Message Passing for Complex Question Answering over Knowledge Graphs

Vakulenko, Svitlana; García, Javier David Fernández; Polleres, Axel; Rijke, Maarten de; Cochez, Michael

doi:10.1145/3357384.3358026

Cited by 60 publications

(73 citation statements)

References 40 publications

(84 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our model outperforms QAmp [15] and WQAqua [3] 5 . We did not compare our model with [8], because their work does not consider entity detection and linking steps.…”

Section: Results Of the Kbqa System On Lc-quad10 Datasetmentioning

confidence: 94%

“…The model of [15] uses message passing for query ranking, which means propagation of confidence scores from candidate entities and relations to the adjacent nodes in the extracted subgraph. The model also includes entity and relation extraction steps.…”

Section: Related Workmentioning

confidence: 99%

“…Question answering systems can use two kinds of sources to find an answer: unstructured text corpora [11], [10], and knowledge bases (KB). KBs are an important source of information which integrates information from different sources [15]. Question answering models using KBs are compact and interpretable [16].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sparql Query Generation for Complex Question Answering With Bert and Bilstm-Based Model

Evseev¹,

Архипов²

2020

Computational Linguistics and Intellectual Technologies

View full text Add to dashboard Cite

In this paper we describe question answering system for answering of complex questions over Wikidata knowledge base. Unlike simple questions, which require extraction of single fact from the knowledge base, complex questions are based on more than one triplet and need logical or comparative reasoning. The proposed question answering system translates a natural language question into a query in SPARQL language, execution of which gives an answer. The system includes the models which define the SPARQL query template corresponding to the question and then fill the slots in the template with entities, relations and numerical values. For entity detection we use BERTbased sequence labelling model. Ranking of candidate relations is performed in two steps with BiLSTM and BERT-based models. The proposed models are the first solution for LC-QUAD2.0 dataset. The system is capable of answering complex questions which involve comparative or boolean reasoning.

show abstract

“…Our model outperforms QAmp [15] and WQAqua [3] 5 . We did not compare our model with [8], because their work does not consider entity detection and linking steps.…”

Section: Results Of the Kbqa System On Lc-quad10 Datasetmentioning

confidence: 94%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Sparql Query Generation for Complex Question Answering With Bert and Bilstm-Based Model

Evseev¹,

Архипов²

2020

Computational Linguistics and Intellectual Technologies

View full text Add to dashboard Cite

show abstract

“…Knowledge graphs provide a structured way to represent information in the form of entities and relations between them [12]. They have become central to a variety of tasks in the Web, including information retrieval [6,13], question answering [19,43], and information extraction [4,14,26]. Many of these tasks can benefit from distributed representations of entities and relations, also known as embeddings.…”

Section: Introductionmentioning

confidence: 99%

Inductive Entity Representations from Text via Link Prediction

Daza

Cochez

Groth

2021

Proceedings of the Web Conference 2021

Self Cite

View full text Add to dashboard Cite

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. To address this problem, there is a large amount of work that proposes using machine learning to complete these graphs by predicting new links. 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.Therefore, 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. CCS CONCEPTS• Computing methodologies → Statistical relational learning; • Information systems → Information retrieval.This paper is published under the Creative Commons Attribution 4.0 International (CC-BY 4.0) license. Authors reserve their rights to disseminate the work on their personal and corporate Web sites with the appropriate attribution.

show abstract

“…Relation extraction is a classification task to find a relation among entities in unstructured texts. It can be applied to many natural language processing tasks, which require structured information, such as knowledge base construction [4,9,23,34], question answering [3,7,38,43], and recommender systems [2,6,16,42].…”

Section: Introductionmentioning

confidence: 99%

Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation

Lee

Seo

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

This paper presents an efficient method of extracting n-ary relations from multiple sentences which is called Entity-path and Discourse relation-centric Relation Extractor (EDCRE). Unlike previous approaches, the proposed method focuses on an entity link, which consists of dependency edges between entities, and discourse relations between sentences. Specifically, the proposed model consists of two main sub-models. The first one encodes sentences with a higher weight on the entity link while considering the other edges with an attention mechanism. To consider various latent discourse relations between sentences, the second sub-model encodes discourse relations between adjacent sentences considering the contents of each sentence. Experiment results on the cross-sentence relation extraction dataset, PubMed, and the document-level relation extraction dataset, DocRED, show that the proposed model outperforms state-of-the-art methods of extracting relations across sentences. Furthermore, ablation study proves that both the two main sub-models have noticeable effect on the relation extraction task. CCS CONCEPTS • Computing methodologies → Information extraction.

show abstract

Message Passing for Complex Question Answering over Knowledge Graphs

Cited by 60 publications

References 40 publications

Sparql Query Generation for Complex Question Answering With Bert and Bilstm-Based Model

Sparql Query Generation for Complex Question Answering With Bert and Bilstm-Based Model

Inductive Entity Representations from Text via Link Prediction

Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation

Contact Info

Product

Resources

About