Encoding Temporal Information for Time-Aware Link Prediction

Jiang, Tingsong; Li, Tianyu; Ge, Tao; Sha, Lei; Li, Sujian; Chang, Baobao; Sui, Zhifang

doi:10.18653/v1/d16-1260

Cited by 111 publications

(69 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• t-TransE (Jiang et al, 2016): This method uses a temporal ordering of relations to model knowledge evolution in the temporal dimension. They regularize the traditional embedding score function with observed relation ordering with respect to head entities.…”

Section: Methods Comparedmentioning

confidence: 99%

“…Only some handful of methods have been proposed for this purpose. t-TransE (Jiang et al, 2016) learns time aware embedding by learning relation ordering jointly with TransE. They try to inflict temporal order on time-sensitive relations e.g.…”

Section: Related Workmentioning

confidence: 99%

“…Metric Mean Rank Hits@10(%) Mean Rank Hits@10(%) tail head tail head tail head tail head Trans-E (Bordes et al, 2013) 504 2020 4.4 1.2 520 740 11.0 6.0 TransH (Wang et al, 2014) 354 1808 5.8 1.5 423 648 23.7 11.8 HolE (Nickel et al, 2016b) 1828 1953 29.4 13.7 734 808 25.0 12.3 t-TransE (Jiang et al, 2016) Table 2: Mean Rank (lower the better) and Hits@10(higher the better) for different methods for Entity Prediction task.…”

Section: Dataset Yago11k Wikidata12kmentioning

confidence: 99%

“…In spite of its importance, temporally aware KG embeddings is a relatively unexplored area. Recently, a KG embedding method which utilizes temporal scopes was proposed in (Jiang et al, 2016). However, instead of directly incorporating time in the learned embeddings, the method proposed in (Jiang et al, 2016) first learns temporal order among relations (e.g., wasBorIn → wonPrize → diedIn).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding

Dasgupta

Ray

Talukdar

2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

324

101

View full text Add to dashboard Cite

Knowledge Graph (KG) embedding has emerged as an active area of research resulting in the development of several KG embedding methods. Relational facts in KG often show temporal dynamics, e.g., the fact (Cristiano Ronaldo, playsFor, Manchester United) is valid only from 2003 to 2009. Most of the existing KG embedding methods ignore this temporal dimension while learning embeddings of the KG elements. In this paper, we propose HyTE, a temporally aware KG embedding method which explicitly incorporates time in the entity-relation space by associating each timestamp with a corresponding hyperplane. HyTE not only performs KG inference using temporal guidance, but also predicts temporal scopes for relational facts with missing time annotations. Through extensive experimentation on temporal datasets extracted from real-world KGs, we demonstrate the effectiveness of our model over both traditional as well as temporal KG embedding methods.

show abstract

Section: Methods Comparedmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Dataset Yago11k Wikidata12kmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding

Dasgupta

Ray

Talukdar

2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

324

101

View full text Add to dashboard Cite

show abstract

“…They do not consider incorporating other information except for facts. There are many methods on entity textual description [9,10], entity types [11], rules [12] or even temporal information [13]. Methods incorporated textual information like NTN [14] simply initialize the entity representation by averaging the word vectors.…”

Section: Introductionmentioning

confidence: 99%

Learning Entity and Relation Embeddings with Entity Description for Knowledge Graph Completion

Dai¹,

Liang²,

Liu³

et al. 2018

Proceedings of the 2018 2nd International Conference on Artificial Intelligence: Technologies and Applications (ICAITA 2018)

View full text Add to dashboard Cite

Abstract-With the growth of existing knowledge graph, the completion of knowledge graph has become a crucial problem. In this paper, we propose a novel model based on descriptionembodied knowledge representation learning framework, which is able to take advantages of both fact triples and entity description. Specifically, the relation projection is combined with description-embodied representation learning to learn entity and relation embeddings. Convolutional neural network and TransR are adopted to get the description-based and structure-based representation of entity and relation, respectively. We employ FB15K dataset generated from a large knowledge graph freebase, to evaluate the performances of the proposed model. Experimental results show that our proposed model greatly outperforms other existing baseline models.

show abstract

Towards Encoding Time in Text-Based Entity Embeddings

Bianchi

Palmonari

Nozza

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Knowledge Graphs (KG) are widely used abstractions to represent entity-centric knowledge. Approaches to embed entities, entity types and relations represented in the graph into vector spaces -often referred to as KG embeddings -have become increasingly popular for their ability to capture the similarity between entities and support other reasoning tasks. However, representation of time has received little attention in these approaches. In this work, we make a first step to encode time into vector-based entity representations using a text-based KG embedding model named Typed Entity Embeddings (TEEs). In TEEs, each entity is represented by a vector that represents the entity and its type, which is learned from entity mentions found in a text corpus. Inspired by evidence from cognitive sciences and application-oriented concerns, we propose an approach to encode representations of years into TEEs by aggregating the representations of the entities that occur in event-based descriptions of the years. These representations are used to define two time-aware similarity measures to control the implicit effect of time on entity similarity. Experimental results show that the linear order of years obtained using our model is highly correlated with natural time flow and the effectiveness of the time-aware similarity measure proposed to flatten the time effect on entity similarity.

show abstract

Encoding Temporal Information for Time-Aware Link Prediction

Cited by 111 publications

References 16 publications

HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding

HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding

Learning Entity and Relation Embeddings with Entity Description for Knowledge Graph Completion

Towards Encoding Time in Text-Based Entity Embeddings

Contact Info

Product

Resources

About