pith. sign in

arxiv: 2010.03496 · v4 · submitted 2020-10-07 · 💻 cs.CL · cs.AI· cs.LG

Inductive Entity Representations from Text via Link Prediction

Daniel Daza , Michael Cochez , Paul Groth This is my paper

Pith reviewed 2026-05-24 14:31 UTC · model grok-4.3

classification 💻 cs.CL cs.AIcs.LG
keywords inductive link predictionentity representationspretrained language modelsknowledge graphstransfer learningentity classificationinformation retrieval
0
0 comments X

The pith

A pretrained language model produces entity representations from knowledge graph text that generalize to unseen entities and transfer to other tasks without fine-tuning.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tests whether vector representations of entities, learned from their textual descriptions in knowledge graphs by optimizing for link prediction, can handle entities never seen in training and can be reused on other tasks. It introduces an evaluation covering inductive link prediction on new entities, entity classification, and entity-oriented information retrieval. The tested architecture relies on a pretrained language model to encode the text and shows clear gains over prior methods on all three settings. This indicates that the representations carry useful information beyond the original link prediction objective and do not require retraining when moved to new entities or tasks.

Core claim

We propose a holistic evaluation protocol for entity representations learned via a link prediction objective. We consider the inductive link prediction and entity classification tasks, which involve entities not seen during training, as well as an information retrieval task for entity-oriented search. An architecture based on a pretrained language model exhibits strong generalization to entities not observed during training, outperforms related state-of-the-art methods with a 22% MRR improvement in link prediction on average, and transfers well to the other tasks without fine-tuning, yielding a 16% accuracy improvement in entity classification and up to 8.8% NDCG@10 in information retrieval.

What carries the argument

An architecture based on a pretrained language model that encodes textual descriptions of entities to support a link prediction training objective.

If this is right

  • Representations learned this way support inductive link prediction on entities absent from the training graph.
  • The same vectors improve entity classification accuracy by an average of 16 percent when used without further training.
  • They also raise NDCG@10 by up to 8.8 percent on natural-language queries in entity-oriented search.
  • Because no task-specific retraining is required, the same vectors can be reused across multiple knowledge-graph applications.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the pattern holds, the cost of maintaining representations for evolving knowledge graphs would drop because new entities could be embedded directly from their text.
  • The same text-to-vector pipeline might be applied to other structured data sources whose nodes carry natural-language descriptions.
  • Downstream systems that currently maintain separate embedding models for search, classification, and recommendation could instead share one text-derived representation store.

Load-bearing premise

The textual descriptions available in knowledge graphs contain sufficient information for a pretrained language model to produce representations that remain useful when applied to entirely new entities and to downstream tasks without any task-specific fine-tuning.

What would settle it

If the same architecture, when tested on a fresh set of entities whose text has no overlap with the training entities, produces link-prediction scores no better than a random embedding baseline, the generalization claim would be falsified.

Figures

Figures reproduced from arXiv: 2010.03496 by Daniel Daza, Michael Cochez, Paul Groth.

Figure 1
Figure 1. Figure 1: Overview of our work: using entity descriptions, [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Inductive link prediction performance (MRR) ver [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Inductive link prediction performance in the vali [PITH_FULL_IMAGE:figures/full_fig_p011_3.png] view at source ↗
read the original abstract

Knowledge Graphs (KG) are of vital importance for multiple applications on the web, including information retrieval, recommender systems, and metadata annotation. Regardless of whether they are built manually by domain experts or with automatic pipelines, KGs are often incomplete. Recent work has begun to explore the use of textual descriptions available in knowledge graphs to learn vector representations of entities in order to preform link prediction. However, the extent to which these representations learned for link prediction generalize to other tasks is unclear. This is important given the cost of learning such representations. Ideally, we would prefer representations that do not need to be trained again when transferring to a different task, while retaining reasonable performance. In this work, we propose a holistic evaluation protocol for entity representations learned via a link prediction objective. We consider the inductive link prediction and entity classification tasks, which involve entities not seen during training. We also consider an information retrieval task for entity-oriented search. We evaluate an architecture based on a pretrained language model, that exhibits strong generalization to entities not observed during training, and outperforms related state-of-the-art methods (22% MRR improvement in link prediction on average). We further provide evidence that the learned representations transfer well to other tasks without fine-tuning. In the entity classification task we obtain an average improvement of 16% in accuracy compared with baselines that also employ pre-trained models. In the information retrieval task, we obtain significant improvements of up to 8.8% in NDCG@10 for natural language queries. We thus show that the learned representations are not limited KG-specific tasks, and have greater generalization properties than evaluated in previous work.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper proposes learning entity representations from textual descriptions in knowledge graphs via a link-prediction objective using a pretrained language model architecture. It introduces a holistic evaluation protocol covering inductive link prediction (on unseen entities), entity classification, and entity-oriented information retrieval, claiming that the resulting representations generalize inductively and transfer to other tasks without fine-tuning, with reported gains of 22% MRR on link prediction, 16% accuracy on classification, and up to 8.8% NDCG@10 on IR over related baselines.

Significance. If the empirical claims hold with proper controls, the work would establish that LM-derived representations trained on link prediction can support inductive generalization to new entities and zero-shot transfer to classification and retrieval, offering a cost-effective alternative to task-specific retraining for KG applications.

major comments (3)
  1. [§4] §4 (Experimental Setup and Results): The abstract and results sections report specific gains (22% MRR, 16% accuracy, 8.8% NDCG@10) but provide no details on how inductive splits were constructed to ensure zero entity overlap between train and test, no statistical significance tests, and no controls for the inductive setting; this undermines verification of the generalization claim.
  2. [§3] §3 (Proposed Method) and §4 (Ablations): No ablation isolates the contribution of the link-prediction training objective versus the frozen pretrained LM encoder alone; without this, it is impossible to confirm that observed inductive and transfer performance depends on KG-specific knowledge rather than general language priors.
  3. [§4] §4 (Transfer Experiments): The entity classification and IR evaluations claim transfer without fine-tuning, but the manuscript does not specify how the representations are extracted or whether any task-specific adaptation occurs during evaluation, which is load-bearing for the 'no fine-tuning' transfer claim.
minor comments (2)
  1. [Abstract] Abstract: Typo 'preform' should be 'perform'.
  2. [§3] Notation for entity representations and scoring function could be clarified with an explicit equation in §3.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive feedback. We address each major comment below and commit to revisions that strengthen the experimental details and clarity of our claims.

read point-by-point responses

  1. Referee: [§4] §4 (Experimental Setup and Results): The abstract and results sections report specific gains (22% MRR, 16% accuracy, 8.8% NDCG@10) but provide no details on how inductive splits were constructed to ensure zero entity overlap between train and test, no statistical significance tests, and no controls for the inductive setting; this undermines verification of the generalization claim.

    Authors: We agree that additional documentation is required. In the revised manuscript we will expand the description of the inductive split construction to explicitly detail how zero entity overlap between train and test was enforced and verified. We will also report statistical significance tests for the reported gains and add explicit controls or protocol clarifications that highlight the inductive nature of the evaluation. revision: yes

  2. Referee: [§3] §3 (Proposed Method) and §4 (Ablations): No ablation isolates the contribution of the link-prediction training objective versus the frozen pretrained LM encoder alone; without this, it is impossible to confirm that observed inductive and transfer performance depends on KG-specific knowledge rather than general language priors.

    Authors: We acknowledge the value of isolating the link-prediction objective. While the current experiments center on the full trained model, we will add an ablation in the revised version that directly compares representations obtained after link-prediction training against those from the frozen pretrained LM encoder alone, thereby clarifying the contribution of the KG-specific training. revision: yes

  3. Referee: [§4] §4 (Transfer Experiments): The entity classification and IR evaluations claim transfer without fine-tuning, but the manuscript does not specify how the representations are extracted or whether any task-specific adaptation occurs during evaluation, which is load-bearing for the 'no fine-tuning' transfer claim.

    Authors: We will revise the transfer-experiment sections to specify the precise extraction method (e.g., pooling strategy over the LM encoder outputs) and to state explicitly that no task-specific fine-tuning or adaptation is applied at evaluation time, thereby reinforcing the zero-shot transfer claim. revision: yes

Circularity Check

0 steps flagged

No circularity; purely empirical claims on benchmarks

full rationale

The paper advances no derivation chain, uniqueness theorem, or first-principles prediction. Its central claims rest on training a pretrained LM architecture on link-prediction loss and reporting empirical gains (22% MRR, 16% accuracy, 8.8% NDCG@10) versus baselines on standard inductive and transfer tasks. No equation reduces to a fitted parameter by construction, no self-citation supplies a load-bearing premise, and no ansatz is smuggled in; the work is therefore self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The approach rests on the domain assumption that pretrained language models already encode the semantic properties needed for KG entities; no new entities are postulated and no free parameters are introduced beyond standard model hyperparameters.

axioms (1)
  • domain assumption Pretrained language models capture semantic information relevant to entities in knowledge graphs
    The architecture uses a pretrained LM to produce entity representations from text; this assumption is required for the inductive generalization claim.

pith-pipeline@v0.9.0 · 5829 in / 1310 out tokens · 37228 ms · 2026-05-24T14:31:05.275462+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

59 extracted references · 59 canonical work pages · 3 internal anchors

  1. [1]

    Sören Auer, Christian Bizer, Georgi Kobilarov, Jens Lehmann, Richard Cyganiak, and Zachary G. Ives. 2007. DBpedia: A Nucleus for a Web of Open Data. In The Semantic Web, 6th International Semantic Web Conference, 2nd Asian Semantic Web Conference, ISWC 2007 + ASWC 2007, Busan, Korea, November 11-15, 2007 (Lecture Notes in Computer Science, Vol. 4825), Kar...

    work page doi:10.1007/978-3-540-76298- 2007

  2. [2]

    Antoine Bordes, Nicolas Usunier, Alberto García-Durán, Jason Weston, and Ok- sana Yakhnenko. 2013. Translating Embeddings for Modeling Multi-relational Data. In Advances in Neural Information Processing Systems 26: 27th Annual Con- ference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, ...

    work page 2013

  3. [3]

    http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling- multi-relational-data

    work page

  4. [4]

    Antoine Bordes, Jason Weston, Ronan Collobert, and Yoshua Bengio. 2011. Learn- ing Structured Embeddings of Knowledge Bases. InProceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2011, San Francisco, California, USA, August 7-11, 2011 , Wolfram Burgard and Dan Roth (Eds.). AAAI Press. http://www.aaai.org/ocs/index.php/AAAI/AAA...

    work page 2011

  5. [5]

    Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Ce- likyilmaz, and Yejin Choi. 2019. COMET: Commonsense Transformers for Auto- matic Knowledge Graph Construction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics . Association for Computational Linguistics, Florence, Italy, 4762–4779. https:...

    work page doi:10.18653/v1/p19-1470 2019

  6. [6]

    Shaosheng Cao, Wei Lu, and Qiongkai Xu. 2016. Deep Neural Networks for Learning Graph Representations. In Proceedings of the Thirtieth AAAI Con- ference on Artificial Intelligence, February 12-17, 2016, Phoenix, Arizona, USA , Dale Schuurmans and Michael P. Wellman (Eds.). AAAI Press, 1145–1152. http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12423

    work page 2016

  7. [7]

    Jeffrey Dalton, Laura Dietz, and James Allan. 2014. Entity query feature expansion using knowledge base links. In The 37th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’14, Gold Coast , QLD, Australia - July 06 - 11, 2014 , Shlomo Geva, Andrew Trotman, Peter Bruza, Charles L. A. Clarke, and Kalervo Järveli...

    work page doi:10.1145/2600428.2609628 2014

  8. [8]

    Tim Dettmers, Pasquale Minervini, Pontus Stenetorp, and Sebastian Riedel. 2018. Convolutional 2D Knowledge Graph Embeddings. In Proceedings of the Thirty- Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Inte...

    work page 2018

  9. [9]

    Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Comput...

    work page doi:10.18653/v1/n19-1423 2019

  10. [10]

    Xin Dong, Evgeniy Gabrilovich, Geremy Heitz, Wilko Horn, Ni Lao, Kevin Murphy, Thomas Strohmann, Shaohua Sun, and Wei Zhang. 2014. Knowl- edge vault: a web-scale approach to probabilistic knowledge fusion. In The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’14, New York, NY, USA - August 24 - 27, 2014 , Sofus A. Ma...

    work page doi:10.1145/2623330.2623623 2014

  11. [11]

    Lucas Drumond, Steffen Rendle, and Lars Schmidt-Thieme. 2012. Predicting RDF Triples in Incomplete Knowledge Bases with Tensor Factorization. InProceedings of the 27th Annual ACM Symposium on Applied Computing (Trento, Italy) (SAC ’12). Association for Computing Machinery, New York, NY, USA, 326–331. https: //doi.org/10.1145/2245276.2245341

    work page doi:10.1145/2245276.2245341 2012

  12. [12]

    Kawin Ethayarajh. 2019. How Contextual are Contextualized Word Represen- tations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Pro- cessing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Lin...

    work page doi:10.18653/v1/d19-1006 2019

  13. [13]

    Dieter Fensel, Umutcan Simsek, Kevin Angele, Elwin Huaman, Elias Kärle, Oleksandra Panasiuk, Ioan Toma, Jürgen Umbrich, and Alexander Wahler

    work page

  14. [14]

    Knowledge Graphs - Method- ology, Tools and Selected Use Cases

    Knowledge Graphs - Methodology, Tools and Selected Use Cases . Springer. https://doi.org/10.1007/978-3-030-37439-6

    work page doi:10.1007/978-3-030-37439-6

  15. [15]

    Gerritse, Faegheh Hasibi, and Arjen P

    Emma J. Gerritse, Faegheh Hasibi, and Arjen P. de Vries. 2020. Graph-Embedding Empowered Entity Retrieval. InAdvances in Information Retrieval - 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal, April 14-17, 2020, Proceed- ings, Part I (Lecture Notes in Computer Science, Vol. 12035) , Joemon M. Jose, Emine Yilmaz, João Magalhães, Pablo...

    work page doi:10.1007/978-3-030-45439-5_7 2020

  16. [16]

    Swapnil Gupta, Sreyash Kenkre, and Partha Talukdar. 2019. CaRe: Open Knowl- edge Graph Embeddings. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) . Association for Computational Linguistics, Hong Kong, China, 378–388. https:/...

    work page doi:10.18653/v1/d19-1036 2019

  17. [17]

    Hamilton, Payal Bajaj, Marinka Zitnik, Dan Jurafsky, and Jure Leskovec

    William L. Hamilton, Payal Bajaj, Marinka Zitnik, Dan Jurafsky, and Jure Leskovec. 2018. Embedding Logical Queries on Knowledge Graphs. In Pro- ceedings of the 32nd International Conference on Neural Information Processing Systems (Montréal, Canada) (NIPS’18). Curran Associates Inc., Red Hook, NY, USA, 2030–2041

    work page 2018

  18. [18]

    Hamilton, Zhitao Ying, and Jure Leskovec

    William L. Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive Represen- tation Learning on Large Graphs. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA , Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. ...

    work page 2017

  19. [19]

    Faegheh Hasibi, Fedor Nikolaev, Chenyan Xiong, Krisztian Balog, Svein Erik Bratsberg, Alexander Kotov, and Jamie Callan. 2017. DBpedia-Entity v2: A Test Collection for Entity Search. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Shinjuku, Tokyo, Japan, August 7-11, 2017 , Noriko Kando, ...

    work page doi:10.1145/3077136.3080751 2017

  20. [20]

    Kamruzzaman Sarker

    Pascal Hitzler, Federico Bianchi, Monireh Ebrahimi, and Md. Kamruzzaman Sarker. 2020. Neural-symbolic integration and the Semantic Web. Semantic Web 11, 1 (2020), 3–11. https://doi.org/10.3233/SW-190368

    work page doi:10.3233/sw-190368 2020

  21. [21]

    Xiao Huang, Jingyuan Zhang, Dingcheng Li, and Ping Li. 2019. Knowledge Graph Embedding Based Question Answering. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, WSDM 2019, Melbourne, VIC, Australia, February 11-15, 2019 , J. Shane Culpepper, Alistair Moffat, Paul N. Bennett, and Kristina Lerman (Eds.). ACM, 105–11...

    work page doi:10.1145/3289600.3290956 2019

  22. [22]

    Ganesh Jawahar, Benoît Sagot, and Djamé Seddah. 2019. What Does BERT Learn about the Structure of Language?. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics . Association for Computational Linguistics, Florence, Italy, 3651–3657. https://doi.org/10.18653/v1/P19-1356

    work page doi:10.18653/v1/p19-1356 2019

  23. [23]

    Rudolf Kadlec, Ondrej Bajgar, and Jan Kleindienst. 2017. Knowledge Base Comple- tion: Baselines Strike Back. In Proceedings of the 2nd Workshop on Representation Learning for NLP. Association for Computational Linguistics, Vancouver, Canada, 69–74. https://doi.org/10.18653/v1/W17-2609

    work page doi:10.18653/v1/w17-2609 2017

  24. [24]

    Seyed Mehran Kazemi and David Poole. 2018. SimplE Embedding for Link Prediction in Knowledge Graphs. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, WWW ’21, April 19–23, 2021, Ljubljana, Slovenia Daniel Daza, Michael Cochez, and Paul Groth NeurIPS 2018, 3-8 December 2018, Montréal,...

    work page 2018

  25. [25]

    Variational Graph Auto-Encoders

    Thomas N. Kipf and Max Welling. 2016. Variational Graph Auto-Encoders. CoRR abs/1611.07308 (2016). arXiv:1611.07308 http://arxiv.org/abs/1611.07308

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  26. [26]

    Tamara G Kolda and Brett W Bader. 2009. Tensor decompositions and applications. SIAM review 51, 3 (2009), 455–500

    work page 2009

  27. [27]

    Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Raetsch, Sylvain Gelly, Bernhard Schölkopf, and Olivier Bachem. 2019. Challenging Common As- sumptions in the Unsupervised Learning of Disentangled Representations. In Proceedings of the 36th International Conference on Machine Learning (Proceed- ings of Machine Learning Research, Vol. 97) , Kamalika ...

    work page 2019

  28. [28]

    Mike Mintz, Steven Bills, Rion Snow, and Daniel Jurafsky. 2009. Distant su- pervision for relation extraction without labeled data. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th Interna- tional Joint Conference on Natural Language Processing of the AFNLP . Asso- ciation for Computational Linguistics, Suntec, Sing...

    work page 2009

  29. [29]

    Maximilian Nickel and Douwe Kiela. 2017. Poincaré Embeddings for Learning Hierarchical Representations. In Advances in Neural Information Processing Sys- tems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA , Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. ...

    work page 2017

  30. [30]

    Maximilian Nickel, Kevin Murphy, Volker Tresp, and Evgeniy Gabrilovich. 2015. A review of relational machine learning for knowledge graphs. Proc. IEEE 104, 1 (2015), 11–33

    work page 2015

  31. [31]

    Maximilian Nickel, Volker Tresp, and Hans-Peter Kriegel. 2011. A Three-Way Model for Collective Learning on Multi-Relational Data. InProceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, Washington, USA, June 28 - July 2, 2011 , Lise Getoor and Tobias Scheffer (Eds.). Omnipress, 809–816. https://icml.cc/2011/papers/438...

    work page 2011

  32. [32]

    Natasha Noy, Yuqing Gao, Anshu Jain, Anant Narayanan, Alan Patterson, and Jamie Taylor. 2019. Industry-scale knowledge graphs: Lessons and challenges. Queue 17, 2 (2019), 48–75

    work page 2019

  33. [33]

    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, EMNLP 2014, October 25-29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL , Alessandro Moschitti, Bo Pang, and Walter Da...

    work page doi:10.3115/v1/d14-1162 2014

  34. [34]

    Matthew Peters, Mark Neumann, Luke Zettlemoyer, and Wen-tau Yih. 2018. Dissecting Contextual Word Embeddings: Architecture and Representation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, 1499–

    work page 2018

  35. [35]

    https://doi.org/10.18653/v1/D18-1179

    work page doi:10.18653/v1/d18-1179

  36. [36]

    Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. InProceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) . Association for Computational Linguistics, Hong Kong, China, 3982–3992. ht...

    work page doi:10.18653/v1/d19-1410 2019

  37. [37]

    Stephen Robertson and Hugo Zaragoza. 2009. The Probabilistic Relevance Frame- work: BM25 and Beyond. Found. Trends Inf. Retr. 3, 4 (April 2009), 333–389. https://doi.org/10.1561/1500000019

    work page doi:10.1561/1500000019 2009

  38. [38]

    Daniel Ruffinelli, Samuel Broscheit, and Rainer Gemulla. 2020. You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https://openreview.net/forum?id= BkxSmlBFvr

    work page 2020

  39. [39]

    Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling

    Michael Sejr Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. 2018. Modeling Relational Data with Graph Convo- lutional Networks. In The Semantic Web - 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, June 3-7, 2018, Proceedings (Lecture Notes in Com- puter Science, Vol. 10843), Aldo Gangemi,...

    work page doi:10.1007/978-3-319-93417-4_38 2018

  40. [40]

    Baoxu Shi and Tim Weninger. 2018. Open-World Knowledge Graph Completion. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, Febr...

    work page 2018

  41. [41]

    Suchanek, Gjergji Kasneci, and Gerhard Weikum

    Fabian M. Suchanek, Gjergji Kasneci, and Gerhard Weikum. 2007. Yago: a core of semantic knowledge. In Proceedings of the 16th International Conference on World Wide Web, WWW 2007, Banff, Alberta, Canada, May 8-12, 2007 , Carey L. Williamson, Mary Ellen Zurko, Peter F. Patel-Schneider, and Prashant J. Shenoy (Eds.). ACM, 697–706. https://doi.org/10.1145/12...

    work page doi:10.1145/1242572.1242667 2007

  42. [42]

    Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, and Jian Tang. 2019. RotatE: Knowl- edge Graph Embedding by Relational Rotation in Complex Space. InInternational Conference on Learning Representations

    work page 2019

  43. [43]

    Teru and William L

    Komal K. Teru and William L. Hamilton. 2019. Inductive Relation Prediction on Knowledge Graphs. CoRR abs/1911.06962 (2019). arXiv:1911.06962 http: //arxiv.org/abs/1911.06962

    work page arXiv 2019

  44. [44]

    Kristina Toutanova and Danqi Chen. 2015. Observed versus latent features for knowledge base and text inference. InProceedings of the 3rd Workshop on Continu- ous Vector Space Models and their Compositionality. Association for Computational Linguistics, Beijing, China, 57–66. https://doi.org/10.18653/v1/W15-4007

    work page doi:10.18653/v1/w15-4007 2015

  45. [45]

    Théo Trouillon, Johannes Welbl, Sebastian Riedel, Éric Gaussier, and Guillaume Bouchard. 2016. Complex Embeddings for Simple Link Prediction. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016 (JMLR Workshop and Conference Proceedings, Vol. 48), Maria-Florina Balcan and Kilian Q. We...

    work page 2016

  46. [46]

    http://proceedings.mlr.press/v48/trouillon16.html

    work page

  47. [47]

    Svitlana Vakulenko, Javier David Fernandez Garcia, Axel Polleres, Maarten de Rijke, and Michael Cochez. 2019. Message Passing for Complex Question An- swering over Knowledge Graphs. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, CIKM 2019, Beijing, China, November 3-7, 2019, Wenwu Zhu, Dacheng Tao, Xueqi C...

    work page doi:10.1145/3357384.3358026 2019

  48. [48]

    Gomez, Lukasz Kaiser, and Illia Polosukhin

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30: Annual Con- ference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg...

    work page 2017

  49. [49]

    Quan Wang, Zhendong Mao, Bin Wang, and Li Guo. 2017. Knowledge graph embedding: A survey of approaches and applications. IEEE Transactions on Knowledge and Data Engineering 29, 12 (2017), 2724–2743

    work page 2017

  50. [50]

    Xiaozhi Wang, Tianyu Gao, Zhaocheng Zhu, Zhiyuan Liu, Juanzi Li, and Jian Tang. 2019. KEPLER: A Unified Model for Knowledge Embedding and Pre- trained Language Representation. CoRR abs/1911.06136 (2019). arXiv:1911.06136 http://arxiv.org/abs/1911.06136

    work page arXiv 2019

  51. [51]

    Zihao Wang, Kwunping Lai, Piji Li, Lidong Bing, and Wai Lam. 2019. Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Pro- cessing (EMNLP-IJCNLP). Association for Computat...

    work page doi:10.18653/v1/d19-1024 2019

  52. [52]

    Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, and Jamie Brew. 2019. HuggingFace’s Transformers: State-of-the-art Natural Language Processing. CoRR abs/1910.03771 (2019). arXiv:1910.03771 http://arxiv.org/abs/ 1910.03771

    work page internal anchor Pith review Pith/arXiv arXiv 2019

  53. [53]

    Ledell Wu, Fabio Petroni, Martin Josifoski, Sebastian Riedel, and Luke Zettlemoyer

    work page

  54. [54]

    CoRR abs/1911.03814 (2019)

    Zero-shot Entity Linking with Dense Entity Retrieval. CoRR abs/1911.03814 (2019). arXiv:1911.03814 http://arxiv.org/abs/1911.03814

    work page arXiv 1911

  55. [55]

    Ruobing Xie, Zhiyuan Liu, Jia Jia, Huanbo Luan, and Maosong Sun. 2016. Repre- sentation Learning of Knowledge Graphs with Entity Descriptions. InProceedings of the Thirtieth AAAI Conference on Artificial Intelligence, February 12-17, 2016, Phoenix, Arizona, USA, Dale Schuurmans and Michael P. Wellman (Eds.). AAAI Press, 2659–2665. http://www.aaai.org/ocs/...

    work page 2016

  56. [56]

    Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2015. Em- bedding Entities and Relations for Learning and Inference in Knowledge Bases. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings , Yoshua Bengio and Yann LeCun (Eds.). http://arxiv.org/abs/1412.6575

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  57. [57]

    Liang Yao, Chengsheng Mao, and Yuan Luo. 2019. KG-BERT: BERT for Knowledge Graph Completion. CoRR abs/1909.03193 (2019). arXiv:1909.03193 http://arxiv. org/abs/1909.03193

    work page arXiv 2019

  58. [58]

    Reddi, and Sanjiv Kumar

    Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, and Sanjiv Kumar. 2020. Are Transformers universal approximators of sequence-to- sequence functions?. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020 . OpenReview.net. https: //openreview.net/forum?id=ByxRM0Ntvr

    work page 2020

  59. [59]

    Nikita Zhiltsov, Alexander Kotov, and Fedor Nikolaev. 2015. Fielded Sequential Dependence Model for Ad-Hoc Entity Retrieval in the Web of Data. InProceedings Inductive Entity Representations from Text via Link Prediction WWW ’21, April 19–23, 2021, Ljubljana, Slovenia of the 38th International ACM SIGIR Conference on Research and Development in Informatio...

    work page doi:10.1145/2766462.2767756 2015