Learning to Predict Denotational Probabilities For Modeling Entailment
Open accessAbstract
We propose a framework that captures the denotational probabilities of words and phrases by embedding them in a vector space, and present a method to induce such an embedding from a dataset of denotational probabilities.We show that our model successfully predicts denotational probabilities for unseen phrases, and that its predictions are useful for textual entailment datasets such as SICK and SNLI.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Recent works represent random variables as more complex geometric objects, such as cones and axis-aligned hyperrectangles (boxes), and use volume as the probability measure.
“recent works (Lai and Hockenmaier, 2017;Vilnis et al., 2018;Li et al., 2019;Dasgupta et al., 2020) represent random variables as more complex geometric objects, such as cones and axis-aligned hyperrectangles (boxes), and use volume as the probability measure.”
From Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning (2021) · cites this paper as Lai and Hockenmaier, 2017
Section 5, “An order embedding for probabilities,” represents phrases as regions in an embedding space and says joint probability is proportional to the size of their intersection. But it defines probability from vector coordinates, rather than explicitly using volume as its probability measure, and does not describe its regions as cones or axis-aligned boxes. The cited paper therefore supports the geometric-region idea, but not those specific examples or the stated measure. (LLM, conf=0.85)
Experimental — accuracy not yet measuredThe rigid structure imposed by the cone representation limits representational capacity, and the resulting model cannot model negative correlation or disjointness.
“Lai and Hockenmaier (2017) extend order embeddings with a probabilistic interpretation by integrating the volume of the infinite cones under the negative exponential measure, however the rigid structure imposed by the cone representation limits the representational capacity, and the resulting model cannot model negative correlation or disjointness.”
From Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning (2021) · cites this paper as Lai and Hockenmaier, 2017
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
No references could be resolved yet.
Research works printed but not linked: 21
- Beltagy, Stephen Roller, Pengxiang Cheng, Ka- trin Erk, and Raymond J. Mooney. 2015. Repre- senting meaning with a combination of logical form and vectors. CoRR, abs/1505.06816. · arXiv
- Jonathan Berant, Ido Dagan, and Jacob Goldberger. 2012. Learning entailment relations by global graph structure optimization. Computational Linguistics, 38(1):73-111, March.
- Samuel R. Bowman, Gabor Angeli, Christopher Potts, and Christopher D. Manning. 2015. A large anno- tated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empiri- cal Methods in Natural Language Processing, pages 632-642.
- Qian Chen, Xiaodan Zhu, Zhenhua Ling, Si Wei, and Hui Jiang. 2016. Enhancing and combining sequen- tial and tree LSTM for natural language inference. CoRR, abs/1609.06038. · arXiv
- Ido Dagan, Oren Glickman, and Bernardo Magnini. 2006. The PASCAL recognising textual entail- ment challenge. In Proceedings of the First In- ternational Conference on Machine Learning Chal- lenges: Evaluating Predictive Uncertainty Visual Object Classification, and Recognizing Textual En- tailment, MLCW'05, pages 177-190, Berlin, Hei- delberg. Springer-Verlag.
- Ido Dagan, Dan Roth, Mark Sammons, and Fabio Mas- simo Zanzotto. 2013. Recognizing textual entail- ment: Models and applications. Synthesis Lectures on Human Language Technologies, 6(4):1-220.
- Katrin Erk. 2009. Representing words as regions in vector space. In Proceedings of the Thirteenth Con- ference on Computational Natural Language Learn- ing (CoNLL-2009), pages 57-65, Boulder, Col- orado, June.
- James Henderson and Diana Popa. 2016. A vector space for distributional semantics for entailment. In Proceedings of the 54th Annual Meeting of the As- sociation for Computational Linguistics (Volume 1: Long Papers), pages 2052-2062, Berlin, Germany, August.
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Comput., 9(8):1735- 1780, November.
- Germn Kruszewski, Denis Paperno, and Marco Baroni. 2015. Deriving boolean structures from distribu- tional vectors. Transactions of the Association for Computational Linguistics, 3:375-388.
- Alice Lai and Julia Hockenmaier. 2014. Illinois-LH: A denotational and distributional approach to seman- tics. In Proceedings of the 8th International Work- shop on Semantic Evaluation (SemEval 2014), pages 329-334.
- Yang Liu, Chengjie Sun, Lei Lin, and Xiaolong Wang. 2016. Learning natural language inference us- ing bidirectional LSTM model and inner-attention. CoRR, abs/1605.09090. · arXiv
- Marco Marelli, Stefano Menini, Marco Baroni, Luisa Bentivogli, Raffaella Bernardi, and Roberto Zam- parelli. 2014. A SICK cure for the evaluation of compositional distributional semantic models. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC- 2014).
- Tsendsuren Munkhdalai and Hong Yu. 2017a. Neural semantic encoders. In Proceedings of the 15th Con- ference of the European Chapter of the Association for Computational Linguistics.
- Tsendsuren Munkhdalai and Hong Yu. 2017b. Neural tree indexers for text understanding. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics.
- Ankur Parikh, Oscar Täckström, Dipanjan Das, and Jakob Uszkoreit. 2016. A decomposable attention model for natural language inference. In Proceed- ings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2249-2255, Austin, Texas, November.
- Jeffrey Pennington, Richard Socher, and Christo- pher D. Manning. 2014. GloVe: Global vectors for word representation. In Empirical Methods in Nat- ural Language Processing (EMNLP), pages 1532- 1543.
- Tim Rocktäschel, Edward Grefenstette, Karl Moritz Hermann, Tomas Kocisky, and Phil Blunsom. 2016. Reasoning about entailment with neural attention. In The International Conference on Learning Rep- resentations (ICLR).
- Ivan Vendrov, Ryan Kiros, Sanja Fidler, and Raquel Urtasun. 2016. Order-embeddings of images and language. In The International Conference on Learning Representations (ICLR).
- Luke Vilnis and Andrew McCallum. 2015. Word rep- resentations via gaussian embedding. In The Inter- national Conference on Learning Representations (ICLR).
- Peter Young, Alice Lai, Micah Hodosh, and Julia Hockenmaier. 2014. From image descriptions to visual denotations. Transactions of the Association of Computational Linguistics -Volume 2, Issue 1, pages 67-78.
Cited by
Sorted by citations
Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings
Ren, H., Hu, W., & Leskovec, J. (2020) · arXiv · doi:10.48550/arxiv.2002.05969 · Cited by 135 · see citing works
Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning
Chen, X., Boratko, M., Chen, M., Dasgupta, S. S., Li, X. L., & McCallum, A. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.68 · Cited by 47 · see citing works
“Lai and Hockenmaier (2017) extend order embeddings with a probabilistic interpretation by integrating the volume of the infinite cones under the negative exponential measure, however the rigid structure imposed by the cone representation limits the representational capacity, and the resulting model…”
BackgroundModeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones
Bai, Y., Ying, R., Ren, H., & Leskovec, J. (2021) · arXiv · doi:10.48550/arxiv.2110.14923 · Cited by 31 · see citing works
“The most related line of work is learning structured embeddings to perform hierarchical reasoning on graphs and ontologies: order embedding, probabilistic order embedding, box embedding, Gumbel-box embedding and hyperbolic embedding [10, 11, 12, 19, 20, 21, 22].”
BackgroundBox-To-Box Transformations for Modeling Joint Hierarchies
Dasgupta, S. S., Li, X. L., Boratko, M., Zhang, D., & McCallum, A. (2021) · Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021) · doi:10.18653/v1/2021.repl4nlp-1.28 · Cited by 2 · see citing works
- Authors
- Lai, A., & Hockenmaier, J.
- Affiliations
- University of Illinois Urbana-Champaign (US)
- ORCID
- Hockenmaier, Julia
- Venue
- Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
- Published
- 2017
- OpenAlex
- W2741449676
- Cited by
- 33
- References
- 0
- Citations by year
- 2024: 4 · 2023: 1 · 2022: 5 · 2021: 11 · 2020: 4 · 2019: 1 · 2018: 5 · 2017: 2
- FWCI
- 1.50
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference of the European Chapter of the Association for Computational Linguistics (publishedVersion, cc-by)
- Funders
- National Science Foundation (1053856, 1563727, 1405883)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Social Sciences › Arts and Humanities › Language and Linguistics › Syntax, Semantics, Linguistic Variation
- Keywords
- word embeddings, phrase embeddings, natural language inference, SICK, SNLI, word sense disambiguation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
