---
title: "Revisiting Selectional Preferences for — Heinzerling 2017"
description: "Selectional preferences, meaning what kinds of arguments a predicate slot plausibly takes, have long been considered helpful for coreference."
authors: ["Benjamin Heinzerling", "Nafise Sadat Moosavi", "Michael Strube"]
year: 2017
venue: "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/D17-1138/"
doi: "10.18653/v1/d17-1138"
arxiv: "1707.06456"
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/papers/heinzerling-2017-revisiting-selectional-preferences-coreference-resolution/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/heinzerling-2017-revisiting-selectional-preferences-coreference-resolution/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2017](https://md.research.elamur.ai/free/papers/2017/page/3/) / Revisiting Selectional Preferences for Coreference Resolution

# Revisiting Selectional Preferences for Coreference Resolution

**Authors:** [Benjamin Heinzerling](https://md.research.elamur.ai/free/authors/benjamin-heinzerling/), [Nafise Sadat Moosavi](https://md.research.elamur.ai/free/authors/nafise-sadat-moosavi/), [Michael Strube](https://md.research.elamur.ai/free/authors/michael-strube/) · **Year:** 2017 · **Venue:** Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/D17-1138/) · [PDF](https://aclanthology.org/D17-1138.pdf) · [DOI 10.18653/v1/d17-1138](https://doi.org/10.18653/v1/d17-1138) · [arXiv 1707.06456](https://arxiv.org/abs/1707.06456) · [OpenAlex](https://openalex.org/W2737243082)

**Citations:** 9 citations (openalex-snapshot · 2026-10-14) · [5](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Selectional preferences, meaning what kinds of arguments a predicate slot plausibly takes, have long been considered helpful for coreference. Modern resolvers mostly capture them only indirectly, and earlier attempts reported little benefit. The authors revisit the idea with a larger model and a more complex resolver. They extract noun phrases with their dependency contexts, using Enhanced++ dependencies from the Stanford CoreNLP parser, from GigaWord. They also extract fine-grained entity types in context from Wikilinks. Dependency-based embeddings (Levy and Goldberg) are trained on these pairs, so cosine similarity between an argument and a predicate@slot scores how plausible that argument is. Cosine similarities between the antecedent and anaphor embeddings are binned and added as features to the deep-coref ranking model. On the CoNLL 2012 test set this gives a small gain. The result matches the reinforcement-learning variant of deep-coref, which needs considerably longer training. Because the gain is modest and the resource is costly to build, the authors question whether explicit selectional preferences are worth the effort. The paper is valuable as an honest, partly negative result.

## Key points
- The training data combine about 1.4 billion phrase–context pairs from GigaWord with about 12.9 million entity type–context pairs from Wikilinks. At test time, entity types come from entity linking, Freebase lookup and the Ling and Weld fine-grained type mapping.
- On a sample of 10k coreferent and 10k non-coreferent CoNLL training pairs, the selectional preference similarity correlates only weakly to moderately with coreference (Matthews correlation 0.30).
- Removing governor features from deep-coref leaves performance essentially unchanged. This suggests its implicit modeling of selectional preferences adds nothing.
- With binned similarity features (+SP), the CoNLL Avg. F1 on the test set rises from 65.60 to 65.90, and LEA rises from 59.59 to 59.98. Reinforce scores 65.84 but takes about six days to train, versus two days for the baseline. Feeding the embeddings in directly generalizes worse.
- +SP adds roughly 260 extra links:
  - Recall errors drop for all mention types, most strongly for pronouns.
  - Precision errors grow, especially for common nouns.
  - When only anaphoric mentions are used, the gain is about 1 point.

*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/)

Topics: [Coreference resolution](https://md.research.elamur.ai/free/topics/coreference-resolution/)

## Cited by

Cited by

5 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 4 not yet.

- [Enhanced Word Representations for Bridging Anaphora Resolution](https://md.research.elamur.ai/free/papers/hou-2018-enhanced-word-representations-bridging-anaphora/)

## Cite

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

```bibtex
@inproceedings{heinzerling2017revisiting,
  title = {{Revisiting Selectional Preferences for Coreference Resolution}},
  author = {Heinzerling, Benjamin and Moosavi, Nafise Sadat and Strube, Michael},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  year = {2017},
  doi = {10.18653/v1/d17-1138},
  eprint = {1707.06456},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/d17-1138}
}
```

- [← previous Results of the WMT17 Metrics Shared Task](https://md.research.elamur.ai/free/papers/bojar-2017-results-wmt17-metrics-shared-task/)
- [next → Revisiting the ISO standard for dialogue act annotation](https://md.research.elamur.ai/free/papers/bunt-2017-revisiting-iso-standard-dialogue-act/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/papers/2017/page/3/)

## References

32 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Eneko Agirre and David Martinez. 2001. Learning class-to-class selectional preferences. In Proceedings of the ACL 2001 Workshop on Computational Natural Language Learning (ConLL), pages 15–22. [find](https://scholar.google.com/scholar?q=Eneko+Agirre+and+David+Martinez%2E+2001%2E+Learning+class%2Dto%2Dclass+selectional+preferences%2E+In+Proceedings+of+the+ACL+2001+Workshop+on+Computational+Natural+Language+Learning+%28ConLL%29%2C+pages+15%E2%80%9322%2E)
2. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In Proceedings of the 1st International Conference on Language Resources and Evaluation, Granada, Spain, 28–30 May 1998, pages 563–566. [find](https://scholar.google.com/scholar?q=Amit+Bagga+and+Breck+Baldwin%2E+1998%2E+Algorithms+for+scoring+coreference+chains%2E+In+Proceedings+of+the+1st+International+Conference+on+Language+Resources+and+Evaluation%2C+Granada%2C+Spain%2C+28%E2%80%9330+May+1998%2C+) [our card](https://md.research.elamur.ai/free/papers/bagga-1998-algorithms-scoring-coreference-chains/)
3. Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: A collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, Vancouver, B.C., Canada, 10–12 June 2008, pages… [find](https://scholar.google.com/scholar?q=Kurt+Bollacker%2C+Colin+Evans%2C+Praveen+Paritosh%2C+Tim+Sturge%2C+and+Jamie+Taylor%2E+2008%2E+Freebase%3A+A+collaboratively+created+graph+database+for+structuring+human+knowledge%2E+In+Proceedings+of+the+2008+ACM+SI)
4. Kevin Clark and Christopher D. Manning. 2016a. Deep reinforcement learning for mention-ranking coreference models. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Tex., 1–5 November 2016, pages 2256–2262. [find](https://scholar.google.com/scholar?q=Kevin+Clark+and+Christopher+D%2E+Manning%2E+2016a%2E+Deep+reinforcement+learning+for+mention%2Dranking+coreference+models%2E+In+Proceedings+of+the+2016+Conference+on+Empirical+Methods+in+Natural+Language+Proces) [our card](https://md.research.elamur.ai/free/papers/clark-2016-deep-reinforcement-learning-mention-ranking/)
5. Kevin Clark and Christopher D. Manning. 2016b. Improving coreference resolution by learning entity-level distributed representations. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Berlin, Germany, 7–12 August 2016. [find](https://scholar.google.com/scholar?q=Kevin+Clark+and+Christopher+D%2E+Manning%2E+2016b%2E+Improving+coreference+resolution+by+learning+entity%2Dlevel+distributed+representations%2E+In+Proceedings+of+the+54th+Annual+Meeting+of+the+Association+for+C) [our card](https://md.research.elamur.ai/free/papers/clark-2016-improving-coreference-resolution-learning-entity/)
6. Tim Van de Cruys. 2010. A non-negative tensor factorization model for selectional preference induction. Natural Language Engineering, 16(4):417–437. [find](https://scholar.google.com/scholar?q=Tim+Van+de+Cruys%2E+2010%2E+A+non%2Dnegative+tensor+factorization+model+for+selectional+preference+induction%2E+Natural+Language+Engineering%2C+16%284%29%3A417%E2%80%93437%2E)
7. Tim Van de Cruys. 2014. A neural network approach to selectional preference acquisition. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 26– 35, Doha, Qatar. [find](https://scholar.google.com/scholar?q=Tim+Van+de+Cruys%2E+2014%2E+A+neural+network+approach+to+selectional+preference+acquisition%2E+In+Proceedings+of+the+2014+Conference+on+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2C+pages+26%E2%80%93+35)
8. Ido Dagan and Alon Itai. 1990. Automatic processing of large corpora for the resolution of anaphora references. In Proceedings of the 13th International Conference on Computational Linguistics, Helsinki, Finland, 20–25 August 1990, volume 3, pages 330– 332. [find](https://scholar.google.com/scholar?q=Ido+Dagan+and+Alon+Itai%2E+1990%2E+Automatic+processing+of+large+corpora+for+the+resolution+of+anaphora+references%2E+In+Proceedings+of+the+13th+International+Conference+on+Computational+Linguistics%2C+Helsin) [our card](https://md.research.elamur.ai/free/papers/dagan-1990-automatic-processing-large-corpora-resolution/)
9. Katrin Erk. 2007. A simple, similarity-based model for selectional preferences. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, Prague, Czech Republic, 23–30 June 2007, pages 216–223. [find](https://scholar.google.com/scholar?q=Katrin+Erk%2E+2007%2E+A+simple%2C+similarity%2Dbased+model+for+selectional+preferences%2E+In+Proceedings+of+the+45th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+Prague%2C+Czech+Republic%2C+23%E2%80%933)
10. Katrin Erk and Sebastian Padó. 2008. A structured vector space model for word meaning in context. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 897–906. [find](https://scholar.google.com/scholar?q=Katrin+Erk+and+Sebastian+Pado%CC%81%2E+2008%2E+A+structured+vector+space+model+for+word+meaning+in+context%2E+In+Proceedings+of+the+2008+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+897%E2%80%93)
11. Benjamin Heinzerling, Alex Judea, and Michael Strube. 2016. HITS at TAC KBP 2015: Entity discovery and linking, and event nugget detection. In Proceedings of the Text Analysis Conference, National Institute of Standards and Technology, Gaithersburg, Maryland, USA, 16–17 November 2015. [find](https://scholar.google.com/scholar?q=Benjamin+Heinzerling%2C+Alex+Judea%2C+and+Michael+Strube%2E+2016%2E+HITS+at+TAC+KBP+2015%3A+Entity+discovery+and+linking%2C+and+event+nugget+detection%2E+In+Proceedings+of+the+Text+Analysis+Conference%2C+National+Ins)
12. Jerry R. Hobbs. 1978. Resolving pronominal references. Lingua, 44:311–338. [find](https://scholar.google.com/scholar?q=Jerry+R%2E+Hobbs%2E+1978%2E+Resolving+pronominal+references%2E+Lingua%2C+44%3A311%E2%80%93338%2E)
13. Andrew Kehler, Douglas Appelt, Lara Taylor, and Aleksandr Simma. 2004. The (non)utility of predicate-argument frequencies for pronoun interpretation. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Boston, Mas… [find](https://scholar.google.com/scholar?q=Andrew+Kehler%2C+Douglas+Appelt%2C+Lara+Taylor%2C+and+Aleksandr+Simma%2E+2004%2E+The+%28non%29utility+of+predicate%2Dargument+frequencies+for+pronoun+interpretation%2E+In+Proceedings+of+the+Human+Language+Technology+Co)
14. Omer Levy and Yoav Goldberg. 2014. Dependency-based word embeddings. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 302–308. [find](https://scholar.google.com/scholar?q=Omer+Levy+and+Yoav+Goldberg%2E+2014%2E+Dependency%2Dbased+word+embeddings%2E+In+Proceedings+of+the+52nd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+2%3A+Short+Papers%29%2C+pages+302%E2%80%93308%2E)
15. Xiao Ling and Daniel S. Weld. Fine-grained entity recognition. In Proceedings of the 26th Conference on the Advancement of Artificial Intelligence, Toronto, Ontario, Canada, 22–26 July 2012, pages 94–100. [find](https://scholar.google.com/scholar?q=Xiao+Ling+and+Daniel+S%2E+Weld%2E+Fine%2Dgrained+entity+recognition%2E+In+Proceedings+of+the+26th+Conference+on+the+Advancement+of+Artificial+Intelligence%2C+Toronto%2C+Ontario%2C+Canada%2C+22%E2%80%9326+July+2012%2C+pages+94%E2%80%93)
16. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of the Human Language Technology Conference and the 2005 Conference on Empirical Methods in Natural Language Processing, Vancouver, B.C., Canada, 6–8 October 2005, pages 25–32. [find](https://scholar.google.com/scholar?q=Xiaoqiang+Luo%2E+2005%2E+On+coreference+resolution+performance+metrics%2E+In+Proceedings+of+the+Human+Language+Technology+Conference+and+the+2005+Conference+on+Empirical+Methods+in+Natural+Language+Processi) [our card](https://md.research.elamur.ai/free/papers/luo-2005-coreference-resolution-performance-metrics/)
17. Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven J. Bethard, and David Mc-Closky. 2014. The Stanford CoreNLP natural language processing toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 55–60. [find](https://scholar.google.com/scholar?q=Christopher+D%2E+Manning%2C+Mihai+Surdeanu%2C+John+Bauer%2C+Jenny+Finkel%2C+Steven+J%2E+Bethard%2C+and+David+Mc%2DClosky%2E+2014%2E+The+Stanford+CoreNLP+natural+language+processing+toolkit%2E+In+Proceedings+of+52nd+Annual+) [our card](https://md.research.elamur.ai/free/papers/manning-2014-stanford-corenlp-natural-language-processing/)
18. Sebastian Martschat and Michael Strube. 2014. Recall error analysis for coreference resolution. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 25–29 October 2014, pages 2070–2081. [find](https://scholar.google.com/scholar?q=Sebastian+Martschat+and+Michael+Strube%2E+2014%2E+Recall+error+analysis+for+coreference+resolution%2E+In+Proceedings+of+the+2014+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+Doha%2C+Qatar%2C+) [our card](https://md.research.elamur.ai/free/papers/martschat-2014-recall-error-analysis-coreference-resolution/)
19. Sebastian Martschat and Michael Strube. 2015. Latent structures for coreference resolution. Transactions of the Association for Computational Linguistics, 3:405–418. [find](https://scholar.google.com/scholar?q=Sebastian+Martschat+and+Michael+Strube%2E+2015%2E+Latent+structures+for+coreference+resolution%2E+Transactions+of+the+Association+for+Computational+Linguistics%2C+3%3A405%E2%80%93418%2E) [our card](https://md.research.elamur.ai/free/papers/martschat-2015-latent-structures-coreference-resolution/)
20. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. In Proceedings of the ICLR 2013 Workshop Track. [find](https://scholar.google.com/scholar?q=Tomas+Mikolov%2C+Kai+Chen%2C+Greg+Corrado%2C+and+Jeffrey+Dean%2E+2013%2E+Efficient+estimation+of+word+representations+in+vector+space%2E+In+Proceedings+of+the+ICLR+2013+Workshop+Track%2E)
21. Nafise Sadat Moosavi and Michael Strube. 2016a. Search space pruning: A simple solution for better coreference resolvers. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, Cal., 12– 17 June 20… [find](https://scholar.google.com/scholar?q=Nafise+Sadat+Moosavi+and+Michael+Strube%2E+2016a%2E+Search+space+pruning%3A+A+simple+solution+for+better+coreference+resolvers%2E+In+Proceedings+of+the+2016+Conference+of+the+North+American+Chapter+of+the+Ass) [our card](https://md.research.elamur.ai/free/papers/moosavi-2016-search-space-pruning-simple-solution/)
22. Nafise Sadat Moosavi and Michael Strube. 2016b. Which coreference evaluation metric do you trust? A proposal for a link-based entity aware metric. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Berlin, Germany, 7–12 August 2016, pa… [find](https://scholar.google.com/scholar?q=Nafise+Sadat+Moosavi+and+Michael+Strube%2E+2016b%2E+Which+coreference+evaluation+metric+do+you+trust%3F+A+proposal+for+a+link%2Dbased+entity+aware+metric%2E+In+Proceedings+of+the+54th+Annual+Meeting+of+the+Asso) [our card](https://md.research.elamur.ai/free/papers/moosavi-2016-which-coreference-evaluation-metric-do/)
23. Nafise Sadat Moosavi and Michael Strube. 2017. Use generalized representations, but do not forget surface features. In Proceedings of the 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017), pages 1–7, Valencia, Spain. [find](https://scholar.google.com/scholar?q=Nafise+Sadat+Moosavi+and+Michael+Strube%2E+2017%2E+Use+generalized+representations%2C+but+do+not+forget+surface+features%2E+In+Proceedings+of+the+2nd+Workshop+on+Coreference+Resolution+Beyond+OntoNotes+%28CORBO)
24. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the 6th Message Understanding Conference (MUC-6), pages 45–52, San Mateo, Cal. Morgan Kaufmann. [find](https://scholar.google.com/scholar?q=Marc+Vilain%2C+John+Burger%2C+John+Aberdeen%2C+Dennis+Connolly%2C+and+Lynette+Hirschman%2E+1995%2E+A+model%2Dtheoretic+coreference+scoring+scheme%2E+In+Proceedings+of+the+6th+Message+Understanding+Conference+%28MUC%2D6%29%2C) [our card](https://md.research.elamur.ai/free/papers/vilain-1995-model-theoretic-coreference-scoring-scheme/)
25. Sam Wiseman, Alexander M. Rush, and Stuart Shieber. 2016. Learning global features for coreference resolution. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, Cal., 12–17 June 2016. To appea… [find](https://scholar.google.com/scholar?q=Sam+Wiseman%2C+Alexander+M%2E+Rush%2C+and+Stuart+Shieber%2E+2016%2E+Learning+global+features+for+coreference+resolution%2E+In+Proceedings+of+the+2016+Conference+of+the+North+American+Chapter+of+the+Association+fo) [our card](https://md.research.elamur.ai/free/papers/wiseman-2016-learning-global-features-coreference-resolution/)
26. Patrick Pantel, Rahul Bhagat, Bonaventura Coppola, Timothy Chklovski, and Eduard Hovy. 2007. ISP: Learning inferential selectional preferences. In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main… [find](https://scholar.google.com/scholar?q=Patrick+Pantel%2C+Rahul+Bhagat%2C+Bonaventura+Coppola%2C+Timothy+Chklovski%2C+and+Eduard+Hovy%2E+2007%2E+ISP%3A+Learning+inferential+selectional+preferences%2E+In+Human+Language+Technologies+2007%3A+The+Conference+of+t)
27. Robert Parker, David Graff, Junbo Kong, Ke Chen, and Kazuaki Maeda. 2011. English Gigaword Fifth Edition. LDC2011T07. [find](https://scholar.google.com/scholar?q=Robert+Parker%2C+David+Graff%2C+Junbo+Kong%2C+Ke+Chen%2C+and+Kazuaki+Maeda%2E+2011%2E+English+Gigaword+Fifth+Edition%2E+LDC2011T07%2E)
28. Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. GloVe: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 25–29 October 2014, pages 1532–1543. [find](https://scholar.google.com/scholar?q=Jeffrey+Pennington%2C+Richard+Socher%2C+and+Christopher+D%2E+Manning%2E+2014%2E+GloVe%3A+Global+vectors+for+word+representation%2E+In+Proceedings+of+the+2014+Conference+on+Empirical+Methods+in+Natural+Language+Proc)
29. Philip Resnik. 1993. Selection and Information: A Class-based Approach to Lexical Relationships. Ph.D. thesis, Department of Computer and Information Science, University of Pennsylvania, Philadelphia, Penn. [find](https://scholar.google.com/scholar?q=Philip+Resnik%2E+1993%2E+Selection+and+Information%3A+A+Class%2Dbased+Approach+to+Lexical+Relationships%2E+Ph%2ED%2E+thesis%2C+Department+of+Computer+and+Information+Science%2C+University+of+Pennsylvania%2C+Philadelphia%2C)
30. Alan Ritter, Mausam, and Oren Etzioni. 2010. A latent dirichlet allocation method for selectional preferences. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 424–434. [find](https://scholar.google.com/scholar?q=Alan+Ritter%2C+Mausam%2C+and+Oren+Etzioni%2E+2010%2E+A+latent+dirichlet+allocation+method+for+selectional+preferences%2E+In+Proceedings+of+the+48th+Annual+Meeting+of+the+Association+for+Computational+Linguistic)
31. Sebastian Schuster and Christopher D. Manning. 2016. Enhanced english universal dependencies: An improved representation for natural language understanding tasks. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016). [find](https://scholar.google.com/scholar?q=Sebastian+Schuster+and+Christopher+D%2E+Manning%2E+2016%2E+Enhanced+english+universal+dependencies%3A+An+improved+representation+for+natural+language+understanding+tasks%2E+In+Proceedings+of+the+Tenth+Internati) [our card](https://md.research.elamur.ai/free/papers/ud-2016-schuster-enhanced-english-universal-dependencies-improved/)
32. Sameer Singh, Amarnag Subramanya, Fernando Pereira, and Andrew McCallum. 2012. Wikilinks: A large-scale cross-document coreference corpus labeled via links to Wikipedia. Technical Report UM-CS-2012-015, University of Massachusetts, Amherst. *Figure 3: Most similar terms for the queries sink@nsubj, s… [find](https://scholar.google.com/scholar?q=Sameer+Singh%2C+Amarnag+Subramanya%2C+Fernando+Pereira%2C+and+Andrew+McCallum%2E+2012%2E+Wikilinks%3A+A+large%2Dscale+cross%2Ddocument+coreference+corpus+labeled+via+links+to+Wikipedia%2E+Technical+Report+UM%2DCS%2D2012%2D01)