Elamur Research
☰
home / papers / 2015 / Leveraging Linguistic Structure For Open Domain Information Extraction

Leveraging Linguistic Structure For Open Domain Information Extraction

Written for the Research library (claude-opus-5-5) from the paper text, in our own words: the license "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" does not allow redistributing the text itself. Original — aclanthology.org/P15-1034.pdf

Summary

The paper addresses open information extraction (open IE), that is, the automatic extraction of "subject; relation; object" triples from text. Systems such as Ollie rely on a large set of learned patterns. As a result, they perform poorly on out-of-domain text and on long-range syntactic dependencies, and their arguments are often overly long. The authors propose a different approach. First, a classifier traverses the sentence's dependency tree and splits it into short, self-contained clauses. Training data for the classifier is obtained via distant supervision from known KBP relations. Next, natural logic shortens each clause, but only when the shorter form is logically entailed by the longer one. Finally, a small set of hand-written patterns turns the result into triples. On the end task, TAC-KBP 2013 Slot Filling, the system outperforms both the official open IE-based submission and Ollie plugged into the same pipeline. The work shows that taking linguistic structure and logical inference into account yields more precise and more useful downstream triples than increasing the number of patterns.

Key points

  • Stage 1, clause splitting. For each Stanford Dependencies edge, the classifier chooses one of three actions: Yield, Recurse, or Stop. A new clause may inherit the subject or object of the main clause, i.e., of the controller. During training, breadth-first search collects up to 10,000 action sequences.
  • Stage 2, natural logic. Argument shortening takes monotonicity into account. For example, "of Austria" can be dropped, whereas "fake" in "fake praise" must be kept. From sentences with quantifiers such as "No …", the system draws no false conclusions.
  • Segmentation into triples. Once the clauses are simplified, 14 hand-written patterns suffice.
  • Results on TAC-KBP 2013 Slot Filling. The system beats the official UW submission and Ollie, including a variant in which this system's nominal relations are added to Ollie. With an alternate-names detector and rules for websites added, F1 reaches 28.2.
  • Scale. The system extracted 42,662,862 triples linking entity pairs, versus 12,274,319 for Ollie. At the start of the precision/recall curve, precision drops noticeably, which the authors attribute to systematic errors of the clause splitter.

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: AI & machine learning

Cited by

214 papers of our library cite it (of the 140673 whose bibliographies we read); 9 of them have a page here, 205 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/v1/p15-1034

@inproceedings{angeli2015leveraging,
  title = {{Leveraging Linguistic Structure For Open Domain Information Extraction}},
  author = {Angeli, Gabor and Premkumar, Melvin Jose Johnson and Manning, Christopher D.},
  booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  year = {2015},
  doi = {10.3115/v1/p15-1034},
  url = {https://doi.org/10.3115/v1/p15-1034}
}

References

46 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Gabor Angeli and Christopher D. Manning. 2013. Philosophers are mortal: Inferring the truth of unseen facts. In CoNLL. find
  2. Gabor Angeli, Julie Tibshirani, Jean Y. Wu, and Christopher D. Manning. 2014. Combining distant and partial supervision for relation extraction. In EMNLP. find
  3. DAILLE Béatrice. 1994. Approche mixte pour l’extraction automatique de terminologie: statistique lexicale et filtres linguistiques. Ph.D. thesis, Thèse de Doctorat. Université de Paris VII. find
  4. Jonathan Berant, Ido Dagan, and Jacob Goldberger. 2011. Global learning of typed entailment rules. In Proceedings of ACL, Portland, OR. find
  5. Samuel R. Bowman, Christopher Potts, and Christopher D. Manning. 2014. Recursive neural networks can learn logical semantics. CoRR, (arXiv:1406.1827). find
  6. Andrew Carlson, Justin Betteridge, Bryan Kisiel, Burr Settles, Estevam R Hruschka Jr, and Tom M Mitchell. 2010. Toward an architecture for never-ending language learning. In AAAI. find
  7. Angel X. Chang and Christopher D. Manning. 2014. TokensRegex: Defining cascaded regular expressions over tokens. Technical Report CSTR 2014-02, Department of Computer Science, Stanford University. find
  8. Zheng Chen, Suzanne Tamang, Adam Lee, Xiang Li, Wen-Pin Lin, Matthew Snover, Javier Artiles, Marissa Passantino, and Heng Ji. 2010. CUNY-BLENDER. In TAC-KBP. find
  9. Mark Craven and Johan Kumlien. 1999. Constructing biological knowledge bases by extracting information from text sources. In AAAI. find
  10. Marie-Catherine de Marneffe and Christopher D. Manning. 2008. The Stanford typed dependencies representation. In Coling 2008: Proceedings of the workshop on Cross-Framework and Cross-Domain Parser Evaluation. find our card
  11. Oren Etzioni. 2011. Search needs a shake-up. Nature, 476(7358):25–26. find
  12. Stefan Evert. 2005. The statistics of word cooccurrences: word pairs and collocations. Ph.D. thesis, Universit at Stuttgart. find
  13. Anthony Fader, Stephen Soderland, and Oren Etzioni. 2011. Identifying relations for open information extraction. In EMNLP. find
  14. Anthony Fader, Luke Zettlemoyer, and Oren Etzioni. 2014. Open question answering over curated and extracted knowledge bases. In KDD. find
  15. Yoav Goldberg and Jon Orwant. 2013. A dataset of syntactic-ngrams over time from a very large corpus of english books. In *SEM. find
  16. Ralph Grishman and Bonan Min. 2010. find
  17. New York University KBP 2010 slot-filling system. In Proc. find
  18. Thomas Icard, III and Lawrence Moss. 2014. Recent progress on monotonicity. Linguistic Issues in Language Technology. find
  19. Heng Ji, Ralph Grishman, Hoa Trang Dang, Kira Griffitt, and Joe Ellis. 2010. Overview of the tac 2010 knowledge base population track. In Third Text Analysis Conference. find
  20. Jay J Jiang and David W Conrath. 1997. Semantic similarity based on corpus statistics and lexical taxonomy. Proceedings of the 10th International Conference on Research on Computational Linguistics. find
  21. Heeyoung Lee, Yves Peirsman, Angel Chang, Nathanael Chambers, Mihai Surdeanu, and Dan Jurafsky. 2011. Stanford’s multi-pass sieve coreference resolution system at the conll-2011 shared task. In CoNLL Shared Task. find our card
  22. Percy Liang, Ben Taskar, and Dan Klein. 2006. Alignment by agreement. In NAACL-HLT. find
  23. Thomas Lin, Mausam, and Oren Etzioni. 2012. No noun phrase left behind: detecting and typing unlinkable entities. In EMNLP-CoNLL. find
  24. Bill MacCartney and Christopher D Manning. 2009. An extended model of natural logic. In Proceedings of the eighth international conference on computational semantics. find
  25. Mausam, Michael Schmitz, Robert Bart, Stephen Soderland, and Oren Etzioni. 2012. Open language learning for information extraction. In EMNLP. find
  26. Filipe Mesquita, Jordan Schmidek, and Denilson Barbosa. 2013. Effectiveness and efficiency of open relation extraction. In EMNLP. find
  27. Bonan Min, Ralph Grishman, Li Wan, Chang Wang, and David Gondek. 2013. Distant supervision for relation extraction with an incomplete knowledge base. In NAACL-HLT. find
  28. Mike Mintz, Steven Bills, Rion Snow, and Dan Jurafsky. 2009. Distant supervision for relation extraction without labeled data. In ACL. find
  29. Neha Nayak, Mark Kowarsky, Gabor Angeli, and Christopher D. Manning. 2014. A dictionary of nonsubsective adjectives. Technical Report CSTR 2014-04, Department of Computer Science, Stanford University, October. find
  30. Glen Pink, Joel Nothman, and R. James Curran. 2014. Analysing recall loss in named entity slot filling. In EMNLP. find
  31. Lev Ratinov, Dan Roth, Doug Downey, and Mike Anderson. 2011. Local and global algorithms for disambiguation to wikipedia. In ACL. find
  32. Sebastian Riedel, Limin Yao, Andrew McCallum, and Benjamin M Marlin. 2013. Relation extraction with matrix factorization and universal schemas. In NAACL-HLT. find
  33. Lorenza Romano, Milen Kouylekov, Idan Szpektor, Ido Dagan, and Alberto Lavelli. 2006. Investigating a generic paraphrase-based approach for relation extraction. EACL. find
  34. Vı́ctor Manuel Sánchez Sánchez Valencia. 1991. Studies on natural logic and categorial grammar. Ph.D. thesis, University of Amsterdam. find
  35. Stephen Soderland, Brendan Roof, Bo Qin, Shi Xu, Mausam, and Oren Etzioni. 2010. Adapting open information extraction to domain-specific relations. AI Magazine, 31(3):93–102. find
  36. Stephen Soderland, John Gilmer, Robert Bart, Oren Etzioni, and Daniel S. Weld. 2013. Open information extraction to KBP relations in 3 hours. In Text Analysis Conference. find
  37. Stephen G Soderland. 1997. Learning text analysis rules for domain-specific natural language processing. Ph.D. thesis, University of Massachusetts. find
  38. Ang Sun, Ralph Grishman, Wei Xu, and Bonan Min. 2011. find
  39. New York University 2011 system for KBP slot filling. In Proceedings of the Text Analytics Conference. find
  40. Mihai Surdeanu. 2013. Overview of the tac2013 knowledge base population evaluation: English slot filling and temporal slot filling. In Sixth Text Analysis Conference. find
  41. Johan van Benthem. 2008. A brief history of natural logic. Technical Report PP-2008-05, University of Amsterdam. find
  42. Yotaro Watanabe, Junta Mizuno, Eric Nichols, Naoaki Okazaki, and Kentaro Inui. 2012. A latent discriminative model for compositional entailment relation recognition using natural logic. In COLING. find
  43. Fei Wu and Daniel S Weld. 2007. Autonomously se-mantifying wikipedia. In Proceedings of the sixteenth ACM conference on information and knowledge management. ACM. find
  44. Fei Wu and Daniel S Weld. 2010. Open information extraction using wikipedia. In ACL. Association for Computational Linguistics. find
  45. Limin Yao, Sebastian Riedel, and Andrew McCallum. 2012. Probabilistic databases of universal schema. In Proceedings of the Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction. find
  46. Alexander Yates, Michael Cafarella, Michele Banko, Oren Etzioni, Matthew Broadhead, and Stephen Soderland. 2007. TextRunner: Open information extraction on the web. In ACL-HLT. find