Data Portal @ linkeddatafragments.org

Matches in ESWC 2020 for { ?s ?p ?o. }

• Paper.52_Review.0_Reviewer type RoleDuringEvent.
• Paper.52_Review.0_Reviewer label "Anonymous Reviewer for Paper 52".
• Paper.52_Review.0_Reviewer withRole ReviewerRole.
• Paper.52_Review.0_Reviewer withRole AnonymousReviewerRole.
• Paper.52_Review.0 type ReviewVersion.
• Paper.52_Review.0 issued "2001-01-26T16:17:00.000Z".
• Paper.52_Review.0 creator Paper.52_Review.0_Reviewer.
• Paper.52_Review.0 hasRating ReviewRating.2.
• Paper.52_Review.0 hasReviewerConfidence ReviewerConfidence.4.
• Paper.52_Review.0 reviews Paper.52.
• Paper.52_Review.0 issuedAt easychair.org.
• Paper.52_Review.0 issuedFor Conference.
• Paper.52_Review.0 releasedBy Conference.
• Paper.52_Review.0 hasContent "In this paper, the author exploited the importance of the geometrical space, hyperbolic space, for the Knowledge Base Completion. They showed that the lagging performance of translational models compared to the bilinear ones is not an intrinsic characteristic of them but a restriction that can be lifted in the hyperbolic space. Experimental results validated that the right choice of geometrical space is a critical decision for KBC. Positive points: 1) The motivation is clear and the related work is sufficient for their research topic. The authors mainly focus shallow embedding. They discuss the shortcoming of current techniques, e.g., RESCAL and TransE and proposed their model based on the benefit of hyperbolic space. The motivation is clear. 2) The paper is well written and happy to follow. The background of some concepts i.e., Hyperbolic Space, are well introduced in the paper. Some Lemmas are also shown to strength their model. And the problem is clear and experimental results do answer their research question. 3) The code and its software document is available for reproducibility. Negative points: 1) The time/space complexity is not provided, which is very important for large-scale dataset. Current bilinear model, like RESCAL, actually scale very well for large dataset. The proposed HyperKG involve some Riemannian gradient. It is unclear how efficiency of the HyperKG. Some complexity will convince the readers. 2) The dataset of WD and WD++ is quite small. Not sure if such small datasets have statistical significance. Some large dataset, e.g., dataset in recommender system area, can be introduced in the experiments. In summary, the overall idea of introducing geometrical spaces for Knowledge Base Completion. The code and its software document is available for reproducibility. I vote for acceptance at this time. =============================== After Rebuttal =============== The authors answer my question about the time and space complexity of HyperKG, which is important. I suggest the authors also add one subsection to discuss time and space complexity in the original paper. The dataset is still an issue by using randomization tests. The auhtors point out that "recent studies have notated many KB relations have very few facts". I keep my original score since the authors answer my questions."".
• Dimitar_Dimitrov type Person.
• Dimitar_Dimitrov name "Dimitar Dimitrov".
• Dimitar_Dimitrov label "Dimitar Dimitrov".
• Dimitar_Dimitrov holdsRole Paper.52_Review.1_Reviewer.
• Dimitar_Dimitrov holdsRole Paper.80_Review.0_Reviewer.
• Dimitar_Dimitrov mbox mailto:Dimitar.Dimitrov@gesis.org.
• Paper.52_Review.1_Reviewer type RoleDuringEvent.
• Paper.52_Review.1_Reviewer label "Dimitar Dimitrov, Reviewer for Paper 52".
• Paper.52_Review.1_Reviewer withRole ReviewerRole.
• Paper.52_Review.1_Reviewer withRole NonAnonymousReviewerRole.
• Paper.52_Review.1_Reviewer isHeldBy Dimitar_Dimitrov.
• Paper.80_Review.0_Reviewer type RoleDuringEvent.
• Paper.80_Review.0_Reviewer label "Dimitar Dimitrov, Reviewer for Paper 80".
• Paper.80_Review.0_Reviewer withRole ReviewerRole.
• Paper.80_Review.0_Reviewer withRole NonAnonymousReviewerRole.
• Paper.80_Review.0_Reviewer isHeldBy Dimitar_Dimitrov.
• Paper.52_Review.1 type ReviewVersion.
• Paper.52_Review.1 issued "2001-01-26T17:47:00.000Z".
• Paper.52_Review.1 creator Paper.52_Review.1_Reviewer.
• Paper.52_Review.1 hasRating ReviewRating.2.
• Paper.52_Review.1 hasReviewerConfidence ReviewerConfidence.4.
• Paper.52_Review.1 reviews Paper.52.
• Paper.52_Review.1 issuedAt easychair.org.
• Paper.52_Review.1 issuedFor Conference.
• Paper.52_Review.1 releasedBy Conference.
• Paper.52_Review.1 hasContent "----------- Strong Points ----------- -Novel approach. -Theoretic proofs and counterexamples are provided. -Strong evaluation. -Implementation and data available online ----------- Weak Points ----------- -Difficult to find any Summary: The paper addresses the important task of link prediction on knowledge bases(KB) i.e. automatic knowledge base completion (KBC). The presented approach adopts hyperbolic geometry to exploit scale-free structures of KBs in order to learn KB embeddings. The authors focus on a specific type of KB embeddings models, i.e., translational models aiming to model vector translation between entities. The proposed model is also shown to be effective in capturing the logical consistency in the facts induced by the KB embeddings. The paper demonstrates how the performance gap between translational and bilinear model families can be closed. The paper provides counterexamples showing the Kazemi and Pool restrictions do not apply to translational models ie TransE when fact validity is based on implausibility scores below a non-zero threshold. Introduction and Related Work: The introduction as the whole paper is well-written and introduces the problem and its specifics for KBs and how they can be exploited through hyperbolic geometry. The authors did a very good job of narrowing down the problem and scope of the paper while putting in the context of the existing body of work. Preliminaries and Proposed Algorithm: The introduced notation and preliminaries are well-explained. Although I am not an expert on hyperbolic geometry and spaces, I was relatively easy to grasp the idea behind it due to the efforts of the authors to provide a clear and easy to follow the narrative. Experiments and Evaluation: A sound evaluation aimed to highlight the specifics of the proposed model. The evaluation addresses the structural properties of the datasets as well as the novel regularisation scheme introduced due to the usage of the Pioncaré-ball model. Critical Appreciation: Overall, I think this paper presents a sound and dense and valuable contribution to the ESWC community and has to be accepted. The paper addresses limitations in a set of KB models i.e. translational and provides strong empirical evidence for that the performance of the TransE model family is not an intrinsic model property but a shortcoming that can be eliminated by the right choice of the geometric space. Moreover, the paper settles an existing disagreement in the recent body of work on KB embeddings as it provides counterexamples showing that Kazemi and Poole restrictions do not apply to TransE models. The authors also provide a theoretical proof that the relation regions captured by the proposed HyperKG are convex and thus can effectively represent QC rules and consequently are reasoning based on HyperKG embeddings would be logically consistent and deductively closed with respect to ontological rules. Minor comments: Page 7: … In our experiments, we noticed a tendency of the “word” vectors to … Page 8: … have shown that the FTransE … =============================== After Rebuttal =============== I keep my original score."".
• Paper.52_Review.2_Reviewer type RoleDuringEvent.
• Paper.52_Review.2_Reviewer label "Anonymous Reviewer for Paper 52".
• Paper.52_Review.2_Reviewer withRole ReviewerRole.
• Paper.52_Review.2_Reviewer withRole AnonymousReviewerRole.
• Paper.52_Review.2 type ReviewVersion.
• Paper.52_Review.2 issued "2001-01-13T12:39:00.000Z".
• Paper.52_Review.2 creator Paper.52_Review.2_Reviewer.
• Paper.52_Review.2 hasRating ReviewRating..
• Paper.52_Review.2 hasReviewerConfidence ReviewerConfidence.4.
• Paper.52_Review.2 reviews Paper.52.
• Paper.52_Review.2 issuedAt easychair.org.
• Paper.52_Review.2 issuedFor Conference.
• Paper.52_Review.2 releasedBy Conference.
• Paper.52_Review.2 hasContent "The paper investigates the impact of the mathematical nature of the embedding space on the performance of lower dimensional embedding approachs to link prediction. Further, they investigate the possibility to represent certain types of logical rules into hyperbolic space. Knowledge-base embedding is a very active area of research with a high potential impact on semantic web technologies. The paper is therefore potentially relevant for ESWC. Concerning the two contributions claimed by the authors (see above), I however only consider the second one (rule embedding) to be valid. The first contribution: the investigation of the impact of the nature of the embedding space on the performance imho has been superseded by recent work by Ruffinelli et al* that shows that the differences between embedding models proposed so far was mainly due to differences in the training and evaluation protocol and that the older translational approaches do not perform worse than more recent ones if the same training and evaluation protocol is applied. Further, the results reported in this paper are systematically worse than the ones achieved by Ruffinelli et al even with the most outdated models. The ability to include rule-like structures into the embedding space is indeed an interesting result. In its present form, however, the paper only discusses this in a very brief and incomplete way. I therefore vote for rejection *Daniel Ruffinelli, Samuel Broscheit, Rainer Gemulla: You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings. Proceedings of the International Conference on Learning Representations ICLR 2020."".
• Author.53.1 type RoleDuringEvent.
• Author.53.1 label "Ilaria Tiddi, 1st Author for Paper 53".
• Author.53.1 withRole PublishingRole.
• Author.53.1 isHeldBy Ilaria_Tiddi.
• b0_g142 first Author.53.2.
• b0_g142 rest b0_g143.
• Author.53.2 type RoleDuringEvent.
• Author.53.2 label "Daniel Balliet, 2nd Author for Paper 53".
• Author.53.2 withRole PublishingRole.
• Author.53.2 isHeldBy Daniel_Balliet.
• b0_g143 first Author.53.3.
• b0_g143 rest nil.
• Author.53.3 type RoleDuringEvent.
• Author.53.3 label "Annette Ten Teije, 3rd Author for Paper 53".
• Author.53.3 withRole PublishingRole.
• Author.53.3 isHeldBy Annette_Ten_Teije.
• Ilaria_Tiddi type Person.
• Ilaria_Tiddi name "Ilaria Tiddi".
• Ilaria_Tiddi label "Ilaria Tiddi".
• Ilaria_Tiddi holdsRole Author.53.1.
• Daniel_Balliet type Person.
• Daniel_Balliet name "Daniel Balliet".
• Daniel_Balliet label "Daniel Balliet".
• Daniel_Balliet holdsRole Author.53.2.
• Annette_Ten_Teije type Person.
• Annette_Ten_Teije name "Annette Ten Teije".
• Annette_Ten_Teije label "Annette Ten Teije".
• Annette_Ten_Teije holdsRole Author.53.3.
• Daniel_Garijo type Person.
• Daniel_Garijo name "Daniel Garijo".
• Daniel_Garijo label "Daniel Garijo".
• Daniel_Garijo holdsRole Paper.53_Review.0_Reviewer.
• Daniel_Garijo holdsRole Paper.116_Review.0_Reviewer.
• Daniel_Garijo mbox mailto:dgarijov@gmail.com.
• Paper.53_Review.0_Reviewer type RoleDuringEvent.
• Paper.53_Review.0_Reviewer label "Daniel Garijo, Reviewer for Paper 53".
• Paper.53_Review.0_Reviewer withRole ReviewerRole.
• Paper.53_Review.0_Reviewer withRole NonAnonymousReviewerRole.
• Paper.53_Review.0_Reviewer isHeldBy Daniel_Garijo.
• Paper.116_Review.0_Reviewer type RoleDuringEvent.
• Paper.116_Review.0_Reviewer label "Daniel Garijo, Reviewer for Paper 116".
• Paper.116_Review.0_Reviewer withRole ReviewerRole.
• Paper.116_Review.0_Reviewer withRole NonAnonymousReviewerRole.
• Paper.116_Review.0_Reviewer isHeldBy Daniel_Garijo.
• Paper.53_Review.0 type ReviewVersion.
• Paper.53_Review.0 issued "2001-01-26T19:58:00.000Z".

• first
• previous
• next