB%A3+%E6%B1%89+%E8%AF%AD+%E8%A2%AB+%E5%8A%A8+%E5%8F%A5+%E6%96%BD+%E4%BA%8B+%E9%9A%90+%E7%8E%B0+%E7%9A%84%E8%AE%A1%E9%87%8F%E5%88%86%E6%9E%90%5B+J%5D%2E+%E4%B8%AD%E5%9B%BD%E8%AF%AD%E6%96%87%2C+2007%28+2%29%3A113+%2D+124%2E) 2. [ 2] 赵元任 . 汉语口语语法 . 上海:商务印书馆[M],1979. [ 3] 兰宾汉 . 汉语语法知识与应用[M]. 北京:石 油 工 业 出 版社,2002. [find](https://scholar.google.com/scholar?q=%5B+2%5D+%E8%B5%B5%E5%85%83%E4%BB%BB+%2E+%E6%B1%89%E8%AF%AD%E5%8F%A3%E8%AF%AD%E8%AF%AD%E6%B3%95+%2E+%E4%B8%8A%E6%B5%B7%3A%E5%95%86%E5%8A%A1%E5%8D%B0%E4%B9%A6%E9%A6%86%5BM%5D%2C1979%2E+%5B+3%5D+%E5%85%B0%E5%AE%BE%E6%B1%89+%2E+%E6%B1%89%E8%AF%AD%E8%AF%AD%E6%B3%95%E7%9F%A5%E8%AF%86%E4%B8%8E%E5%BA%94%E7%94%A8%5BM%5D%2E+%E5%8C%97%E4%BA%AC%3A%E7%9F%B3+%E6%B2%B9+%E5%B7%A5+%E4%B8%9A+%E5%87%BA+%E7%89%88%E7%A4%BE%2C2002%2E) 3. [ ] 4 王 振 来 . 被 动 表 述 对 自 主 动 词 和 非 自 主 动 词 的 选 择 [ J]. 汉语学习,2004( 6):17 - 22. [find](https://scholar.google.com/scholar?q=%5B+%5D+4+%E7%8E%8B+%E6%8C%AF+%E6%9D%A5+%2E+%E8%A2%AB+%E5%8A%A8+%E8%A1%A8+%E8%BF%B0+%E5%AF%B9+%E8%87%AA+%E4%B8%BB+%E5%8A%A8+%E8%AF%8D+%E5%92%8C+%E9%9D%9E+%E8%87%AA+%E4%B8%BB+%E5%8A%A8+%E8%AF%8D+%E7%9A%84+%E9%80%89+%E6%8B%A9+%5B+J%5D%2E+%E6%B1%89%E8%AF%AD%E5%AD%A6%E4%B9%A0%2C2004%28+6%29%3A17+%2D+22%2E) 4. [ 5] 蚁坤 . 汉语被动句的句法语义特征和使用 条 件[ D]. 北 京:北京语言文化大学硕士学位论文, 2000. [find](https://scholar.google.com/scholar?q=%5B+5%5D+%E8%9A%81%E5%9D%A4+%2E+%E6%B1%89%E8%AF%AD%E8%A2%AB%E5%8A%A8%E5%8F%A5%E7%9A%84%E5%8F%A5%E6%B3%95%E8%AF%AD%E4%B9%89%E7%89%B9%E5%BE%81%E5%92%8C%E4%BD%BF%E7%94%A8+%E6%9D%A1+%E4%BB%B6%5B+D%5D%2E+%E5%8C%97+%E4%BA%AC%3A%E5%8C%97%E4%BA%AC%E8%AF%AD%E8%A8%80%E6%96%87%E5%8C%96%E5%A4%A7%E5%AD%A6%E7%A1%95%E5%A3%AB%E5%AD%A6%E4%BD%8D%E8%AE%BA%E6%96%87%2C+2000%2E) 5. [ 6] 王惠 . 从及物性系统看 现 代 汉 语 的 句 式 [ J]. 语 言 学 论 ) : 丛,1997( 19 193 - 252. [find](https://scholar.google.com/scholar?q=%5B+6%5D+%E7%8E%8B%E6%83%A0+%2E+%E4%BB%8E%E5%8F%8A%E7%89%A9%E6%80%A7%E7%B3%BB%E7%BB%9F%E7%9C%8B+%E7%8E%B0+%E4%BB%A3+%E6%B1%89+%E8%AF%AD+%E7%9A%84+%E5%8F%A5+%E5%BC%8F+%5B+J%5D%2E+%E8%AF%AD+%E8%A8%80+%E5%AD%A6+%E8%AE%BA+%29+%3A+%E4%B8%9B%2C1997%28+19+193+%2D+252%2E) 6. [ 7] 王一平 . 从遭受类动 词 所 带 宾 语 的 情 况 看 遭 受 类 动 词 的特点[ J]. 语文研究,1994 ( 4):28 - 34. [find](https://scholar.google.com/scholar?q=%5B+7%5D+%E7%8E%8B%E4%B8%80%E5%B9%B3+%2E+%E4%BB%8E%E9%81%AD%E5%8F%97%E7%B1%BB%E5%8A%A8+%E8%AF%8D+%E6%89%80+%E5%B8%A6+%E5%AE%BE+%E8%AF%AD+%E7%9A%84+%E6%83%85+%E5%86%B5+%E7%9C%8B+%E9%81%AD+%E5%8F%97+%E7%B1%BB+%E5%8A%A8+%E8%AF%8D+%E7%9A%84%E7%89%B9%E7%82%B9%5B+J%5D%2E+%E8%AF%AD%E6%96%87%E7%A0%94%E7%A9%B6%2C1994+%28+4%29%3A28+%2D+34%2E)