相关论文: Empirical Evaluation of Pretraining Strategies for…

The growth of cross-lingual pre-trained models has enabled NLP tools to rapidly generalize to new languages. While these models have been applied to tasks involving entities, their ability to explicitly predict typological features of these…

Forms are a widespread type of template-based document used in a great variety of fields including, among others, administration, medicine, finance, or insurance. The automatic extraction of the information included in these documents is…

As entity type systems become richer and more fine-grained, we expect the number of types assigned to a given entity to increase. However, most fine-grained typing work has focused on datasets that exhibit a low degree of type multiplicity.…

Links are a fundamental part of information networks, turning isolated pieces of knowledge into a network of information that is much richer than the sum of its parts. However, adding a new link to the network is not trivial: it requires…

This thesis investigates how natural language understanding and generation with transformer models can benefit from grounding the models with knowledge representations and addresses the following key research questions: (i) Can knowledge of…

Entity linking is an indispensable operation of populating knowledge repositories for information extraction. It studies on aligning a textual entity mention to its corresponding disambiguated entry in a knowledge repository. In this paper,…

In many information extraction applications, entity linking (EL) has emerged as a crucial task that allows leveraging information about named entities from a knowledge base. In this paper, we address the task of multimodal entity linking…

Existing state of the art neural entity linking models employ attention-based bag-of-words context model and pre-trained entity embeddings bootstrapped from word embeddings to assess topic level context compatibility. However, the latent…

A key challenge in entity linking is making effective use of contextual information to disambiguate mentions that might refer to different entities in different contexts. We present a model that uses convolutional neural networks to capture…

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,…

Entity Linking is the task of matching a mention to an entity in a given knowledge base (KB). It contributes to annotating a massive amount of documents existing on the Web to harness new facts about their matched entities. However,…

Understanding human language often necessitates understanding entities and their place in a taxonomy of knowledge -- their types. Previous methods to learn entity types rely on training classifiers on datasets with coarse, noisy, and…

Rich entity representations are useful for a wide class of problems involving entities. Despite their importance, there is no standardized benchmark that evaluates the overall quality of entity representations. In this work, we propose…

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…

Recent studies have shown that multilingual pretrained language models can be effectively improved with cross-lingual alignment information from Wikipedia entities. However, existing methods only exploit entity information in pretraining…

Pre-trained models such as BERT are widely used in NLP tasks and are fine-tuned to improve the performance of various NLP tasks consistently. Nevertheless, the fine-tuned BERT model trained on our protocol corpus still has a weak…

Entity linking (EL) in conversations faces notable challenges in practical applications, primarily due to the scarcity of entity-annotated conversational datasets and sparse knowledge bases (KB) containing domain-specific, long-tail…

The wide applicability of pretrained transformer models (PTMs) for natural language tasks is well demonstrated, but their ability to comprehend short phrases of text is less explored. To this end, we evaluate different PTMs from the lens of…

We introduce ReFinED, an efficient end-to-end entity linking model which uses fine-grained entity types and entity descriptions to perform linking. The model performs mention detection, fine-grained entity typing, and entity disambiguation…

This paper describes the system proposed by Sabanc{\i} University Natural Language Processing Group in the SemEval-2022 MultiCoNER task. We developed an unsupervised entity linking pipeline that detects potential entity mentions with the…