---
title: "Commonsense in Parts — paper by Tandon et al. (2016) · AAAI-16"
description: "Machines lack everyday knowledge about how things are composed: which objects… 89% accuracy. 32 references, cited by 9 papers here."
authors: ["Niket Tandon", "Charles Hariman", "Jacopo Urbani", "Anna Rohrbach", "Marcus Rohrbach", "Gerhard Weikum"]
year: 2016
venue: "AAAI-16"
source: "https://ojs.aaai.org/index.php/AAAI/article/view/9992"
licence: "All rights reserved — free to read at the source"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/tandon-2016-commonsense-parts-mining-part-whole/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tandon-2016-commonsense-parts-mining-part-whole/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2016](https://md.research.elamur.ai/free/en/papers/2016/page/4/) / Commonsense in Parts: Mining Part-Whole Relations from the Web and Image Tags

# Commonsense in Parts: Mining Part-Whole Relations from the Web and Image Tags

**Authors:** [Niket Tandon](https://md.research.elamur.ai/free/en/authors/niket-tandon/), Charles Hariman, [Jacopo Urbani](https://md.research.elamur.ai/free/en/authors/jacopo-urbani/), [Anna Rohrbach](https://md.research.elamur.ai/free/en/authors/anna-rohrbach/), [Marcus Rohrbach](https://md.research.elamur.ai/free/en/authors/marcus-rohrbach/) and [Gerhard Weikum](https://md.research.elamur.ai/free/en/authors/gerhard-weikum/) · **Year:** 2016 · **Venue:** [AAAI-16](https://md.research.elamur.ai/free/en/venues/proceedings-of-the-aaai-conference-on-artificial-intelligence/) ([Proceedings of the AAAI Conference on Artificial Intelligence 2016](https://md.research.elamur.ai/free/en/venues/proceedings-of-the-aaai-conference-on-artificial-intelligence/2016/)) · **Publisher:** [Association for the Advancement of Artificial Intelligence](https://md.research.elamur.ai/free/en/publishers/association-for-the-advancement-of-artificial-intelligence/) · **Licence:** All rights reserved — free to read at the source

**Links:** [Publisher's page](https://doi.org/10.1609/aaai.v30i1.9992) · [PDF](https://ojs.aaai.org/index.php/AAAI/article/download/9992/9851) · [OpenAlex](https://openalex.org/W2317388616)

**Citations:** 22 citations (OpenAlex, 2026-10-14) · [9](https://md.research.elamur.ai/free/en/papers/tandon-2016-commonsense-parts-mining-part-whole/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Machines lack everyday knowledge about how things are composed: which objects have which parts, who belongs to which group, and what things are made of. Earlier resources such as WordNet and ConceptNet are small and hand-built. Automatic collections are noisy, lump all part-whole links into one relation, use ambiguous words instead of senses, and say nothing about whether a part can be seen or how many there are.

The authors built PWKB, a knowledge base learned automatically from the Wikipedia full text and Google n-grams. Bootstrapped pattern extraction uses a new scoring scheme with weighted seeds that rewards patterns which separate the relation types. Arguments, including multi-word phrases, are mapped to WordNet senses. Logical rules then remove inconsistent candidates and derive new ones. Flickr image tags indicate whether a part is visible, and multilingual Google Books n-grams supply part counts.

The result has about 6.75 million assertions, with 89% accuracy in sampled manual checks. That is far larger than prior resources at comparable or better quality. It is useful for search, question answering and vision.

## Key points
- PWKB separates three WordNet-based relations, each with domain and range type restrictions: physicalPartOf, memberOf and substanceOf.
- Pattern extraction starts from 1,200 WordNet seed pairs. Disambiguation extends the IMS tool with OpenNLP noun-phrase chunking, so that phrase heads get resolved to synsets.
- Visibility comes from tags of 100 million Flickr images (YFCC100M). Cardinality comes from Google Books n-grams, with German and Italian grammar used for cases that are hard to resolve in English.
- The final KB holds about 6.75M assertions at 89% sampled accuracy. ConceptNet, by comparison, has only 1,086 part-whole instances.
- In zero-shot image classification over 200 unseen categories, using 811 part classifiers, PWKB raised top-5 accuracy from 23.8% to 25.5%.

*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

- [University of California, Berkeley](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) — University, Berkeley, United States · 243 works · 251,774 citations
- [Max Planck Institute for Informatics](https://md.research.elamur.ai/free/en/labs/max-planck-institute-for-informatics/) — Research institute, Saarbrücken, Germany · 22 works · 4,687 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,959 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,789 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,948 works

## Cite

Cite as: Niket Tandon, Charles Hariman, Jacopo Urbani, Anna Rohrbach, Marcus Rohrbach and Gerhard Weikum. 2016. Commonsense in Parts: Mining Part-Whole Relations from the Web and Image Tags. AAAI-16.

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

```bibtex
@inproceedings{tandon2016commonsense,
  title = {{Commonsense in Parts: Mining Part-Whole Relations from the Web and Image Tags}},
  author = {Niket Tandon, Charles Hariman, Jacopo Urbani, Anna Rohrbach, Marcus Rohrbach and Gerhard Weikum},
  booktitle = {AAAI-16},
  year = {2016},
  doi = {10.1609/aaai.v30i1.9992},
  url = {https://doi.org/10.1609/aaai.v30i1.9992}
}
```

- [← previous Tweet Acts: A Speech Act Classifier for Twitter](https://md.research.elamur.ai/free/en/papers/vosoughi-2016-tweet-acts-speech-act-classifier/)
- [next → Morpho-syntactic Lexicon Generation Using Graph-based Semi-supervised Learning](https://md.research.elamur.ai/free/en/papers/faruqui-2016-morpho-syntactic-lexicon-generation-graph/)
- [↑ back to papers of 2016](https://md.research.elamur.ai/free/en/papers/2016/page/4/)

## References

32 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Berland, M., and Charniak, E. 1999. [Finding parts in very large corpora](https://md.research.elamur.ai/free/en/papers/berland-1999-finding-parts-very-large-corpora/). In ACL.
2. Bouma, G. 2009. Normalized (pointwise) mutual information in collocation extraction. Proceedings of GSCL 31–40. [find](https://scholar.google.com/scholar?q=Bouma%2C+G%2E+2009%2E+Normalized+%28pointwise%29+mutual+information+in+collocation+extraction%2E+Proceedings+of+GSCL+31%E2%80%9340%2E)
3. Brants, T., and Franz, A. 2006. tWeb 1T 5-gram Version 1u. [find](https://scholar.google.com/scholar?q=Brants%2C+T%2E%2C+and+Franz%2C+A%2E+2006%2E+tWeb+1T+5%2Dgram+Version+1u%2E)
4. Brown, L. D.; Cai, T. T.; and DasGupta, A. 2001. Interval estimation for a binomial proportion. [find](https://scholar.google.com/scholar?q=Brown%2C+L%2E+D%2E%3B+Cai%2C+T%2E+T%2E%3B+and+DasGupta%2C+A%2E+2001%2E+Interval+estimation+for+a+binomial+proportion%2E)
5. Statistical Science. Carlson, A.; Betteridge, J.; Kisiel, B.; Settles, B.; Jr., E. H.; and Mitchell, T. 2010. Toward an architecture for never-ending language learning. In AAAI, 1306–1313. AAAI Press. [find](https://scholar.google.com/scholar?q=Statistical+Science%2E+Carlson%2C+A%2E%3B+Betteridge%2C+J%2E%3B+Kisiel%2C+B%2E%3B+Settles%2C+B%2E%3B+Jr%2E%2C+E%2E+H%2E%3B+and+Mitchell%2C+T%2E+2010%2E+Toward+an+architecture+for+never%2Dending+language+learning%2E+In+AAAI%2C+1306%E2%80%931313%2E+AAAI+Press%2E)
6. Chen, X.; Shrivastava, A.; and Gupta, A. 2013. Neil: Extracting visual knowledge from web data. In CVPR. [find](https://scholar.google.com/scholar?q=Chen%2C+X%2E%3B+Shrivastava%2C+A%2E%3B+and+Gupta%2C+A%2E+2013%2E+Neil%3A+Extracting+visual+knowledge+from+web+data%2E+In+CVPR%2E)
7. Chen, X.; Shrivastava, A.; and Gupta, A. 2014. Enriching visual knowledge bases via object discovery and segmentation. In CVPR. [find](https://scholar.google.com/scholar?q=Chen%2C+X%2E%3B+Shrivastava%2C+A%2E%3B+and+Gupta%2C+A%2E+2014%2E+Enriching+visual+knowledge+bases+via+object+discovery+and+segmentation%2E+In+CVPR%2E)
8. Fellbaum, C., ed. 1998. WordNet: An Electronic Lexical Database. The MIT Press. [find](https://scholar.google.com/scholar?q=Fellbaum%2C+C%2E%2C+ed%2E+1998%2E+WordNet%3A+An+Electronic+Lexical+Database%2E+The+MIT+Press%2E)
9. Girju, R.; Badulescu, A.; and Moldovan, D. 2003. [Learning semantic constraints for the automatic discovery of part-whole relations](https://md.research.elamur.ai/free/en/papers/girju-2003-learning-semantic-constraints-automatic-discovery/). In NAACL.
10. Girju, R.; Badulescu, A.; and Moldovan, D. 2006. Automatic discovery of part-whole relations. Computational Linguistics. [find](https://scholar.google.com/scholar?q=Girju%2C+R%2E%3B+Badulescu%2C+A%2E%3B+and+Moldovan%2C+D%2E+2006%2E+Automatic+discovery+of+part%2Dwhole+relations%2E+Computational+Linguistics%2E)
11. Havasi, C.; Speer, R.; and Alonso, J. 2007. ConceptNet 3: a flexible, multilingual semantic network for common sense knowledge. In RANLP. [find](https://scholar.google.com/scholar?q=Havasi%2C+C%2E%3B+Speer%2C+R%2E%3B+and+Alonso%2C+J%2E+2007%2E+ConceptNet+3%3A+a+flexible%2C+multilingual+semantic+network+for+common+sense+knowledge%2E+In+RANLP%2E)
12. Hoffman, J.; Guadarrama, S.; Tzeng, E.; Donahue, J.; Girshick, R.; Darrell, T.; and Saenko, K. 2014. LSDA: Large scale detection through adaptation. In NIPS. [find](https://scholar.google.com/scholar?q=Hoffman%2C+J%2E%3B+Guadarrama%2C+S%2E%3B+Tzeng%2C+E%2E%3B+Donahue%2C+J%2E%3B+Girshick%2C+R%2E%3B+Darrell%2C+T%2E%3B+and+Saenko%2C+K%2E+2014%2E+LSDA%3A+Large+scale+detection+through+adaptation%2E+In+NIPS%2E)
13. Ittoo, A., and Bouma, G. 2010. On learning subtypes of the part-whole relation: do not mix your seeds. In ACL. [find](https://scholar.google.com/scholar?q=Ittoo%2C+A%2E%2C+and+Bouma%2C+G%2E+2010%2E+On+learning+subtypes+of+the+part%2Dwhole+relation%3A+do+not+mix+your+seeds%2E+In+ACL%2E)
14. Ittoo, A., and Bouma, G. 2013. Minimally-supervised extraction of domain-specific part–whole relations using wikipedia as knowledge-base. Data & Knowledge Engineering 85:57–79. [find](https://scholar.google.com/scholar?q=Ittoo%2C+A%2E%2C+and+Bouma%2C+G%2E+2013%2E+Minimally%2Dsupervised+extraction+of+domain%2Dspecific+part%E2%80%93whole+relations+using+wikipedia+as+knowledge%2Dbase%2E+Data+%26+Knowledge+Engineering+85%3A57%E2%80%9379%2E)
15. Keet, C. M., and Artale, A. 2008. Representing and Reasoning over a Taxonomy of Part-Whole Relations. Applied Ontology. [find](https://scholar.google.com/scholar?q=Keet%2C+C%2E+M%2E%2C+and+Artale%2C+A%2E+2008%2E+Representing+and+Reasoning+over+a+Taxonomy+of+Part%2DWhole+Relations%2E+Applied+Ontology%2E)
16. Lenat, D. B. 1995. CYC: A large-scale investment in knowledge infrastructure. Commun. ACM. [find](https://scholar.google.com/scholar?q=Lenat%2C+D%2E+B%2E+1995%2E+CYC%3A+A+large%2Dscale+investment+in+knowledge+infrastructure%2E+Commun%2E+ACM%2E)
17. Ling, X.; Clark, P.; and Weld, D. S. 2013. Extracting meronyms for a biology knowledge base using distant supervision. In Proceedings of the 2013 workshop on Automated knowledge base construction, 7–12. [find](https://scholar.google.com/scholar?q=Ling%2C+X%2E%3B+Clark%2C+P%2E%3B+and+Weld%2C+D%2E+S%2E+2013%2E+Extracting+meronyms+for+a+biology+knowledge+base+using+distant+supervision%2E+In+Proceedings+of+the+2013+workshop+on+Automated+knowledge+base+construction%2C+7%E2%80%931)
18. ACM. Matuszek, C.; Witbrock, M.; Kahlert, R.; Cabral, J.; Schneider, D.; Shah, P.; and Lenat, D. 2005. Searching for common sense: Populating Cyc from the Web. In Proc. [find](https://scholar.google.com/scholar?q=ACM%2E+Matuszek%2C+C%2E%3B+Witbrock%2C+M%2E%3B+Kahlert%2C+R%2E%3B+Cabral%2C+J%2E%3B+Schneider%2C+D%2E%3B+Shah%2C+P%2E%3B+and+Lenat%2C+D%2E+2005%2E+Searching+for+common+sense%3A+Populating+Cyc+from+the+Web%2E+In+Proc%2E)
19. McCarthy, D. 2001. Lexical acquisition at the syntax-semantics interface: diathesis alternations, subcategorization frames and selectional preferences. PhD. thesis. [find](https://scholar.google.com/scholar?q=McCarthy%2C+D%2E+2001%2E+Lexical+acquisition+at+the+syntax%2Dsemantics+interface%3A+diathesis+alternations%2C+subcategorization+frames+and+selectional+preferences%2E+PhD%2E+thesis%2E)
20. Mitchell, T.; Cohen, W.; Hruschka, E.; Talukdar, P.; Betteridge, J.; Carlson, A.; Dalvi, B.; Gardner, M.; Kisiel, B.; Krishnamurthy, J.; Lao, N.; Mazaitis, K.; Mohamed, T.; Nakashole, N.; Platanios, E.; Ritter, A.; Samadi, M.; Settles, B.; Wang, R.; Wijaya, D.; Gupta, A.; Chen, X.; Saparov, A.; Grea… [find](https://scholar.google.com/scholar?q=Mitchell%2C+T%2E%3B+Cohen%2C+W%2E%3B+Hruschka%2C+E%2E%3B+Talukdar%2C+P%2E%3B+Betteridge%2C+J%2E%3B+Carlson%2C+A%2E%3B+Dalvi%2C+B%2E%3B+Gardner%2C+M%2E%3B+Kisiel%2C+B%2E%3B+Krishnamurthy%2C+J%2E%3B+Lao%2C+N%2E%3B+Mazaitis%2C+K%2E%3B+Mohamed%2C+T%2E%3B+Nakashole%2C+N%2E%3B+Platanios%2C+E)
21. Pantel, P., and Pennacchiotti, M. 2006. [Espresso: Leveraging generic patterns for automatically harvesting semantic relations](https://md.research.elamur.ai/free/en/papers/pantel-2006-espresso-leveraging-generic-patterns-automatically/). In ACL.
22. Ravichandran, D., and Hovy, E. 2002. [Learning surface text patterns for a question answering system](https://md.research.elamur.ai/free/en/papers/ravichandran-2002-learning-surface-text-patterns-question/). 41–47. ACL.
23. Rohrbach, M.; Stark, M.; and Schiele, B. 2011. Evaluating Knowledge Transfer and Zero-Shot Learning in a Large-Scale Setting. In CVPR. [find](https://scholar.google.com/scholar?q=Rohrbach%2C+M%2E%3B+Stark%2C+M%2E%3B+and+Schiele%2C+B%2E+2011%2E+Evaluating+Knowledge+Transfer+and+Zero%2DShot+Learning+in+a+Large%2DScale+Setting%2E+In+CVPR%2E)
24. Ruiz-Casado, M.; Alfonseca, E.; and Castells, P. 2007. Au-tomatising the learning of lexical patterns: An application to the enrichment of wordnet by extracting semantic relationships from wikipedia. Data & Knowledge Engineering 61(3):484–499. [find](https://scholar.google.com/scholar?q=Ruiz%2DCasado%2C+M%2E%3B+Alfonseca%2C+E%2E%3B+and+Castells%2C+P%2E+2007%2E+Au%2Dtomatising+the+learning+of+lexical+patterns%3A+An+application+to+the+enrichment+of+wordnet+by+extracting+semantic+relationships+from+wikipedia%2E+)
25. Shamma, D. 2014. One hundred million Creative Commons Flickr images for research. [http://labs.yahoo.com/news/yfcc100m/](http://labs.yahoo.com/news/yfcc100m/). [↗](http://labs.yahoo.com/news/yfcc100m/)
26. Shaoul, C. 2010. The westbury lab wikipedia corpus. Edmonton, AB: University of Alberta. Smith, B.; Ceusters, W.; Klagges, B.; Köhler, J.; Kumar, A.; Lomax, J.; Mungall, C.; Neuhaus, F.; Rector, A. L.; and Rosse, C. 2005. Relations in biomedical ontologies. Genome Biology 6(R46). [find](https://scholar.google.com/scholar?q=Shaoul%2C+C%2E+2010%2E+The+westbury+lab+wikipedia+corpus%2E+Edmonton%2C+AB%3A+University+of+Alberta%2E+Smith%2C+B%2E%3B+Ceusters%2C+W%2E%3B+Klagges%2C+B%2E%3B+Ko%CC%88hler%2C+J%2E%3B+Kumar%2C+A%2E%3B+Lomax%2C+J%2E%3B+Mungall%2C+C%2E%3B+Neuhaus%2C+F%2E%3B+Rector%2C+A%2E+L)
27. Speer, R., and Havasi, C. 2012. Representing general relational knowledge in conceptnet 5. In LREC. [find](https://scholar.google.com/scholar?q=Speer%2C+R%2E%2C+and+Havasi%2C+C%2E+2012%2E+Representing+general+relational+knowledge+in+conceptnet+5%2E+In+LREC%2E)
28. Tandon, N.; de Melo, G.; Suchanek, F. M.; and Weikum, G. 2014. Webchild: harvesting and organizing commonsense knowledge from the web. In WSDM. [find](https://scholar.google.com/scholar?q=Tandon%2C+N%2E%3B+de+Melo%2C+G%2E%3B+Suchanek%2C+F%2E+M%2E%3B+and+Weikum%2C+G%2E+2014%2E+Webchild%3A+harvesting+and+organizing+commonsense+knowledge+from+the+web%2E+In+WSDM%2E)
29. Tandon, N.; de Melo, G.; and Weikum, G. 2011. [Deriving a web-scale common sense fact database](https://md.research.elamur.ai/free/en/papers/tandon-2011-deriving-web-scale-common-sense/). In AAAI.
30. Varzi, A. C. 2014. Mereology. In Zalta, E. N., ed., Stanford Encyclopedia of Philosophy. [find](https://scholar.google.com/scholar?q=Varzi%2C+A%2E+C%2E+2014%2E+Mereology%2E+In+Zalta%2C+E%2E+N%2E%2C+ed%2E%2C+Stanford+Encyclopedia+of+Philosophy%2E)
31. Winston, M. E.; Chaffin, R.; and Herrmann, D. 1987. A Taxonomy of Part-Whole Relations. Cognitive Science. [find](https://scholar.google.com/scholar?q=Winston%2C+M%2E+E%2E%3B+Chaffin%2C+R%2E%3B+and+Herrmann%2C+D%2E+1987%2E+A+Taxonomy+of+Part%2DWhole+Relations%2E+Cognitive+Science%2E)
32. Zhong, Z., and Ng, H. T. 2010. It makes sense: A wide-coverage word sense disambiguation system for free text. In ACL. [find](https://scholar.google.com/scholar?q=Zhong%2C+Z%2E%2C+and+Ng%2C+H%2E+T%2E+2010%2E+It+makes+sense%3A+A+wide%2Dcoverage+word+sense+disambiguation+system+for+free+text%2E+In+ACL%2E)

*Updated 3 November 2026*