Elamur Research⌕
☰
home / papers / 2014 / NaturalLI: Natural Logic Inference for Common Sense Reasoning

NaturalLI: Natural Logic Inference for Common Sense Reasoning

Paper · 2014 · Gabor Angeli and Christopher D. Manning

Summary

The paper addresses database completion for common-sense knowledge: deciding whether a short, unseen fact (e.g., that cats have tails) should be accepted as true, given a huge collection of known facts in plain text. The authors present NaturalLI, which performs inference directly over natural-language strings using Natural Logic, building on MacCartney's NatLog relations and the formal semantics of Icard and Moss. Earlier work aligned a query with one premise. NaturalLI instead treats inference as a single search from the query toward any supporting premise. Each step is a reverse Natural Logic mutation with a cost learned from data, so the system can return both strictly valid proofs and merely plausible ones with a confidence score. The authors also show that the finite-state view of the join table can be losslessly reduced to three states: valid, invalid and unknown. Evaluation on the FraCaS suite shows that the system handles strict logical inferences. On common-sense facts it reaches 49% recall at 91% precision. The approach matters because it needs no fixed schema or formal meaning representation and scales to very large text databases.

Key points

  • The premise database contains about 270 million lemmatized, lower-cased short extractions. Test queries combine true ConceptNet facts with false ReVerb extractions.
  • Exact lookup of query facts in the database finds only 12% of them. NaturalLI raises recall roughly fourfold, losing about 9.4% precision.
  • The headline common-sense result is 49% recall with 91% precision.
  • The method relies on MacCartney's seven lexical relations, monotonicity and polarity projection, and Icard's join table. The join table is recast as a finite state automaton that collapses into three truth states.
  • Strict inference is checked on the FraCaS test suite. Planned extensions include meronymy, relation entailment, richer lexicalized parameters and use of syntactic structure during search.

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

🎓Stanford UniversityStanford · United States310 works · 284,480 citations

📚 Shelves 4 Computer Science · 9,086 works Artificial Intelligence · 8,889 works Arts and Humanities · 9,296 works Language and Linguistics · 9,206 works

🧭 Topics 1 Reasoning · 510 works

Cite

Cite as Gabor Angeli and Christopher D. Manning. 2014. NaturalLI: Natural Logic Inference for Common Sense Reasoning. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/v1/d14-1059

@inproceedings{angeli2014naturalli,
  title = {{NaturalLI: Natural Logic Inference for Common Sense Reasoning}},
  author = {Gabor Angeli and Christopher D. Manning},
  booktitle = {Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year = {2014},
  doi = {10.3115/v1/d14-1059},
  url = {https://doi.org/10.3115/v1/d14-1059}
}

References

46 references, 7 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 Manning. 2013. Philosophers are mortal: Inferring the truth of unseen facts. In CoNLL. find
  2. 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. Proc. Linguistic Annotation Workshop. our card
  3. J. Berant and P. Liang. 2014. Semantic parsing via paraphrasing. In Association for Computational Linguistics (ACL). our card
  4. Jonathan Berant, Ido Dagan, and Jacob Goldberger. 2011. Global learning of typed entailment rules. In Proceedings of ACL, Portland, OR. our card
  5. Antoine Bordes, Jason Weston, Ronan Collobert, Yoshua Bengio, et al. 2011. Learning structured embeddings of knowledge bases. In AAAI. find
  6. Thorsten Brants and Alex Franz. 2006. Web 1T 5-gram version 1. Linguistic Data Consortium. find
  7. 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
  8. Danqi Chen, Richard Socher, Christopher D Manning, and Andrew Y Ng. 2013. Learning new facts from knowledge bases with neural tensor networks and semantic word vectors. arXiv preprint arXiv:1301.3618. — [arXiv:1301.3618](https://arxiv.org/abs/1301.3618) find
  9. Robin Cooper, Dick Crouch, Jan Van Eijck, Chris Fox, Johan Van Genabith, Jan Jaspars, Hans Kamp, David Milward, Manfred Pinkal, Massimo Poesio, et al. 1996. Using the framework. Technical report, The FraCaS Consortium. find
  10. Alex J Djalali. 2013. Synthetic logic. Linguistic Issues in Language Technology, 9:1–18. find
  11. Anthony Fader, Stephen Soderland, and Oren Etzioni. 2011. Identifying relations for open information extraction. In EMNLP. find
  12. Anthony Fader, Luke Zettlemoyer, and Oren Etzioni. 2014. Open question answering over curated and extracted knowledge bases. In KDD. find
  13. Matt Gardner, Partha Pratim Talukdar, Bryan Kisiel, and Tom Mitchell. 2013. Improving learning and inference in a large knowledge-base using latent syntactic cues. EMNLP. find
  14. Raphael Hoffmann, Congle Zhang, Xiao Ling, Luke Zettlemoyer, and Daniel S Weld. 2011. Knowledge-based weak supervision for information extraction of overlapping relations. In ACL-HLT. find
  15. Eric H Huang, Richard Socher, Christopher D Manning, and Andrew Y Ng. 2012. Improving word representations via global context and multiple word prototypes. ACL. our card
  16. Thomas Icard, III and Lawrence Moss. 2014. Recent progress on monotonicity. Linguistic Issues in Language Technology. find
  17. Thomas Icard, III. 2012. Inclusion and exclusion in natural language. Studia Logica. find
  18. Rodolphe Jenatton, Nicolas L Roux, Antoine Bordes, and Guillaume R Obozinski. 2012. A latent factor model for highly multi-relational data. In NIPS. find
  19. 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
  20. Tom Kwiatkowski, Eunsol Choi, Yoav Artzi, and Luke Zettlemoyer. 2013. Scaling semantic parsers with on-the-fly ontology matching. our card
  21. Mike Lewis and Mark Steedman. 2013. Combined distributional and logical semantics. TACL, 1:179– 192. find
  22. Bill MacCartney and Christopher D Manning. 2007. Natural logic for textual inference. In ACL-PASCAL Workshop on Textual Entailment and Paraphrasing. find
  23. Bill MacCartney and Christopher D Manning. 2008. Modeling semantic containment and exclusion in natural language inference. In Coling. 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. Bill MacCartney. 2009. Natural Language Inference. Ph.D. thesis, Stanford. find
  26. Mausam, Michael Schmitz, Robert Bart, Stephen Soderland, and Oren Etzioni. 2012. Open language learning for information extraction. In EMNLP. find
  27. John McCarthy. 1980. Circumscription—a form of non-monotonic reasoning. Artificial intelligence. find
  28. Judea Pearl. 1989. Probabilistic semantics for non-monotonic reasoning: A survey. Principles of Knowledge Representation and Reasoning. find
  29. Raymond Reiter. 1980. A logic for default reasoning. Artificial intelligence, 13(1):81–132. find
  30. Sebastian Riedel, Limin Yao, Andrew McCallum, and Benjamin M Marlin. 2013. Relation extraction with matrix factorization and universal schemas. In NAACL-HLT. find
  31. Stefan Schoenmackers, Oren Etzioni, Daniel S Weld, and Jesse Davis. 2010. Learning first-order horn clauses from web text. In EMNLP. find
  32. Lenhart Schubert. 2002. Can we derive general world knowledge from texts? In HLT. find
  33. Rion Snow, Daniel Jurafsky, and Andrew Y Ng. 2006. Semantic taxonomy induction from heterogenous evidence. In ACL. find
  34. Richard Socher, Danqi Chen, Christopher D Manning, and Andrew Ng. 2013. Reasoning with neural tensor networks for knowledge base completion. In NIPS. our card
  35. Stephen Soderland, Brendan Roof, Bo Qin, Shi Xu, Oren Etzioni, et al. 2010. Adapting open information extraction to domain-specific relations. AI Magazine. find
  36. Mihai Surdeanu, Julie Tibshirani, Ramesh Nallapati, and Christopher D. Manning. 2012. Multi-instance multi-label learning for relation extraction. In EMNLP. find
  37. Niket Tandon, Gerard de Melo, and Gerhard Weikum. 2011. Deriving a web-scale common sense fact database. In AAAI. find
  38. Vı́ctor Manuel Sánchez Valencia. 1991. Studies on natural logic and categorial grammar. Ph.D. thesis, University of Amsterdam. find
  39. Johan van Benthem. 1986. Essays in logical semantics. Springer. find
  40. Johan van Benthem. 2008. A brief history of natural logic. Technical Report PP-2008-05, University of Amsterdam. find
  41. Benjamin Van Durme, Phillip Michalak, and Lenhart K Schubert. 2009. Deriving generalized knowledge from corpora using wordnet abstraction. In EACL. find
  42. Ellen M Voorhees. 2001. Question answering in TREC. In Proceedings of the tenth international conference on Information and knowledge management. find
  43. 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
  44. 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
  45. John M. Zelle and Raymond J. Mooney. 1996. Learning to parse database queries using inductive logic programming. In AAAI/IAAI, Portland, OR. our card
  46. Luke S. Zettlemoyer and Michael Collins. 2007. Online learning of relaxed CCG grammars for parsing to logical form. In EMNLP-CoNLL. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/angeli-2014-naturalli-natural-logic-inference-common/