Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks

Proceedings of the Web Conference 2020

Deng

Sun

et al. 2020

Self Cite

Knowledge Graph Completion (KGC) has been proposed to improve Knowledge Graphs by filling in missing connections via link prediction or relation extraction. One of the main difficulties for KGC is a low resource problem. Previous approaches assume sufficient training triples to learn versatile vectors for entities and relations, or a satisfactory number of labeled sentences to train a competent relation extraction model. However, low resource relations are very common in KGs, and those newly added relations often do not have many known samples for training. In this work, we aim at predicting new facts under a challenging setting where only limited training instances are available. We propose a general framework called Weighted Relation Adversarial Network, which utilizes an adversarial procedure to help adapt knowledge/features learned from high resource relations to different but related low resource relations. Specifically, the framework takes advantage of a relation discriminator to distinguish between samples from different relations, and help learn relation-invariant features more transferable from source relations to target relations. Experimental results show that the proposed approach outperforms previous methods regarding low resource settings for both link prediction and relation extraction.

Section: Related Workmentioning

confidence: 99%

Relation Adversarial Network for Low Resource Knowledge Graph Completion

Proceedings of the Web Conference 2020

Deng

Sun

et al. 2020

Self Cite

“…A pipeline method first extracts entities, then it identifies their relations (Hendrickx et al 2019;Zeng et al 2015). Although pipeline models have achieved great progress (Zhang et al 2018;He et al 2018;Zhang et al 2019aZhang et al , 2020a, they introduce an error propagation problem (Li and Ji 2014), which does harm to the overall performance.…”

Section: Related Work Triple Extractionmentioning

confidence: 99%

Contrastive Triple Extraction with Generative Transformer

Chen

et al. 2020

Preprint

Self Cite

Triple extraction is an essential task in information extraction for natural language processing and knowledge graph construction. In this paper, we revisit the end-to-end triple extraction task for sequence generation. Since generative triple extraction may struggle to capture long-term dependencies and generate unfaithful triples, we introduce a novel model, contrastive triple extraction with a generative transformer. Specifically, we introduce a single shared transformer module for encoder-decoder-based generation. To generate faithful results, we propose a novel triplet contrastive training object. Moreover, We introduce two mechanisms to further improve model performance (i.e., batch-wise dynamic attentionmasking and triple-wise calibration). Experimental results on three datasets (i.e., NYT, WebNLG, and MIE) show that our approach achieves better performance than that of baselines. Our code and datasets will be released after publication.

“…Previous work that is closest to our work is the task of entity recommendation. Entity recommendation can be categorized into the following two categories: First, for query assistance for knowledge graphs [16,17], GQBE [9] and Exemplar Queries [13] studied how to retrieve entities from a knowledge base by specifying example entities. For example, the input entity pair {Jerry Yang, Yahoo!}…”

Section: Related Workmentioning

confidence: 99%

Context-aware Deep Model for Entity Recommendation in Search Engine at Alibaba

Jia

Hua

2019

Preprint

Self Cite

Entity recommendation, providing search users with an improved experience via assisting them in finding related entities for a given query, has become an indispensable feature of today's search engines. Existing studies typically only consider the queries with explicit entities. They usually fail to handle complex queries that without entities, such as "what food is good for cold weather", because their models could not infer the underlying meaning of the input text. In this work, we believe that contexts convey valuable evidence that could facilitate the semantic modeling of queries, and take them into consideration for entity recommendation. In order to better model the semantics of queries and entities, we learn the representation of queries and entities jointly with attentive deep neural networks. We evaluate our approach using large-scale, realworld search logs from a widely used commercial Chinese search engine. Our system has been deployed in ShenMa Search Engine 1 and you can fetch it in UC Browser of Alibaba. Results from online A/B test suggest that the impression efficiency of click-through rate increased by 5.1% and page view increased by 5.5%.