Related papers: Entity Tracking Improves Cloze-style Reading Compr…

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…

Knowledge is captured in the form of entities and their relationships and stored in knowledge graphs. Knowledge graphs enhance the capabilities of applications in many different areas including Web search, recommendation, and natural…

To enhance the domain-specific capabilities of large language models, continued pre-training on a domain-specific corpus is a prevalent method. Recent work demonstrates that adapting models using reading comprehension data formatted by…

Tracking by detection, the dominant approach for online multi-object tracking, alternates between localization and association steps. As a result, it strongly depends on the quality of instantaneous observations, often failing when objects…

Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully…

Measuring entity relatedness is a fundamental task for many natural language processing and information retrieval applications. Prior work often studies entity relatedness in static settings and an unsupervised manner. However, entities in…

There is a practically unlimited amount of natural language data available. Still, recent work in text comprehension has focused on datasets which are small relative to current computing possibilities. This article is making a case for the…

Continual learning addresses the problem of continuously acquiring and transferring knowledge without catastrophic forgetting of old concepts. While humans achieve continual learning via diverse neurocognitive mechanisms, there is a…

Current state-of-the-art reading comprehension models rely heavily on recurrent neural networks. We explored an entirely different approach to question answering: a convolutional model. By their nature, these convolutional models are fast…

Entity Linking aims to link entity mentions in texts to knowledge bases, and neural models have achieved recent success in this task. However, most existing methods rely on local contexts to resolve entities independently, which may usually…

Robust and efficient learning remains a challenging problem in robotics, in particular with complex visual inputs. Inspired by human attention mechanism, with which we quickly process complex visual scenes and react to changes in the…

Reading comprehension is a challenging task, especially when executed across longer or across multiple evidence documents, where the answer is likely to reoccur. Existing neural architectures typically do not scale to the entire evidence,…

This paper presents a Kernel Entity Salience Model (KESM) that improves text understanding and retrieval by better estimating entity salience (importance) in documents. KESM represents entities by knowledge enriched distributed…

Extracting entities and relations for types of interest from text is important for understanding massive text corpora. Traditionally, systems of entity relation extraction have relied on human-annotated corpora for training and adopted an…

Keeping track of how states of entities change as a text or dialog unfolds is a key prerequisite to discourse understanding. Yet, there have been few systematic investigations into the ability of large language models (LLMs) to track…

The tracking method based on the extreme learning machine (ELM) is efficient and effective. ELM randomly generates input weights and biases in the hidden layer, and then calculates and computes the output weights by reducing the iterative…

Understanding the semantic meaning of content on the web through the lens of entities and concepts has many practical advantages. However, when building large-scale entity extraction systems, practitioners are facing unique challenges…

Cross-modal entity linking refers to the ability to align entities and their attributes across different modalities. While cross-modal entity linking is a fundamental skill needed for real-world applications such as multimodal code…

Broad textual understanding and in-context learning require language models that utilize full document contexts. Due to the implementation challenges associated with directly training long-context models, many methods have been proposed for…

While Neural Machine Translation(NMT) has achieved great progress in recent years, it still suffers from inaccurate translation of entities (e.g., person/organization name, location), due to the lack of entity training instances. When we…