Entity-GCN model answers multi-document questions by reasoning across documents.
problem Answering questions based on multiple documents and cross-document relations.
method Graph Convolutional Networks (GCNs) applied to a graph of mentions and their relations.
result Achieves state-of-the-art results on WikiHop dataset.
mGENRE improves multilingual entity linking with autoregressive sequence prediction.
problem Multilingual Entity Linking (MEL) task of resolving language-specific mentions to a multilingual Knowledge Base.
method Autoregressive sequence-to-sequence system that cross-encodes mention strings and entity names.
result Over 50% improvement in average accuracy in zero-shot settings.
A new system learns entity representations to improve local entity disambiguation.
problem Local entity disambiguation in text.
method Entity-ELMo (E-ELMo) approach for contextual entity representation.
result Outperforms state-of-the-art models by 0.5% on AIDA test-b.
Model learns to discover and disambiguate entities and relations in text streams.
problem Learning to follow and resolve mentions in a continuous text stream.
method End-to-end trainable memory network for online, one-shot learning.
result Improves disambiguation and discovery skills with minimal supervision.
Paper proposes a method to predict EL difficulty using consensus-based labels.
problem Challenges in automatically identifying and resolving ambiguous entity mentions.
method Consensus-based method to generate difficulty labels, supervised classification with various features.
result EL difficulty can be accurately predicted with high accuracy.
Improves biomedical entity linking with latent type modeling.
problem Lack of fine-grained type information for entity disambiguation.
method Jointly models entity disambiguation and latent type learning without direct supervision.
result Significant performance improvements over state-of-the-art techniques.
Efficient autoregressive entity linking with correction for faster, more accurate results.
problem High computational cost and non-parallelizable decoding in autoregressive entity linking.
method Parallelizes autoregressive linking across all mentions, uses a shallow decoder, and adds a discriminative correction term.
result 70 times faster and more accurate than previous methods, outperforming state-of-the-art approaches.
Paper tackles noisy relation classification by sentence-level reinforcement learning.
problem Noisy distant supervision in relation classification.
method Two-module approach: instance selector using reinforcement learning, relation classifier making sentence-level predictions.
result Jointly trained model optimizes instance selection and relation classification, effectively handling noisy data.
Paper proposes a reinforcement learning framework for distant supervision of question parsing.
problem Lack of gold annotations for parsing in QA datasets.
method Reinforcement learning framework based on formal queries to learn mentions of entities and relations.
result Significant improvement in entity and relation linking compared to state of the art.
We present an LDA approach to entity disambiguation. Each topic is associated with a Wikipedia article and topics generate either content words or entity mentions. Training such models is challenging because of the topic and vocabulary size, both in the millions. We tackle these problems using a novel distributed infer…
Paper proposes a novel model to improve n-ary cross-sentence relation extraction by addressing noisy data and non-consecutive sentences.
problem Noisy labeled data and non-consecutive sentences in n-ary cross-sentence relation extraction.
method Two-level agent reinforcement learning model and hybrid attention mechanism/PCNN approach.
result The model reduces the impact of noisy data and achieves better performance.
Improved NER in biomedical literature using weakly-supervised augmentation.
problem Challenging NER in scientific literature, especially for biomedical entities.
method Weakly-supervised data augmentation with a reference set.
result Iterative model retraining improves NER performance significantly.
Paper improves relation extraction in clinical texts with limited data.
problem Relation extraction in narrow knowledge domains with scarce annotated data.
method Introduces a bag-of-concepts (BoC) model and compares it with window-bounded co-occurrence (WBC).
result BoC model outperforms baseline and other complex methods on small dataset.
We propose Macau, a powerful and flexible Bayesian factorization method for heterogeneous data. Our model can factorize any set of entities and relations that can be represented by a relational model, including tensors and also multiple relations for each entity. Macau can also incorporate side information, specificall…
A model for entity relatedness considering time and context.
problem Time and context influence entity relatedness.
method Flexible model using time-aware and corpus-specific word embeddings.
result The model generates accurate entity relatedness lists.
Sparse hypergraph neural networks improve reasoning in large knowledge graphs.
problem Reasoning about relationships in large, real-world domains using sparse and local inferences.
method Sparse and local hypergraph neural networks (SpaLoc) exploiting relational inferences that are usually local and sparse.
result State-of-the-art performance on real-world knowledge graph reasoning benchmarks.
Proposes a new method for predicting missing relations in knowledge graphs.
problem Predicting missing relations between entities in knowledge graphs.
method Relational message passing method considering only edge features without entity IDs.
result PathCon method outperforms state-of-the-art methods significantly.
CURE extracts relations without supervision by clustering similar entity pairs.
problem Extracting relations unsupervised without considering sentence correlations.
method CURE uses Encoder-Decoder architecture for self-supervised learning and clustering similar relations.
result CURE outperforms state-of-the-art models on NYT and UNPC datasets.
TransGCN combines GCNs with transformation assumptions for better link prediction in KGs.
problem Link prediction in knowledge graphs for understanding graph structure.
method Unified GCN framework with simultaneous learning of entity and relation embeddings, using transformation assumptions.
result TransGCN outperforms state-of-the-art models on FB15K-237 and WN18RR.
New methods predict links in hypergraphs with multiple entities.
problem Link prediction in knowledge hypergraphs with non-binary relations.
method Introduce HSimplE and HypE embedding-based methods for hypergraphs.
result Proposed methods outperform baselines in hypergraph prediction.
Knowledge graphs have emerged as an important model for studying complex multi-relational data. This has given rise to the construction of numerous large scale but incomplete knowledge graphs encoding information extracted from various resources. An effective and scalable approach to jointly learn over multiple graphs …
A multi-task learning model for slot tagging in biomedical domains.
problem Limited labeled data, memory constraints, and domain-specific slot types.
method Multi-task learning using deep bidirectional transformers.
result Outperforms previous state-of-the-art systems in efficiency and effectiveness.
Neural model for dynamic entity relatedness ranking.
problem Dynamic entity relationships in real-world applications.
method A neural network-based approach leveraging collective attention as supervision.
result Our model achieves better results than competitive baselines on large-scale datasets.
In many supervised learning tasks, the entities to be labeled are related to each other in complex ways and their labels are not independent. For example, in hypertext classification, the labels of linked pages are highly correlated. A standard approach is to classify each entity independently, ignoring the correlation…
Paper uses knowledge bases to discover new relations from text.
problem Discover new relations from text without annotated data.
method Construct constraints based on knowledge base embeddings and incorporate into variational auto-encoder for relation discovery.
result Improves relation discovery performance significantly.
EERN uses deep learning for relational databases, outperforming other methods.
problem Deep learning for relational databases.
method Equivariant Entity-Relationship Network (EERN) using MLP equivariant to Entity-Relationship model symmetries.
result EERN outperforms other methods in synthetic and real-data experiments.
GraIL predicts relations by reasoning over subgraphs, outperforming embeddings.
problem Relation prediction in knowledge graphs using latent representations is limited.
method Graph neural network with inductive bias to learn entity-independent relational semantics.
result GraIL outperforms existing rule-induction baselines in the inductive setting.
Quaternion embeddings model entities and relations in knowledge graphs.
problem Modeling latent inter-dependencies and expressive rotations in knowledge graphs.
method Quaternion-valued embeddings and rotations in hypercomplex space.
result Quaternion embeddings achieve state-of-the-art performance on knowledge graph benchmarks.
GenIE extracts structured text with fewer errors and more entities.
problem Closed information extraction with errors and limited entities.
method End-to-end autoregressive generation with bi-level constraints.
result State-of-the-art performance on closed information extraction.
MedCAT extracts valuable medical information from unstructured text.
problem Extracting structured information from unstructured biomedical documents.
method Unsupervised machine learning for disambiguation of entities.
result Improved entity detection and linking compared to existing tools.
Discovering causal relations is fundamental to reasoning and intelligence. In particular, observational causal discovery algorithms estimate the cause-effect relation between two random entities X and Y, given n samples from P(X,Y). In this paper, we develop a framework to estimate the cause-effect relation bet…
The article proposes an expert system for detection, and subsequent investigation, of groups of collaborating automobile insurance fraudsters. The system is described and examined in great detail, several technical difficulties in detecting fraud are also considered, for it to be applicable in practice. Opposed to many…
Proposes OpenKI for better web-scale knowledge extraction and alignment.
problem Combining OpenIE and KB for web-scale knowledge extraction and alignment.
method Instance-level inference using neighborhood information from KB and OpenIE extractions, with attention mechanisms.
result Significantly improves performance on OpenIE extractions and semi-structured data.
Often, more time is spent on finding a model that works well, rather than tuning the model and working directly with the dataset. Our research began as an attempt to improve upon a simple Recurrent Neural Network for answering "simple" first-order questions (QA-RNN), developed by Ferhan Ture and Oliver Jojic, from Comc…
Improved KG completion on large datasets using entity-relation pair occurrences.
problem Performance bottleneck in training large-scale KGs due to memory constraints.
method Construct a joint learning model using pairwise occurrence information and increase negative sampling quality.
result Significant improvement in performance, especially with low batch size and negative examples.
Attention-based embeddings improve relation prediction in incomplete KGs.
problem Incomplete or missing relations in knowledge graphs.
method Attention-based feature embedding that captures entity and relation features in local neighborhoods.
result Marked performance gains on all datasets compared to state-of-the-art methods.
Method quantifies relation similarity using entity pair distributions.
problem Measuring similarity between relations in knowledge bases.
method Simple neural network parameterizes conditional probability distributions over entity pairs. Sampling-based approximation for similarity computation.
result Approximation correlates with human judgments and detects redundant relations.
HAKE embeds entities in polar coordinates to model semantic hierarchies in knowledge graphs.
problem Lack of modeling semantic hierarchies in knowledge graph embeddings.
method HAKE embeds entities in a polar coordinate system, where the radial coordinate represents hierarchy levels and the angular coordinate distinguishes entities at the same level.
result HAKE significantly outperforms existing methods on link prediction tasks in knowledge graphs.
GEMRank embeds users and items using co-occurrence relations for better collaborative filtering.
problem Lack of textual data for entity embedding in recommender systems.
method Uses profile co-occurrence for entity relations and factorization for embedding. Feeds embeddings into a neural network for predictions.
result Significantly outperforms baseline algorithms in various data sets.
GENRE retrieves entities autoregressively, improving efficiency and accuracy.
problem Retrieving entities from queries efficiently and accurately.
method Autoregressive generation of entity names, reducing memory footprint and improving context encoding.
result Significantly improved performance on entity disambiguation, linking, and retrieval tasks.
Knowledge graphs enable a wide variety of applications, including question answering and information retrieval. Despite the great effort invested in their creation and maintenance, even the largest (e.g., Yago, DBPedia or Wikidata) remain incomplete. We introduce Relational Graph Convolutional Networks (R-GCNs) and app…
RotatE embeds knowledge graphs using rotations in complex space for better link prediction.
problem Predicting missing links in knowledge graphs.
method RotatE models relations as rotations in complex vector space, using self-adversarial negative sampling.
result RotatE models and infers various relation patterns, outperforming existing models.
Knowledge graphs are a versatile framework to encode richly structured data relationships, but it can be challenging to combine these graphs with unstructured data. Methods for retrofitting pre-trained entity representations to the structure of a knowledge graph typically assume that entities are embedded in a connecte…
Flexible embedding framework for diverse data types.
problem Limited applicability of existing embedding learning methods.
method A flexible framework using entity-relation-matrices and sampling mechanism.
result Framework outperforms state-of-the-art approaches in various tasks.
MKBE embeds multimodal data for knowledge base completion.
problem Missing multimodal data in knowledge bases.
method Multimodal encoders and decoders for text, images, and numerical values.
result State-of-the-art link prediction with 5-7% improvement.
Improved RL for knowledge graph reasoning with entity types.
problem Challenges in path-based relational reasoning over knowledge graphs.
method Type-enhanced RL agent using GNN for neighborhood information.
result Outperforms state-of-the-art RL methods and discovers novel paths.
The study categorizes knowledge graph relations and explains their embedding representations.
problem Understanding how knowledge graph relation representations capture semantic information.
method Categorizing knowledge graph relations into three types and deriving explicit requirements for their representations.
result Empirical properties of relation representations and the performance of methods are justified by the analysis.
A novel geometric algebra-based KG embedding framework improves link prediction.
problem KG embedding to model entities and relations in a low-dimensional space.
method Utilizes multivector representations and geometric product in geometric algebra.
result Outperforms state-of-the-art models in link prediction experiments.