---
title: "Solving Geometry Problems — paper by Seo et al. (2015)"
description: "The paper presents GeoS, described as the first automated system that solves unmodified SAT… 49 references, cited by 65 papers here."
authors: ["Minjoon Seo", "Hannaneh Hajishirzi", "Ali Farhadi", "Oren Etzioni", "Clint Malcolm"]
year: 2015
venue: "Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/D15-1171/"
doi: "10.18653/v1/d15-1171"
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/seo-2015-solving-geometry-problems-combining-text/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/seo-2015-solving-geometry-problems-combining-text/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2015](https://md.research.elamur.ai/free/en/papers/2015/page/2/) / Solving Geometry Problems: Combining Text and Diagram Interpretation

# Solving Geometry Problems: Combining Text and Diagram Interpretation

**Authors:** [Minjoon Seo](https://md.research.elamur.ai/free/en/authors/minjoon-seo/), [Hannaneh Hajishirzi](https://md.research.elamur.ai/free/en/authors/hannaneh-hajishirzi/), [Ali Farhadi](https://md.research.elamur.ai/free/en/authors/ali-farhadi/), [Oren Etzioni](https://md.research.elamur.ai/free/en/authors/oren-etzioni/) and Clint Malcolm · **Year:** 2015 · **Venue:** [Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2015](https://md.research.elamur.ai/free/en/venues/emnlp/2015/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **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/D15-1171/) · [PDF](https://aclanthology.org/D15-1171.pdf) · [DOI 10.18653/v1/d15-1171](https://doi.org/10.18653/v1/d15-1171) · [OpenAlex](https://openalex.org/W2250564385)

**Citations:** 154 citations (OpenAlex, 2026-10-14) · [65](https://md.research.elamur.ai/free/en/papers/seo-2015-solving-geometry-problems-combining-text/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
The paper presents GeoS, described as the first automated system that solves unmodified SAT plane-geometry multiple-choice questions. Each question combines a natural-language text with a raster diagram. GeoS turns both into a formal description in Ω, a typed subset of first-order logic with constants, variables, predicates and functions. It works in three steps:
- The text parser deliberately over-generates candidate literals and scores each one with a log-linear model.
- A diagram parser grounds those literals in the image and scores them.
- A subset of literals is chosen by maximizing an objective that rewards affinity with text and diagram and penalizes redundancy (coherence). Because this objective is submodular, a greedy algorithm gives a near-optimal selection.

An algebraic solver then checks which answer choice is consistent with the chosen literals. GeoS scores 49% on official SAT questions and 61% on practice questions. The authors note that roughly half of a typical SAT math score is the median. Using the diagram also makes text interpretation and dependency parsing more accurate. This matters because it shows multimodal grounding can compensate for very small training sets, and the data and code are public.

## Key points
- **End-to-end scores:** 49% on official and 61% on practice SAT questions. Using only diagram parsing gives about 5–10%, and using only text parsing gives about 10%. With both parsers replaced by oracles, scores rise to 84% (official) and 88% (practice).
- **Text interpretation (official set, F1):**
  - Rule-based baseline: 0.37 (P 0.99, R 0.23).
  - GeoS without the diagram: 0.67.
  - Full GeoS: 0.83.
  - A fully supervised generic semantic parser (Berant et al., 2013): about 33%.
- **Dependency parsing:** GeoS reranks the top-50 trees from the Stanford parser (Chen and Manning, 2014) by its text score. This improves results by 16% over Stanford combined with an equation-separating preprocessor.
- **Error analysis:** about 38% of errors come from text parsing and about 46% from diagram parsing, with about 15% failing in both. The remaining errors involve missing coreference or reasoning beyond the system's scope.
- **Availability:** the dataset, annotations and source code are released at geometry.allenai.org.

## Interesting ideas
- **Over-generate, then select.** Rather than committing to one parse, GeoS proposes many scored candidate relations and picks a consistent subset. This could suit any low-resource semantic parsing task, where a single fragile parse is risky.
- **Submodular objective for interpretation.** Combining an affinity term with a coverage/anti-redundancy term makes a greedy, near-optimal search possible. The same framing could apply to grounded tasks such as navigation instructions or extracting facts from tables.
- **Cross-modal rescoring.** Literals proposed from the text are checked against a second source of evidence, the diagram. The authors show this extra evidence substantially boosts precision. It is a cheap way to clean noisy NLP output wherever an aligned modality or structured resource exists.
- **Reranking a generic parser's n-best list with downstream task scores.** GeoS fixes errors in an off-the-shelf dependency parser without retraining it. This could help adapt UD-style parsers to domains with formulas or other special notation.
- **Oracle-component ablations.** Swapping individual modules for gold annotations shows where the error budget lies, which helps decide which component to improve first in a pipeline.

*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 Washington](https://md.research.elamur.ai/free/en/universities/university-of-washington/) — University, Seattle, United States · 263 works · 180,581 citations
- [Allen Institute for Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/allen-institute-for-artificial-intelligence/) — Research institute, Seattle, United States · 219 works · 89,712 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 1,282 works

## Cite

Cite as: Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi, Oren Etzioni and Clint Malcolm. 2015. Solving Geometry Problems: Combining Text and Diagram Interpretation. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.

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

```bibtex
@inproceedings{seo2015solving,
  title = {{Solving Geometry Problems: Combining Text and Diagram Interpretation}},
  author = {Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi, Oren Etzioni and Clint Malcolm},
  booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing},
  year = {2015},
  doi = {10.18653/v1/d15-1171},
  url = {https://doi.org/10.18653/v1/d15-1171}
}
```

- [← previous Joint prediction in MST-style discourse parsing for argumentation mining](https://md.research.elamur.ai/free/en/papers/peldszus-2015-joint-prediction-mst-style-discourse/)
- [next → Better Summarization Evaluation with Word Embeddings for ROUGE](https://md.research.elamur.ai/free/en/papers/ng-2015-better-summarization-evaluation-word-embeddings/)
- [↑ back to papers of 2015](https://md.research.elamur.ai/free/en/papers/2015/page/2/)

## References

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

1. Chris Alvin, Sumit Gulwani, Rupak Majumdar, and Supratik Mukhopadhyay. 2014. Synthesis of geometry proof problems. In AAAI. [find](https://scholar.google.com/scholar?q=Chris+Alvin%2C+Sumit+Gulwani%2C+Rupak+Majumdar%2C+and+Supratik+Mukhopadhyay%2E+2014%2E+Synthesis+of+geometry+proof+problems%2E+In+AAAI%2E)
2. Gabor Angeli and Christopher D. Manning. 2014. [Naturalli: Natural logic inference for common sense reasoning](https://md.research.elamur.ai/free/en/papers/angeli-2014-naturalli-natural-logic-inference-common/). In EMNLP.
3. Yoav Artzi and Luke Zettlemoyer. 2013. [Weakly supervised learning of semantic parsers for mapping instructions to actions](https://md.research.elamur.ai/free/en/papers/artzi-2013-weakly-supervised-learning-semantic-parsers/). TACL, 1.
4. J. Berant and P. Liang. 2014. [Semantic parsing via paraphrasing](https://md.research.elamur.ai/free/en/papers/berant-2014-semantic-parsing-paraphrasing/). In ACL.
5. Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 2013. [Semantic parsing on freebase from question-answer pairs](https://md.research.elamur.ai/free/en/papers/berant-2013-semantic-parsing-freebase-question-answer/). In EMNLP.
6. College Board. 2014. The college board. [find](https://scholar.google.com/scholar?q=College+Board%2E+2014%2E+The+college+board%2E)
7. Antoine Bordes, Nicolas Usunier, and Jason Weston. 2010. Label ranking under ambiguous supervision for learning semantic correspondences. In ICML. [find](https://scholar.google.com/scholar?q=Antoine+Bordes%2C+Nicolas+Usunier%2C+and+Jason+Weston%2E+2010%2E+Label+ranking+under+ambiguous+supervision+for+learning+semantic+correspondences%2E+In+ICML%2E)
8. SRK Branavan, Nate Kushman, Tao Lei, and Regina Barzilay. 2012. Learning high-level planning from text. In ACL. [find](https://scholar.google.com/scholar?q=SRK+Branavan%2C+Nate+Kushman%2C+Tao+Lei%2C+and+Regina+Barzilay%2E+2012%2E+Learning+high%2Dlevel+planning+from+text%2E+In+ACL%2E)
9. William C. Bulko. 1988. Understanding text with an accompanying diagram. In IEA/AIE. [find](https://scholar.google.com/scholar?q=William+C%2E+Bulko%2E+1988%2E+Understanding+text+with+an+accompanying+diagram%2E+In+IEA%2FAIE%2E)
10. Danqi Chen and Christopher D Manning. 2014. [A fast and accurate dependency parser using neural networks](https://md.research.elamur.ai/free/en/papers/chen-2014-fast-accurate-dependency-parser-neural/). In EMNLP.
11. David Chen, Joohyun Kim, and Raymond Mooney. 2010. Training a multilingual sportscaster: Using perceptual context to learn language. JAIR, 37. [find](https://scholar.google.com/scholar?q=David+Chen%2C+Joohyun+Kim%2C+and+Raymond+Mooney%2E+2010%2E+Training+a+multilingual+sportscaster%3A+Using+perceptual+context+to+learn+language%2E+JAIR%2C+37%2E)
12. Jim Cowie and Wendy Lehnert. 1996. Information extraction. Communications of the ACM, 39(1). [find](https://scholar.google.com/scholar?q=Jim+Cowie+and+Wendy+Lehnert%2E+1996%2E+Information+extraction%2E+Communications+of+the+ACM%2C+39%281%29%2E)
13. Aron Culotta and Jeffrey Sorensen. 2004. [Dependency tree kernels for relation extraction](https://md.research.elamur.ai/free/en/papers/culotta-2004-dependency-tree-kernels-relation-extraction/). In ACL.
14. Jacob Eisenstein, James Clarke, Dan Goldwasser, and Dan Roth. 2009. Reading to learn: Constructing features from semantic abstracts. In EMNLP. [find](https://scholar.google.com/scholar?q=Jacob+Eisenstein%2C+James+Clarke%2C+Dan+Goldwasser%2C+and+Dan+Roth%2E+2009%2E+Reading+to+learn%3A+Constructing+features+from+semantic+abstracts%2E+In+EMNLP%2E)
15. Thomas G Evans. 1964. A heuristic program to solve geometric-analogy problems. In Proceedings of the April 21-23, 1964, spring joint computer conference. [find](https://scholar.google.com/scholar?q=Thomas+G+Evans%2E+1964%2E+A+heuristic+program+to+solve+geometric%2Danalogy+problems%2E+In+Proceedings+of+the+April+21%2D23%2C+1964%2C+spring+joint+computer+conference%2E)
16. Hao Fang, Saurabh Gupta, Forrest Iandola, Rupesh Srivastava, Li Deng, Piotr Dollár, Jianfeng Gao, Xiaodong He, Margaret Mitchell, John Platt, et al. 2014. From captions to visual concepts and back. In CVPR. [find](https://scholar.google.com/scholar?q=Hao+Fang%2C+Saurabh+Gupta%2C+Forrest+Iandola%2C+Rupesh+Srivastava%2C+Li+Deng%2C+Piotr+Dolla%CC%81r%2C+Jianfeng+Gao%2C+Xiaodong+He%2C+Margaret+Mitchell%2C+John+Platt%2C+et+al%2E+2014%2E+From+captions+to+visual+concepts+and+back%2E+I)
17. Ali Farhadi, Mohsen Hejrati, Mohammad Amin Sadeghi, Peter Young, Cyrus Rashtchian, Julia Hockenmaier, and David Forsyth. 2010. Every picture tells a story: Generating sentences from images. In ECCV. [find](https://scholar.google.com/scholar?q=Ali+Farhadi%2C+Mohsen+Hejrati%2C+Mohammad+Amin+Sadeghi%2C+Peter+Young%2C+Cyrus+Rashtchian%2C+Julia+Hockenmaier%2C+and+David+Forsyth%2E+2010%2E+Every+picture+tells+a+story%3A+Generating+sentences+from+images%2E+In+ECCV%2E)
18. E.A. Feigenbaum and J. Feldman, editors. 1963. Computers and Thought. McGraw Hill, New York. [find](https://scholar.google.com/scholar?q=E%2EA%2E+Feigenbaum+and+J%2E+Feldman%2C+editors%2E+1963%2E+Computers+and+Thought%2E+McGraw+Hill%2C+New+York%2E)
19. Jeffrey Flanigan, Sam Thomson, Jaime Carbonell, Chris Dyer, and Noah A. Smith. 2014. [A discriminative graph-based parser for the abstract meaning representation](https://md.research.elamur.ai/free/en/papers/flanigan-2014-discriminative-graph-based-parser-abstract/). In ACL.
20. Ruifang Ge and Raymond J. Mooney. 2006. Discriminative reranking for semantic parsing. In ACL. [find](https://scholar.google.com/scholar?q=Ruifang+Ge+and+Raymond+J%2E+Mooney%2E+2006%2E+Discriminative+reranking+for+semantic+parsing%2E+In+ACL%2E)
21. Dan Goldwasser and Dan Roth. 2011. Learning from natural instructions. In IJCAI. [find](https://scholar.google.com/scholar?q=Dan+Goldwasser+and+Dan+Roth%2E+2011%2E+Learning+from+natural+instructions%2E+In+IJCAI%2E)
22. Yunchao Gong, Liwei Wang, Micah Hodosh, Julia Hockenmaier, and Svetlana Lazebnik. 2014. Improving image-sentence embeddings using large weakly annotated photo collections. In ECCV. [find](https://scholar.google.com/scholar?q=Yunchao+Gong%2C+Liwei+Wang%2C+Micah+Hodosh%2C+Julia+Hockenmaier%2C+and+Svetlana+Lazebnik%2E+2014%2E+Improving+image%2Dsentence+embeddings+using+large+weakly+annotated+photo+collections%2E+In+ECCV%2E)
23. Sonal Gupta and Raymond J. Mooney. 2010. Using closed captions as supervision for video activity recognition. In AAAI. [find](https://scholar.google.com/scholar?q=Sonal+Gupta+and+Raymond+J%2E+Mooney%2E+2010%2E+Using+closed+captions+as+supervision+for+video+activity+recognition%2E+In+AAAI%2E)
24. Hannaneh Hajishirzi, Julia Hockenmaier, Erik T. Mueller, and Eyal Amir. 2011. Reasoning about robocup soccer narratives. In UAI. [find](https://scholar.google.com/scholar?q=Hannaneh+Hajishirzi%2C+Julia+Hockenmaier%2C+Erik+T%2E+Mueller%2C+and+Eyal+Amir%2E+2011%2E+Reasoning+about+robocup+soccer+narratives%2E+In+UAI%2E)
25. Hannaneh Hajishirzi, Leila Zilles, Daniel S Weld, and Luke S Zettlemoyer. 2013. [Joint coreference resolution and named-entity linking with multi-pass sieves](https://md.research.elamur.ai/free/en/papers/hajishirzi-2013-joint-coreference-resolution-named-entity/). In EMNLP.
26. Mary Hegarty and Marcel Adam Just. 1989. 10 understanding machines from text and diagrams. Knowledge acquisition from text and pictures. [find](https://scholar.google.com/scholar?q=Mary+Hegarty+and+Marcel+Adam+Just%2E+1989%2E+10+understanding+machines+from+text+and+diagrams%2E+Knowledge+acquisition+from+text+and+pictures%2E)
27. Ben Hixon, Peter Clark, and Hannaneh Hajishirzi. 2015. Learning knowledge graphs for question answering through conversational dialog. In NAACL. [find](https://scholar.google.com/scholar?q=Ben+Hixon%2C+Peter+Clark%2C+and+Hannaneh+Hajishirzi%2E+2015%2E+Learning+knowledge+graphs+for+question+answering+through+conversational+dialog%2E+In+NAACL%2E)
28. Mohammad Javad Hosseini, Hannaneh Hajishirzi, Oren Etzioni, and Nate Kushman. 2014. [Learning to solve arithmetic word problems with verb categorization](https://md.research.elamur.ai/free/en/papers/hosseini-2014-learning-solve-arithmetic-word-problems/). In EMNLP.
29. Rohit J. Kate and Raymond J. Mooney. 2007. Learning language semantics from ambiguous supervision. In AAAI. [find](https://scholar.google.com/scholar?q=Rohit+J%2E+Kate+and+Raymond+J%2E+Mooney%2E+2007%2E+Learning+language+semantics+from+ambiguous+supervision%2E+In+AAAI%2E)
30. Joohyun Kim and Raymond J. Mooney. 2013. Adapting discriminative reranking to grounded language learning. In ACL. [find](https://scholar.google.com/scholar?q=Joohyun+Kim+and+Raymond+J%2E+Mooney%2E+2013%2E+Adapting+discriminative+reranking+to+grounded+language+learning%2E+In+ACL%2E)
31. Dan Klein and Christopher D Manning. 2005. Parsing and hypergraphs. In New developments in parsing technology. Springer. [find](https://scholar.google.com/scholar?q=Dan+Klein+and+Christopher+D+Manning%2E+2005%2E+Parsing+and+hypergraphs%2E+In+New+developments+in+parsing+technology%2E+Springer%2E)
32. R Koncel-Kedziorski, Hannaneh Hajishirzi, and Ali Farhadi. 2014. Multi-resolution language grounding with weak supervision. In EMNLP. [find](https://scholar.google.com/scholar?q=R+Koncel%2DKedziorski%2C+Hannaneh+Hajishirzi%2C+and+Ali+Farhadi%2E+2014%2E+Multi%2Dresolution+language+grounding+with+weak+supervision%2E+In+EMNLP%2E)
33. Dieter et. al. Kraft. 1988. A software package for sequential quadratic programming. DFVLR Obers-faffeuhofen, Germany. [find](https://scholar.google.com/scholar?q=Dieter+et%2E+al%2E+Kraft%2E+1988%2E+A+software+package+for+sequential+quadratic+programming%2E+DFVLR+Obers%2Dfaffeuhofen%2C+Germany%2E)
34. Girish Kulkarni, Visruth Premraj, Sagnik Dhar, Siming Li, Yejin Choi, Alexander C Berg, and Tamara L Berg. 2011. Baby talk: Understanding and generating image descriptions. In CVPR. [find](https://scholar.google.com/scholar?q=Girish+Kulkarni%2C+Visruth+Premraj%2C+Sagnik+Dhar%2C+Siming+Li%2C+Yejin+Choi%2C+Alexander+C+Berg%2C+and+Tamara+L+Berg%2E+2011%2E+Baby+talk%3A+Understanding+and+generating+image+descriptions%2E+In+CVPR%2E)
35. Nate Kushman, Yoav Artzi, Luke Zettlemoyer, and Regina Barzilay. 2014. Learning to automatically solve algebra word problems. In ACL. [find](https://scholar.google.com/scholar?q=Nate+Kushman%2C+Yoav+Artzi%2C+Luke+Zettlemoyer%2C+and+Regina+Barzilay%2E+2014%2E+Learning+to+automatically+solve+algebra+word+problems%2E+In+ACL%2E)
36. T Kwiatkowski, E Choi, Y Artzi, and L Zettlemoyer. 2013. [Scaling semantic parsers with on-the-fly ontology matching](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2013-scaling-semantic-parsers-fly-ontology/). In EMNLP.
37. Percy Liang, Michael I. Jordan, and Dan Klein. 2009. [Learning semantic correspondences with less supervision](https://md.research.elamur.ai/free/en/papers/liang-2009-learning-semantic-correspondences-less-supervision/). In ACLAFNLP.
38. Xinggang Lin, Shigeyoshi Shimotsuji, Michihiko Minoh, and Toshiyuki Sakai. 1985. Efficient diagram understanding with characteristic pattern detection. CVGIP, 30(1). [find](https://scholar.google.com/scholar?q=Xinggang+Lin%2C+Shigeyoshi+Shimotsuji%2C+Michihiko+Minoh%2C+and+Toshiyuki+Sakai%2E+1985%2E+Efficient+diagram+understanding+with+characteristic+pattern+detection%2E+CVGIP%2C+30%281%29%2E)
39. A. Lovett and K. Forbus. 2012. Modeling multiple strategies for solving geometric analogy problems. In CCS. [find](https://scholar.google.com/scholar?q=A%2E+Lovett+and+K%2E+Forbus%2E+2012%2E+Modeling+multiple+strategies+for+solving+geometric+analogy+problems%2E+In+CCS%2E)
40. Gordon Novak. 1995. Diagrams for solving physical problems. Diagrammatic reasoning: Cognitive and computational perspectives. [find](https://scholar.google.com/scholar?q=Gordon+Novak%2E+1995%2E+Diagrams+for+solving+physical+problems%2E+Diagrammatic+reasoning%3A+Cognitive+and+computational+perspectives%2E)
41. Lawrence O’Gorman and Rangachar Kasturi. 1995. Document image analysis, volume 39. Citeseer. [find](https://scholar.google.com/scholar?q=Lawrence+O%E2%80%99Gorman+and+Rangachar+Kasturi%2E+1995%2E+Document+image+analysis%2C+volume+39%2E+Citeseer%2E)
42. Hoifung Poon and Pedro Domingos. 2009. [Unsupervised semantic parsing](https://md.research.elamur.ai/free/en/papers/poon-2009-unsupervised-semantic-parsing/). In EMNLP.
43. Siva Reddy, Mirella Lapata, and Mark Steedman. 2014. Large-scale semantic parsing without question-answer pairs. TACL, 2(Oct). [find](https://scholar.google.com/scholar?q=Siva+Reddy%2C+Mirella+Lapata%2C+and+Mark+Steedman%2E+2014%2E+Large%2Dscale+semantic+parsing+without+question%2Danswer+pairs%2E+TACL%2C+2%28Oct%29%2E)
44. S. Roy, T. Vieira, and D. Roth. 2015. Reasoning about quantities in natural language. [find](https://scholar.google.com/scholar?q=S%2E+Roy%2C+T%2E+Vieira%2C+and+D%2E+Roth%2E+2015%2E+Reasoning+about+quantities+in+natural+language%2E)
45. Min Joon Seo, Hannaneh Hajishirzi, Ali Farhadi, and Oren Etzioni. 2014. Diagram understanding in geometry questions. In AAAI. [find](https://scholar.google.com/scholar?q=Min+Joon+Seo%2C+Hannaneh+Hajishirzi%2C+Ali+Farhadi%2C+and+Oren+Etzioni%2E+2014%2E+Diagram+understanding+in+geometry+questions%2E+In+AAAI%2E)
46. Rohini K Srihari. 1994. Computational models for integrating linguistic and visual information: A survey. Artificial Intelligence Review, 8(5-6). [find](https://scholar.google.com/scholar?q=Rohini+K+Srihari%2E+1994%2E+Computational+models+for+integrating+linguistic+and+visual+information%3A+A+survey%2E+Artificial+Intelligence+Review%2C+8%285%2D6%29%2E)
47. Adam Vogel and Daniel Jurafsky. 2010. Learning to follow navigational directions. In ACL. [find](https://scholar.google.com/scholar?q=Adam+Vogel+and+Daniel+Jurafsky%2E+2010%2E+Learning+to+follow+navigational+directions%2E+In+ACL%2E)
48. David J Wales and Jonathan PK Doye. 1997. Global optimization by basin-hopping and the lowest energy structures of lennard-jones clusters containing up to 110 atoms. The Journal of Physical Chemistry A, 101(28). [find](https://scholar.google.com/scholar?q=David+J+Wales+and+Jonathan+PK+Doye%2E+1997%2E+Global+optimization+by+basin%2Dhopping+and+the+lowest+energy+structures+of+lennard%2Djones+clusters+containing+up+to+110+atoms%2E+The+Journal+of+Physical+Chemistry+)
49. Luke S. Zettlemoyer and Michael Collins. 2005. [Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars](https://md.research.elamur.ai/free/en/papers/zettlemoyer-2012-learning-map-sentences-logical-form/). In UAI.

*Updated 24 October 2026*