---
title: "Lingua-Graph — paper by Sun et al. (2026) — summary and ideas"
description: "The authors propose \"Analytic NLP\": first build a shared, task-agnostic intermediate structure, then let task-specific… 15.6 AUC. 43 references."
authors: ["Mingming Sun", "Runze Jiang", "Zhu Zhangchenxi", "Minlong Peng", "Yunfeng Cai"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1129/"
doi: "10.18653/v1/2026.acl-long.1129"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/sun-2026-lingua-graph-unified-representation-cross/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sun-2026-lingua-graph-unified-representation-cross/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/39/) / Lingua-Graph: A Unified Representation of Cross-Task Common Substructures for Analytic Language Processing

# Lingua-Graph: A Unified Representation of Cross-Task Common Substructures for Analytic Language Processing

**Authors:** Mingming Sun, Runze Jiang, Zhu Zhangchenxi, Minlong Peng and Yunfeng Cai · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.1129/) · [PDF](https://aclanthology.org/2026.acl-long.1129.pdf) · [DOI 10.18653/v1/2026.acl-long.1129](https://doi.org/10.18653/v1/2026.acl-long.1129) · [OpenAlex](https://openalex.org/W7166823140)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Structural-analytic tasks such as entity detection, coreference, OpenIE and semantic role labeling are usually solved separately. Each task uses its own label scheme, so the learned structures transfer poorly, and LLM prompting still struggles with conflicting annotation conventions. The authors propose "Analytic NLP": first build a shared, task-agnostic intermediate structure, then let task-specific decision modules select substructures from it.

Their representation layer, Lingua-Graph, is a labeled, single-rooted DAG built on a hierarchical predicate–function–argument design. Its nodes partition the sentence's tokens, and candidate units are either a single node or its full set of descendants. The authors annotated a Lingua-Graph dataset and trained a baseline parser. They compare representations with two oracle metrics: expressivity (how many gold units appear among the candidates) and selectivity (how many candidates are gold).

For entity spans, Lingua-Graph covers clearly more than constituency, dependency and AMR structures on average, with similar selectivity. Plugging it into a rule-based OpenIE pipeline improves results on three benchmarks. This suggests that one inspectable structural layer can serve many tasks.

## Key points
- Lingua-Graph offers two candidate constructors, SELF (one node) and DESCENDANT (a node's descendant closure). Expressivity is compared against constituency parsing, dependency parsing and AMR. UCCA was excluded because its outdated dependencies prevented running its pipeline.
- Out-of-domain entity evaluation used CrossNER, MIT-Restaurant and MIT-Movie, none of which appear in the Lingua-Graph training data. Roughly 10% of gold entity spans remain unhostable, mostly involving complex phenomena not covered by the current annotation.
- OIE@Lingua replaces OIA-Graph with Lingua-Graph in the OIE@OIA pipeline and outperforms it:
  - OIE2016: AUC/F1 of 67.2/78.3 vs. 54.3/71.6.
  - Re-OIE2016: 82.7/87.4 vs. 76.9/85.3.
- On BenchIE, OIE@Lingua reaches 15.6 AUC and 35.5 F1, the best among the reported systems (ClauseIE: 13.9/33.9).
- The data, code and trained parser are publicly available at github.com/rudaoshi/Lingua.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Peking University](https://md.research.elamur.ai/free/en/universities/peking-university/) — University, Beijing, China · 315 works · 43,267 citations
- [Tencent](https://md.research.elamur.ai/free/en/companies/tencent/) — Company, Shenzhen, China · 163 works · 21,032 citations

Also on the byline: [Beijing Institute of Mathematical Sciences and Applications](https://ror.org/05t6hvr95).

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

## Cite

Cite as: Mingming Sun, Runze Jiang, Zhu Zhangchenxi, Minlong Peng and Yunfeng Cai. 2026. Lingua-Graph: A Unified Representation of Cross-Task Common Substructures for Analytic Language Processing. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{sun2026lingua,
  title = {{Lingua-Graph: A Unified Representation of Cross-Task Common Substructures for Analytic Language Processing}},
  author = {Mingming Sun, Runze Jiang, Zhu Zhangchenxi, Minlong Peng and Yunfeng Cai},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1129},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1129}
}
```

- [← previous Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration](https://md.research.elamur.ai/free/en/papers/shim-2026-linear-script-representations-speech-foundation/)
- [next → LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation](https://md.research.elamur.ai/free/en/papers/ye-2026-linguagame-linguistically-grounded-game-theoretic/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/39/)

## References

43 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Omri Abend and Ari Rappoport. 2013. [Universal Conceptual Cognitive Annotation (UCCA)](https://md.research.elamur.ai/free/en/papers/abend-2013-universal-conceptual-cognitive-annotation-ucca/). In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 228–238, Sofia, Bulgaria. Association for Computational Linguistics.
2. Rami Al-Rfou, Vivek Kulkarni, Bryan Perozzi, and Steven Skiena. 2015. POLYGLOT-NER: Massive multilingual named entity recognition. In Proceedings of the 2015 SIAM International Conference on Data Mining (SDM), pages 586–594. [find](https://scholar.google.com/scholar?q=Rami+Al%2DRfou%2C+Vivek+Kulkarni%2C+Bryan+Perozzi%2C+and+Steven+Skiena%2E+2015%2E+POLYGLOT%2DNER%3A+Massive+multilingual+named+entity+recognition%2E+In+Proceedings+of+the+2015+SIAM+International+Conference+on+Data+Mini)
3. Petr Anokhin, Nikita Semenov, Artyom Sorokin, Dmitry Evseev, Mikhail Burtsev, and Evgeny Burnaev. 2024. Arigraph: Learning knowledge graph world models with episodic memory for llm agents. Preprint, arXiv:2407.04363. — [arXiv:2407.04363](https://arxiv.org/abs/2407.04363) [find](https://scholar.google.com/scholar?q=Petr+Anokhin%2C+Nikita+Semenov%2C+Artyom+Sorokin%2C+Dmitry+Evseev%2C+Mikhail+Burtsev%2C+and+Evgeny+Burnaev%2E+2024%2E+Arigraph%3A+Learning+knowledge+graph+world+models+with+episodic+memory+for+llm+agents%2E+Preprint%2C+a)
4. Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer, and Nathan Schneider. 2013. [Abstract Meaning Representation for sembanking](https://md.research.elamur.ai/free/en/papers/banarescu-2013-abstract-meaning-representation-sembanking/). In Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discou…
5. Michele Banko, Michael J. Cafarella, Stephen Soderland, Matt Broadhead, and Oren Etzioni. 2007. [Open information extraction from the web](https://md.research.elamur.ai/free/en/papers/banko-2007-open-information-extraction-web/). In Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI), pages 2670–2676.
6. Zhoujun Cheng, Tianbao Xie, Peng Shi, Chengzu Li, Rahul Nadkarni, Yushi Hu, Caiming Xiong, Dragomir Radev, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith, and Tao Yu. 2023. [Binding language models in symbolic languages](https://md.research.elamur.ai/free/en/papers/cheng-2022-binding-language-models-symbolic-languages/). In The Eleventh International Conference on Learning Representations.
7. Noam Chomsky. 1957. Syntactic Structures. Mouton, The Hague/Paris. [find](https://scholar.google.com/scholar?q=Noam+Chomsky%2E+1957%2E+Syntactic+Structures%2E+Mouton%2C+The+Hague%2FParis%2E)
8. Janara Christensen, Mausam, Stephen Soderland, and Oren Etzioni. 2011. An analysis of open information extraction based on semantic role labeling. In Proceedings of the 6th International Conference on Knowledge Capture (K-CAP), pages 113–120, Banff, Alberta, Canada. [find](https://scholar.google.com/scholar?q=Janara+Christensen%2C+Mausam%2C+Stephen+Soderland%2C+and+Oren+Etzioni%2E+2011%2E+An+analysis+of+open+information+extraction+based+on+semantic+role+labeling%2E+In+Proceedings+of+the+6th+International+Conference+on)
9. Luciano Del Corro and Rainer Gemulla. 2013. ClausIE: clause-based open information extraction. In Proceedings of the 22nd International World Wide Web Conference (WWW), pages 355–366, Rio de Janeiro, Brazil. [find](https://scholar.google.com/scholar?q=Luciano+Del+Corro+and+Rainer+Gemulla%2E+2013%2E+ClausIE%3A+clause%2Dbased+open+information+extraction%2E+In+Proceedings+of+the+22nd+International+World+Wide+Web+Conference+%28WWW%29%2C+pages+355%E2%80%93366%2C+Rio+de+Janeiro%2C+)
10. CSAIL, MIT. 2006a. Mit movie corpus. [https://groups.csail.mit.edu/sls/downloads/movie/](https://groups.csail.mit.edu/sls/downloads/movie/). Semantically tagged training and test corpus in BIO format. [↗](https://groups.csail.mit.edu/sls/downloads/movie/)
11. CSAIL, MIT. 2006b. Mit restaurant corpus. [https://groups.csail.mit.edu/sls/](https://groups.csail.mit.edu/sls/) downloads/restaurant/. Semantically tagged training and test corpus in BIO format. [↗](https://groups.csail.mit.edu/sls/)
12. Marie-Catherine de Marneffe, Christopher D. Manning, Joakim Nivre, and Daniel Zeman. 2021. [Universal Dependencies](https://md.research.elamur.ai/free/en/papers/marneffe-2021-universal-dependencies-2/). Computational Linguistics, 47(2):255–308.
13. DeepSeek. 2026. DeepSeek Chat. [https://chat.deepseek.com/](https://chat.deepseek.com/). DeepSeek. [↗](https://chat.deepseek.com/)
14. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [BERT: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
15. Timothy Dozat and Christopher D. Manning. 2017. [Deep biaffine attention for neural dependency parsing](https://md.research.elamur.ai/free/en/papers/dozat-2016-deep-biaffine-attention-neural-dependency/). In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. Open-Review.net.
16. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2025. From local to global: A graph rag approach to query-focused summarization. Preprint, arXiv:2404.16130. [find](https://scholar.google.com/scholar?q=Darren+Edge%2C+Ha+Trinh%2C+Newman+Cheng%2C+Joshua+Bradley%2C+Alex+Chao%2C+Apurva+Mody%2C+Steven+Truitt%2C+Dasha+Metropolitansky%2C+Robert+Osazuwa+Ness%2C+and+Jonathan+Larson%2E+2025%2E+From+local+to+global%3A+A+graph+rag+app)
17. Hans Kamp and Uwe Reyle. 1993. From Discourse to Logic: Introduction to Modeltheoretic Semantics of Natural Language, Formal Logic and Discourse Representation Theory, volume 42 of Studies in Linguistics and Philosophy. Springer Dordrecht, Dordrecht. [find](https://scholar.google.com/scholar?q=Hans+Kamp+and+Uwe+Reyle%2E+1993%2E+From+Discourse+to+Logic%3A+Introduction+to+Modeltheoretic+Semantics+of+Natural+Language%2C+Formal+Logic+and+Discourse+Representation+Theory%2C+volume+42+of+Studies+in+Linguist)
18. Tushar Khot, Ashish Sabharwal, and Peter Clark. 2017. [Answering complex questions using open information extraction](https://md.research.elamur.ai/free/en/papers/khot-2017-answering-complex-questions-open-information/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 311–316, Vancouver, Canada. Association for Computational Li…
19. Hongjin Kim, Jai-Eun Kim, and Harksoo Kim. 2024. Exploring Nested Named Entity Recognition with Large Language Models: Methods, Challenges, and Insights. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8653–8670, Miami, Florida, USA. Association for C… [find](https://scholar.google.com/scholar?q=Hongjin+Kim%2C+Jai%2DEun+Kim%2C+and+Harksoo+Kim%2E+2024%2E+Exploring+Nested+Named+Entity+Recognition+with+Large+Language+Models%3A+Methods%2C+Challenges%2C+and+Insights%2E+In+Proceedings+of+the+2024+Conference+on+Empir)
20. J.-D. Kim, T. Ohta, Y. Tateisi, and J. Tsujii. 2003. GE-NIA corpus—a semantically annotated corpus for bio-textmining. Bioinformatics (Oxford, England), 19(suppl_1):i180–i182. [find](https://scholar.google.com/scholar?q=J%2E%2DD%2E+Kim%2C+T%2E+Ohta%2C+Y%2E+Tateisi%2C+and+J%2E+Tsujii%2E+2003%2E+GE%2DNIA+corpus%E2%80%94a+semantically+annotated+corpus+for+bio%2Dtextmining%2E+Bioinformatics+%28Oxford%2C+England%29%2C+19%28suppl%5F1%29%3Ai180%E2%80%93i182%2E)
21. Zihan Liu, Yan Xu, Tiezheng Yu, Wenliang Dai, Ziwei Ji, Samuel Cahyawijaya, Andrea Madotto, and Pascale Fung. 2021. CrossNER: Evaluating cross-domain named entity recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15):13452–13460. [find](https://scholar.google.com/scholar?q=Zihan+Liu%2C+Yan+Xu%2C+Tiezheng+Yu%2C+Wenliang+Dai%2C+Ziwei+Ji%2C+Samuel+Cahyawijaya%2C+Andrea+Madotto%2C+and+Pascale+Fung%2E+2021%2E+CrossNER%3A+Evaluating+cross%2Ddomain+named+entity+recognition%2E+Proceedings+of+the+AAAI+)
22. OpenAI. 2026. ChatGPT. [https://chat.openai.com/](https://chat.openai.com/). OpenAI. [↗](https://chat.openai.com/)
23. Erik F. Tjong Sang and Fien De Meulder. 2003. [Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/sang-2003-introduction-conll-2003-shared-task/). In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003, pages 142–147.
24. Christopher Walker, Stephanie Strassel, Julie Medero, and Kazuaki Maeda. 2006. [find](https://scholar.google.com/scholar?q=Christopher+Walker%2C+Stephanie+Strassel%2C+Julie+Medero%2C+and+Kazuaki+Maeda%2E+2006%2E)
25. Ace 2005 multilingual training corpus. Technical Report 57:45, Linguistic Data Consortium, Philadelphia, PA. [find](https://scholar.google.com/scholar?q=Ace+2005+multilingual+training+corpus%2E+Technical+Report+57%3A45%2C+Linguistic+Data+Consortium%2C+Philadelphia%2C+PA%2E)
26. Xiao Wang, Weikang Zhou, Can Zu, Han Xia, Tianze Chen, Yuansen Zhang, Rui Zheng, Junjie Ye, Qi Zhang, Tao Gui, Jihua Kang, Jingsheng Yang, Siyuan Li, and Chunsai Du. 2023. [Instructuie: Multi-task instruction tuning for unified information extraction](https://md.research.elamur.ai/free/en/papers/wang-2023-instructuie-multi-task-instruction-tuning/). Preprint, arXiv:2304.08085.
27. Xin Wang, Minlong Peng, Mingming Sun, and Ping Li. 2022. OIE@OIA: an adaptable and efficient open information extraction framework. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6213–6226, Dublin, Ireland. Association for Co… [find](https://scholar.google.com/scholar?q=Xin+Wang%2C+Minlong+Peng%2C+Mingming+Sun%2C+and+Ping+Li%2E+2022%2E+OIE%40OIA%3A+an+adaptable+and+efficient+open+information+extraction+framework%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Com)
28. Xiaoman Pan, Boliang Zhang, Jonathan May, Joel Nothman, Kevin Knight, and Heng Ji. 2017. [Cross-lingual name tagging and linking for 282 languages](https://md.research.elamur.ai/free/en/papers/pan-2017-cross-lingual-name-tagging-linking/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1946–1958, Vancouver, Canada. A…
29. Ralph Weischedel, Mitch Marcus, Martha Palmer, Eduard Hovy, Robert Belvin, Sameer Pradhan, and Lance Ramshaw. 2010. Ontonotes: A large training corpus for enhanced processing. In Handbook of Natural Language Processing and Machine Translation. Springer, New York, NY. [find](https://scholar.google.com/scholar?q=Ralph+Weischedel%2C+Mitch+Marcus%2C+Martha+Palmer%2C+Eduard+Hovy%2C+Robert+Belvin%2C+Sameer+Pradhan%2C+and+Lance+Ramshaw%2E+2010%2E+Ontonotes%3A+A+large+training+corpus+for+enhanced+processing%2E+In+Handbook+of+Natural+L)
30. Matthew Richardson and Pedro M. Domingos. 2006. Markov logic networks. Machine Learning, 62(1– 2):107–136. [find](https://scholar.google.com/scholar?q=Matthew+Richardson+and+Pedro+M%2E+Domingos%2E+2006%2E+Markov+logic+networks%2E+Machine+Learning%2C+62%281%E2%80%93+2%29%3A107%E2%80%93136%2E)
31. Terry Winograd. 1970. Procedures as a representation for data in a computer program for understanding natural language. AI Technical Report 235, MIT Artificial Intelligence Laboratory. [find](https://scholar.google.com/scholar?q=Terry+Winograd%2E+1970%2E+Procedures+as+a+representation+for+data+in+a+computer+program+for+understanding+natural+language%2E+AI+Technical+Report+235%2C+MIT+Artificial+Intelligence+Laboratory%2E)
32. Youngbin Ro, Yukyung Lee, and Pilsung Kang. 2020. Multi 2 OIE: Multilingual open information extraction based on multi-head attention with BERT. In Findings of the Association for Computational Linguistics (EMNLP Findings), pages 1107–1117, Online Event. [find](https://scholar.google.com/scholar?q=Youngbin+Ro%2C+Yukyung+Lee%2C+and+Pilsung+Kang%2E+2020%2E+Multi+2+OIE%3A+Multilingual+open+information+extraction+based+on+multi%2Dhead+attention+with+BERT%2E+In+Findings+of+the+Association+for+Computational+Lingui)
33. Zacchary Sadeddine, Juri Opitz, and Fabian Suchanek. 2024. A survey of meaning representations – from theory to practical utility. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)… [find](https://scholar.google.com/scholar?q=Zacchary+Sadeddine%2C+Juri+Opitz%2C+and+Fabian+Suchanek%2E+2024%2E+A+survey+of+meaning+representations+%E2%80%93+from+theory+to+practical+utility%2E+In+Proceedings+of+the+2024+Conference+of+the+North+American+Chapter+o)
34. Mingming Sun, Wenyue Hua, Zoey Liu, Xin Wang, Kangjie Zheng, and Ping Li. 2020. A predicate-function-argument annotation of natural language for open-domain information expression. In Conference on Empirical Methods in Natural Language Processing. [find](https://scholar.google.com/scholar?q=Mingming+Sun%2C+Wenyue+Hua%2C+Zoey+Liu%2C+Xin+Wang%2C+Kangjie+Zheng%2C+and+Ping+Li%2E+2020%2E+A+predicate%2Dfunction%2Dargument+annotation+of+natural+language+for+open%2Ddomain+information+expression%2E+In+Conference+on+Em)
35. Simone Tedeschi and Roberto Navigli. 2022. MultiN-ERD: A multilingual, multi-genre and fine-grained dataset for named entity recognition (and disambiguation). In Findings of the Association for Computational Linguistics: NAACL 2022, pages 801–812, Seattle, United States. Association for Computationa… [find](https://scholar.google.com/scholar?q=Simone+Tedeschi+and+Roberto+Navigli%2E+2022%2E+MultiN%2DERD%3A+A+multilingual%2C+multi%2Dgenre+and+fine%2Dgrained+dataset+for+named+entity+recognition+%28and+disambiguation%29%2E+In+Findings+of+the+Association+for+Comput)
36. Tingyu Xie, Qi Li, Jian Zhang, Yan Zhang, Zuozhu Liu, and Hongwei Wang. 2023. Empirical Study of Zero-Shot NER with ChatGPT. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7935–7956, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Tingyu+Xie%2C+Qi+Li%2C+Jian+Zhang%2C+Yan+Zhang%2C+Zuozhu+Liu%2C+and+Hongwei+Wang%2E+2023%2E+Empirical+Study+of+Zero%2DShot+NER+with+ChatGPT%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+in+Natural+Langu)
37. Alexander Yates, Michele Banko, Matthew Broadhead, Michael J Cafarella, Oren Etzioni, and Stephen Soderland. 2007. [Textrunner: open information extraction on the web](https://md.research.elamur.ai/free/en/papers/yates-2007-textrunner-open-information-extraction-web/). In Proceedings of Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computation…
38. Dongran Yu, Bo Yang, Dayou Liu, Hui Wang, and Shirui Pan. 2023. A survey on neural-symbolic learning systems. Neural Networks, 166:105–126. [find](https://scholar.google.com/scholar?q=Dongran+Yu%2C+Bo+Yang%2C+Dayou+Liu%2C+Hui+Wang%2C+and+Shirui+Pan%2E+2023%2E+A+survey+on+neural%2Dsymbolic+learning+systems%2E+Neural+Networks%2C+166%3A105%E2%80%93126%2E)
39. Ruihong Zeng, Jinyuan Fang, Siwei Liu, and Zaiqiao Meng. 2024. On the structural memory of llm agents. Preprint, arXiv:2412.15266. — [arXiv:2412.15266](https://arxiv.org/abs/2412.15266) [find](https://scholar.google.com/scholar?q=Ruihong+Zeng%2C+Jinyuan+Fang%2C+Siwei+Liu%2C+and+Zaiqiao+Meng%2E+2024%2E+On+the+structural+memory+of+llm+agents%2E+Preprint%2C+arXiv%3A2412%2E15266%2E+%E2%80%94+%5BarXiv%3A2412%2E15266%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2412%2E15266%29)
40. Junlang Zhan and Hai Zhao. 2020. Span model for open information extraction on accurate corpus. In Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), pages 9523–9530, New York, NY. [find](https://scholar.google.com/scholar?q=Junlang+Zhan+and+Hai+Zhao%2E+2020%2E+Span+model+for+open+information+extraction+on+accurate+corpus%2E+In+Proceedings+of+the+Thirty%2DFourth+AAAI+Conference+on+Artificial+Intelligence+%28AAAI%29%2C+pages+9523%E2%80%939530%2C+)
41. Zijie Zhong, Hanwen Liu, Xiaoya Cui, Xiaofan Zhang, and Zengchang Qin. 2025. [Mix-of-granularity: Optimize the chunking granularity for retrieval-augmented generation](https://md.research.elamur.ai/free/en/papers/zhong-2025-mix-granularity-optimize-chunking-granularity/). In Proceedings of the 31st International Conference on Computational Linguistics, pages 5756–5774, Abu Dhabi, UAE. Association for Co…
42. Wenxuan Zhou, Sheng Zhang, Yu Gu, Muhao Chen, and Hoifung Poon. 2024. [UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/zhou-2023-universalner-targeted-distillation-large-language/). Preprint, arXiv:2308.03279.
43. Jingming Zhuo, Songyang Zhang, Xinyu Fang, Haodong Duan, Dahua Lin, and Kai Chen. 2024. ProSA: Assessing and understanding the prompt sensitivity of LLMs. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 1950–1976, Miami, Florida, USA. Association for Computational Lin… [find](https://scholar.google.com/scholar?q=Jingming+Zhuo%2C+Songyang+Zhang%2C+Xinyu+Fang%2C+Haodong+Duan%2C+Dahua+Lin%2C+and+Kai+Chen%2E+2024%2E+ProSA%3A+Assessing+and+understanding+the+prompt+sensitivity+of+LLMs%2E+In+Findings+of+the+Association+for+Computatio)

*Updated 2 November 2026*