---
title: "Semantic Parsing via Paraphrasing — Berant 2014"
description: "A semantic parser maps a natural-language question to a logical form that can be executed against a knowledge… 36 references, cited by 186 papers here."
authors: ["Jonathan Berant", "Percy Liang"]
year: 2014
venue: "Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/P14-1133/"
doi: "10.3115/v1/p14-1133"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/berant-2014-semantic-parsing-paraphrasing/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/berant-2014-semantic-parsing-paraphrasing/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2014](https://md.research.elamur.ai/free/en/papers/2014/) / Semantic Parsing via Paraphrasing

# Semantic Parsing via Paraphrasing

**Authors:** [Jonathan Berant](https://md.research.elamur.ai/free/en/authors/jonathan-berant/) and [Percy Liang](https://md.research.elamur.ai/free/en/authors/percy-liang/) · **Year:** 2014 · **Venue:** Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/P14-1133/) · [PDF](https://aclanthology.org/P14-1133.pdf) · [DOI 10.3115/v1/p14-1133](https://doi.org/10.3115/v1/p14-1133) · [OpenAlex](https://openalex.org/W2250225488)

**Citations:** 495 citations (OpenAlex, 2026-10-14) · [186](https://md.research.elamur.ai/free/en/papers/berant-2014-semantic-parsing-paraphrasing/cited-by/) in our library, of the 140,884 papers whose bibliographies we read

## Summary

A semantic parser maps a natural-language question to a logical form that can be executed against a knowledge base. The central problem is that the same knowledge-base predicate can be phrased in countless ways. Conventional parsers are trained only on text aligned with the knowledge base, so vast amounts of ordinary text go unused. Berant and Liang turn the task around. First, simple deterministic rules start from the entities in the question and construct a set of candidate logical forms. For each form, a "canonical" utterance is generated from the predicate descriptions in Freebase. A paraphrase model then selects the utterance closest in meaning to the input question and returns the corresponding logical form. Paraphrases are scored by two models: an association model built on the PARALEX corpus and a vector space model. They are trained jointly from question–answer pairs alone. The PARASEMPRE system improved on the then state-of-the-art result on WebQuestions and matched the best system on Free917. The work shows that text not aligned with the knowledge base can also help train semantic parsers.

## Key points

- **Data:** WebQuestions contains 5,810 question–answer pairs drawn from real web queries; Free917 contains 917 questions written by annotators. The knowledge base is Freebase: about 41M entities, 19K properties, and 596M assertions. Logical forms are expressed in simple λ-DCS.
- **Results:** on WebQuestions, accuracy improved by about 12% relative to the previous state-of-the-art; on Free917, the result is on par with the best system. Simple baselines (Jaccard, Edit, WDDC06) perform reasonably well on Free917 because the vocabulary of its questions is close to Freebase phrasing, but they are considerably weaker on WebQuestions.
- **Model:** a discriminative log-linear model combines paraphrase features with logical-form features. Training uses AdaGrad with L1 regularization and a beam of size 2,000. Candidate logical forms are built from 5 templates, including ones for multi-argument events and for aggregation (count).
- **Resources:** the association model relies on the PARALEX monolingual parallel corpus, and the vector space model on word vectors trained on Wikipedia. The PARASEMPRE code has been released as part of SEMPRE (Stanford NLP).
- **Limitations:** error analysis revealed spurious word matches in the paraphrase model, entity recognition errors, and a lack of support for temporal information. The approach is designed for factoid questions with limited compositionality.

*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: [Machine translation](https://md.research.elamur.ai/free/en/shelves/machine-translation/) · [AI & machine learning](https://md.research.elamur.ai/free/en/shelves/ai/)

Topics: [🕸️ Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/) · [🧾 Semantic parsing & meaning representation](https://md.research.elamur.ai/free/en/topics/semantic-parsing/)

## Institutions

- [Stanford University](https://md.research.elamur.ai/free/en/universities/stanford-university/) — University, Stanford, United States · 248 works · 214,804 citations

## Cite

Cite as: Jonathan Berant and Percy Liang. 2014. Semantic Parsing via Paraphrasing. Proceedings of the 52nd 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{berant2014semantic,
  title = {{Semantic Parsing via Paraphrasing}},
  author = {Jonathan Berant and Percy Liang},
  booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2014},
  doi = {10.3115/v1/p14-1133},
  url = {https://doi.org/10.3115/v1/p14-1133}
}
```

- [← previous Machine Reading Tea Leaves: Automatically Evaluating Topic Coherence and Topic Model Quality](https://md.research.elamur.ai/free/en/papers/lau-2014-machine-reading-tea-leaves-automatically/)
- [next → Fast and Robust Neural Network Joint Models for Statistical Machine Translation](https://md.research.elamur.ai/free/en/papers/devlin-2014-fast-robust-neural-network-joint/)
- [↑ back to papers of 2014](https://md.research.elamur.ai/free/en/papers/2014/)

## References

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

1. J. Berant, A. Chou, R. Frostig, and P. Liang. 2013. Semantic parsing on Freebase from question-answer pairs. In Empirical Methods in Natural Language Processing (EMNLP). [our card](https://md.research.elamur.ai/free/en/papers/berant-2013-semantic-parsing-freebase-question-answer/)
2. Q. Cai and A. Yates. 2013. Large-scale semantic parsing via schema matching and lexicon extension. In Association for Computational Linguistics (ACL). [find](https://scholar.google.com/scholar?q=Q%2E+Cai+and+A%2E+Yates%2E+2013%2E+Large%2Dscale+semantic+parsing+via+schema+matching+and+lexicon+extension%2E+In+Association+for+Computational+Linguistics+%28ACL%29%2E)
3. M. Chang, D. Goldwasser, D. Roth, and V. Srikumar. 2010. Discriminative learning over constrained latent representations. In North American Association for Computational Linguistics (NAACL). [find](https://scholar.google.com/scholar?q=M%2E+Chang%2C+D%2E+Goldwasser%2C+D%2E+Roth%2C+and+V%2E+Srikumar%2E+2010%2E+Discriminative+learning+over+constrained+latent+representations%2E+In+North+American+Association+for+Computational+Linguistics+%28NAACL%29%2E)
4. I. Dagan, D. Roth, M. Sammons, and F. M. Zanzotto. 2013. Recognizing Textual Entailment: Models and Applications. Morgan and Claypool Publishers. [find](https://scholar.google.com/scholar?q=I%2E+Dagan%2C+D%2E+Roth%2C+M%2E+Sammons%2C+and+F%2E+M%2E+Zanzotto%2E+2013%2E+Recognizing+Textual+Entailment%3A+Models+and+Applications%2E+Morgan+and+Claypool+Publishers%2E)
5. R. Dale, S. Geldof, and J. Prost. 2003. Coral: using natural language generation for navigational assistance. In Australasian computer science conference, pages 35–44. [find](https://scholar.google.com/scholar?q=R%2E+Dale%2C+S%2E+Geldof%2C+and+J%2E+Prost%2E+2003%2E+Coral%3A+using+natural+language+generation+for+navigational+assistance%2E+In+Australasian+computer+science+conference%2C+pages+35%E2%80%9344%2E)
6. D. Das and N. A. Smith. 2009. Paraphrase identification as probabilistic quasi-synchronous recognition. In Association for Computational Linguistics (ACL), pages 468–476. [our card](https://md.research.elamur.ai/free/en/papers/das-2009-paraphrase-identification-as-probabilistic-quasi/)
7. B. Dolan, C. Quirk, and C. Brockett. 2004. Unsupervised construction of large paraphrase corpora: Exploiting massively parallel news sources. In International Conference on Computational Linguistics (COLING). [our card](https://md.research.elamur.ai/free/en/papers/dolan-2004-unsupervised-construction-large-paraphrase-corpora/)
8. J. Duchi, E. Hazan, and Y. Singer. 2010. Adaptive subgradient methods for online learning and stochastic optimization. In Conference on Learning Theory (COLT). [find](https://scholar.google.com/scholar?q=J%2E+Duchi%2C+E%2E+Hazan%2C+and+Y%2E+Singer%2E+2010%2E+Adaptive+subgradient+methods+for+online+learning+and+stochastic+optimization%2E+In+Conference+on+Learning+Theory+%28COLT%29%2E)
9. A. Fader, S. Soderland, and O. Etzioni. 2011. Identifying relations for open information extraction. In Empirical Methods in Natural Language Processing (EMNLP). [find](https://scholar.google.com/scholar?q=A%2E+Fader%2C+S%2E+Soderland%2C+and+O%2E+Etzioni%2E+2011%2E+Identifying+relations+for+open+information+extraction%2E+In+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2E)
10. A. Fader, L. Zettlemoyer, and O. Etzioni. 2013. Paraphrase-driven learning for open question answering. In Association for Computational Linguistics (ACL). [our card](https://md.research.elamur.ai/free/en/papers/fader-2013-paraphrase-driven-learning-open-question/)
11. C. Fellbaum. 1998. WordNet: An Electronic Lexical Database. MIT Press. [find](https://scholar.google.com/scholar?q=C%2E+Fellbaum%2E+1998%2E+WordNet%3A+An+Electronic+Lexical+Database%2E+MIT+Press%2E)
12. J. R. Finkel, T. Grenager, and C. Manning. 2005. Incorporating non-local information into information extraction systems by Gibbs sampling. In Association for Computational Linguistics (ACL), pages 363–370. [our card](https://md.research.elamur.ai/free/en/papers/finkel-2005-incorporating-non-local-information-into/)
13. Google. 2013. Freebase data dumps (2013-06-09). [https://developers.google.com/freebase/data](https://developers.google.com/freebase/data). [↗](https://developers.google.com/freebase/data)
14. A. Haghighi, A. Y. Ng, and C. D. Manning. 2005. Robust textual inference via graph matching. In Empirical Methods in Natural Language Processing (EMNLP). [find](https://scholar.google.com/scholar?q=A%2E+Haghighi%2C+A%2E+Y%2E+Ng%2C+and+C%2E+D%2E+Manning%2E+2005%2E+Robust+textual+inference+via+graph+matching%2E+In+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2E)
15. S. Harabagiu and A. Hickl. 2006. Methods for using textual entailment in open-domain question answering. In Association for Computational Linguistics (ACL). [find](https://scholar.google.com/scholar?q=S%2E+Harabagiu+and+A%2E+Hickl%2E+2006%2E+Methods+for+using+textual+entailment+in+open%2Ddomain+question+answering%2E+In+Association+for+Computational+Linguistics+%28ACL%29%2E)
16. M. Heilman and N. A. Smith. 2010. Tree edit models for recognizing textual entailments, paraphrases, and answers to questions. In Human Language Technology and North American Association for Computational Linguistics (HLT/NAACL), pages 1011–1019. [our card](https://md.research.elamur.ai/free/en/papers/heilman-2010-tree-edit-models-recognizing-textual/)
17. E. H. Huang, R. Socher, C. D. Manning, and A. Y. Ng. 2012. Improving word representations via global context and multiple word prototypes. In Association for Computational Linguistics (ACL). [our card](https://md.research.elamur.ai/free/en/papers/huang-2012-improving-word-representations-global-context/)
18. D. Klein and C. Manning. 2003. Accurate unlexicalized parsing. In Association for Computational Linguistics (ACL), pages 423–430. [our card](https://md.research.elamur.ai/free/en/papers/klein-2003-accurate-unlexicalized-parsing/)
19. T. Kwiatkowski, L. Zettlemoyer, S. Goldwater, and M. Steedman. 2010. Inducing probabilistic CCG grammars from logical form with higher-order unification. In Empirical Methods in Natural Language Processing (EMNLP), pages 1223–1233. [find](https://scholar.google.com/scholar?q=T%2E+Kwiatkowski%2C+L%2E+Zettlemoyer%2C+S%2E+Goldwater%2C+and+M%2E+Steedman%2E+2010%2E+Inducing+probabilistic+CCG+grammars+from+logical+form+with+higher%2Dorder+unification%2E+In+Empirical+Methods+in+Natural+Language+Proce)
20. T. Kwiatkowski, E. Choi, Y. Artzi, and L. Zettlemoyer. 2013. Scaling semantic parsers with on-the-fly ontology matching. In Empirical Methods in Natural Language Processing (EMNLP). [our card](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2013-scaling-semantic-parsers-fly-ontology/)
21. P. Liang. 2013. Lambda dependency-based compositional semantics. Technical report, ArXiv. [find](https://scholar.google.com/scholar?q=P%2E+Liang%2E+2013%2E+Lambda+dependency%2Dbased+compositional+semantics%2E+Technical+report%2C+ArXiv%2E)
22. T. Lin, Mausam, and O. Etzioni. 2012. Entity linking at web scale. In Knowledge Extraction Workshop (AKBC-WEKEX). [find](https://scholar.google.com/scholar?q=T%2E+Lin%2C+Mausam%2C+and+O%2E+Etzioni%2E+2012%2E+Entity+linking+at+web+scale%2E+In+Knowledge+Extraction+Workshop+%28AKBC%2DWEKEX%29%2E)
23. T. Mikolov, K. Chen, G. Corrado, and Jeffrey. 2013. Efficient estimation of word representations in vector space. Technical report, ArXiv. [our card](https://md.research.elamur.ai/free/en/papers/mikolov-2013-efficient-estimation-word-representations-vector/)
24. F. J. Och and H. Ney. 2004. The alignment template approach to statistical machine translation. Computational Linguistics, 30:417–449. [find](https://scholar.google.com/scholar?q=F%2E+J%2E+Och+and+H%2E+Ney%2E+2004%2E+The+alignment+template+approach+to+statistical+machine+translation%2E+Computational+Linguistics%2C+30%3A417%E2%80%93449%2E)
25. P. Piwek and K. E. Boyer. 2012. Varieties of question generation: Introduction to this special issue. Dialogue and Discourse, 3:1–9. [find](https://scholar.google.com/scholar?q=P%2E+Piwek+and+K%2E+E%2E+Boyer%2E+2012%2E+Varieties+of+question+generation%3A+Introduction+to+this+special+issue%2E+Dialogue+and+Discourse%2C+3%3A1%E2%80%939%2E)
26. E. Reiter, S. Sripada, J. Hunter, J. Yu, and I. Davy. 2005. Choosing words in computer-generated weather forecasts. Artificial Intelligence, 167:137– 169. [find](https://scholar.google.com/scholar?q=E%2E+Reiter%2C+S%2E+Sripada%2C+J%2E+Hunter%2C+J%2E+Yu%2C+and+I%2E+Davy%2E+2005%2E+Choosing+words+in+computer%2Dgenerated+weather+forecasts%2E+Artificial+Intelligence%2C+167%3A137%E2%80%93+169%2E)
27. L. Romano, M. kouylekov, I. Szpektor, I. Dagan, and A. Lavelli. 2006. Investigating a generic paraphrase-based approach for relation extraction. In Proceedings of ECAL. [find](https://scholar.google.com/scholar?q=L%2E+Romano%2C+M%2E+kouylekov%2C+I%2E+Szpektor%2C+I%2E+Dagan%2C+and+A%2E+Lavelli%2E+2006%2E+Investigating+a+generic+paraphrase%2Dbased+approach+for+relation+extraction%2E+In+Proceedings+of+ECAL%2E)
28. R. Socher, E. H. Huang, J. Pennin, C. D. Manning, and A. Ng. 2011. Dynamic pooling and unfolding recursive autoencoders for paraphrase detection. In Advances in Neural Information Processing Systems (NIPS), pages 801–809. [find](https://scholar.google.com/scholar?q=R%2E+Socher%2C+E%2E+H%2E+Huang%2C+J%2E+Pennin%2C+C%2E+D%2E+Manning%2C+and+A%2E+Ng%2E+2011%2E+Dynamic+pooling+and+unfolding+recursive+autoencoders+for+paraphrase+detection%2E+In+Advances+in+Neural+Information+Processing+Systems+%28)
29. A. Stern and I. Dagan. 2011. A confidence model for syntactically-motivated entailment proofs. In Recent Advances in Natural Language Processing, pages 455–462. [find](https://scholar.google.com/scholar?q=A%2E+Stern+and+I%2E+Dagan%2E+2011%2E+A+confidence+model+for+syntactically%2Dmotivated+entailment+proofs%2E+In+Recent+Advances+in+Natural+Language+Processing%2C+pages+455%E2%80%93462%2E)
30. K. Toutanova and C. D. Manning. 2003. Feature-rich part-of-speech tagging with a cyclic dependency network. In Human Language Technology and North American Association for Computational Linguistics (HLT/NAACL). [our card](https://md.research.elamur.ai/free/en/papers/toutanova-2003-feature-rich-part-speech-tagging/)
31. R. Turner, Y. Sripada, and E. Reiter. 2009. Generating approximate geographic descriptions. In European Workshop on Natural Language Generation, pages 42–49. [find](https://scholar.google.com/scholar?q=R%2E+Turner%2C+Y%2E+Sripada%2C+and+E%2E+Reiter%2E+2009%2E+Generating+approximate+geographic+descriptions%2E+In+European+Workshop+on+Natural+Language+Generation%2C+pages+42%E2%80%9349%2E)
32. S. Wan, M. Dras, R. Dale, and C. Paris. 2006. Using dependency-based features to take the “para-farce” out of paraphrase. In Australasian Language Technology Workshop. [find](https://scholar.google.com/scholar?q=S%2E+Wan%2C+M%2E+Dras%2C+R%2E+Dale%2C+and+C%2E+Paris%2E+2006%2E+Using+dependency%2Dbased+features+to+take+the+%E2%80%9Cpara%2Dfarce%E2%80%9D+out+of+paraphrase%2E+In+Australasian+Language+Technology+Workshop%2E)
33. M. Wang and C. D. Manning. 2010. Probabilistic tree-edit models with structured latent variables for textual entailment and question answering. In The International Conference on Computational Linguistics, pages 1164–1172. [find](https://scholar.google.com/scholar?q=M%2E+Wang+and+C%2E+D%2E+Manning%2E+2010%2E+Probabilistic+tree%2Dedit+models+with+structured+latent+variables+for+textual+entailment+and+question+answering%2E+In+The+International+Conference+on+Computational+Linguis)
34. Y. W. Wong and R. J. Mooney. 2007. Learning synchronous grammars for semantic parsing with lambda calculus. In Association for Computational Linguistics (ACL), pages 960–967. [our card](https://md.research.elamur.ai/free/en/papers/wong-2007-learning-synchronous-grammars-semantic-parsing/)
35. M. Zelle and R. J. Mooney. 1996. Learning to parse database queries using inductive logic proramming. In Association for the Advancement of Artificial Intelligence (AAAI), pages 1050–1055. [find](https://scholar.google.com/scholar?q=M%2E+Zelle+and+R%2E+J%2E+Mooney%2E+1996%2E+Learning+to+parse+database+queries+using+inductive+logic+proramming%2E+In+Association+for+the+Advancement+of+Artificial+Intelligence+%28AAAI%29%2C+pages+1050%E2%80%931055%2E)
36. L. S. Zettlemoyer and M. Collins. 2005. Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars. In Uncertainty in Artificial Intelligence (UAI), pages 658– 666. [our card](https://md.research.elamur.ai/free/en/papers/zettlemoyer-2012-learning-map-sentences-logical-form/)