相关论文: CEVO: Comprehensive EVent Ontology Enhancing Cogni…

We present the Multilingual Entity Linking of Occupations (MELO) Benchmark, a new collection of 48 datasets for evaluating the linking of entity mentions in 21 languages to the ESCO Occupations multilingual taxonomy. MELO was built using…

Community annotation of biological entities with concepts from multiple bio-ontologies has created large and growing repositories of ontology-based annotation data with embedded implicit relationships among orthogonal ontologies.…

Named entity recognition (NER) is frequently addressed as a sequence classification task where each input consists of one sentence of text. It is nevertheless clear that useful information for the task can often be found outside of the…

Fine-grained entity typing (FET), which assigns entities in text with context-sensitive, fine-grained semantic types, is a basic but important task for knowledge extraction from unstructured text. FET has been studied extensively in natural…

Ontologies of research areas have been proven to be useful in many application for analysing and making sense of scholarly data. In this chapter, we present the Computer Science Ontology (CSO), which is the largest ontology of research…

Ontology embeddings map classes, roles, and individuals in ontologies into $\mathbb{R}^n$, and within $\mathbb{R}^n$ similarity between entities can be computed or new axioms inferred. For ontologies in the Description Logic…

Online encyclopedia such as Wikipedia has become one of the best sources of knowledge. Much effort has been devoted to expanding and enriching the structured data by automatic information extraction from unstructured text in Wikipedia.…

Every culture and language is unique. Our work expressly focuses on the uniqueness of culture and language in relation to human affect, specifically sentiment and emotion semantics, and how they manifest in social multimedia. We develop…

Concept-based explainable approaches have emerged as a promising method in explainable AI because they can interpret models in a way that aligns with human reasoning. However, their adaption in the text domain remains limited. Most existing…

Contextual word representations, typically trained on unstructured, unlabeled text, do not contain any explicit grounding to real world entities and are often unable to remember facts about those entities. We propose a general method to…

Entity Linking involves detecting and linking entity mentions in natural language texts to a knowledge graph. Traditional methods use a two-step process with separate models for entity recognition and disambiguation, which can be…

We present a novel way of injecting factual knowledge about entities into the pretrained BERT model (Devlin et al., 2019): We align Wikipedia2Vec entity vectors (Yamada et al., 2016) with BERT's native wordpiece vector space and use the…

Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities using length-limited encoders. However, these methods often…

Employers collect a large number of resumes from job portals, or from the company's own website. These documents are used for an automated selection of candidates satisfying the requirements and therefore reducing recruitment costs. Various…

Structured documents--tables paired with captions, figures with explanations, equations with the paragraphs that interpret them--are routinely fragmented when indexed for retrieval. Element-level indexing treats every parsed element as an…

In this work, we aim at equipping pre-trained language models with structured knowledge. We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models,…

In this work we leverage recent advances in context-sensitive language models to improve the task of query expansion. Contextualized word representation models, such as ELMo and BERT, are rapidly replacing static embedding models. We…

Modern entity linking systems rely on large collections of documents specifically annotated for the task (e.g., AIDA CoNLL). In contrast, we propose an approach which exploits only naturally occurring information: unlabeled documents and…

The diverse relationships among real-world events, including coreference, temporal, causal, and subevent relations, are fundamental to understanding natural languages. However, two drawbacks of existing datasets limit event relation…

Deep learning models, while effective and versatile, are becoming increasingly complex, often including multiple overlapping networks of arbitrary depths, multiple objectives and non-intuitive training methodologies. This makes it…