Related papers: Unsupervised Context Retrieval for Long-tail Entit…

In human-human conversations, Context Tracking deals with identifying important entities and keeping track of their properties and relationships. This is a challenging problem that encompasses several subtasks such as slot tagging,…

Textual information is considered as significant supplement to knowledge representation learning (KRL). There are two main challenges for constructing knowledge representations from plain texts: (1) How to take full advantages of sequential…

Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs). URE methods can be categorised into generative and discriminative approaches,…

Benchmark datasets for visual recognition assume that data is uniformly distributed, while real-world datasets obey long-tailed distribution. Current approaches handle the long-tailed problem to transform the long-tailed dataset to uniform…

Entity state tracking is a necessary component of world modeling that requires maintaining coherent representations of entities over time. Previous work has benchmarked entity tracking performance in purely text-based tasks. We introduce…

Entity Alignment (EA) aims to find the equivalent entities between two Knowledge Graphs (KGs). Existing methods usually encode the triples of entities as embeddings and learn to align the embeddings, which prevents the direct interaction…

Extending context windows (i.e., Long Context, LC) and using retrievers to selectively access relevant information (i.e., Retrieval-Augmented Generation, RAG) are the two main strategies to enable LLMs to incorporate extremely long external…

Structured representations of entity names are useful for many entity-related tasks such as entity normalization and variant generation. Learning the implicit structured representations of entity names without context and external knowledge…

We propose an unsupervised method for sentence summarization using only language modeling. The approach employs two language models, one that is generic (i.e. pretrained), and the other that is specific to the target domain. We show that by…

Conventional entity typing approaches are based on independent classification paradigms, which make them difficult to recognize inter-dependent, long-tailed and fine-grained entity types. In this paper, we argue that the implicitly entailed…

The large volume of text in electronic healthcare records often remains underused due to a lack of methodologies to extract interpretable content. Here we present an unsupervised framework for the analysis of free text that combines…

Long-context modeling capabilities are important for large language models (LLMs) in various applications. However, directly training LLMs with long context windows is insufficient to enhance this capability since some training samples do…

Language has become a prominent modality in computer vision with the rise of LLMs. Despite supporting long context-lengths, their effectiveness in handling long-term information gradually declines with input length. This becomes critical,…

In this work, we present a dual learning approach for unsupervised text to path and path to text transfers in Commonsense Knowledge Bases (KBs). We investigate the impact of weak supervision by creating a weakly supervised dataset and show…

In document-level relation extraction, entities may appear multiple times in a document, and their relationships can shift from one context to another. Accurate prediction of the relationship between two entities across an entire document…

Insightful findings in political science often require researchers to analyze documents of a certain subject or type, yet these documents are usually contained in large corpora that do not distinguish between pertinent and non-pertinent…

Citation texts are sometimes not very informative or in some cases inaccurate by themselves; they need the appropriate context from the referenced paper to reflect its exact contributions. To address this problem, we propose an unsupervised…

Unsupervised learning of low-dimensional, semantic representations of words and entities has recently gained attention. In this paper we describe the Semantic Entity Retrieval Toolkit (SERT) that provides implementations of our previously…

As the context limits of Large Language Models (LLMs) increase, the range of possible applications and downstream functions broadens. In many real-world tasks, decisions depend on details scattered across collections of often disparate…

Large Language Models (LLMs) face information overload when handling long contexts, particularly in Retrieval-Augmented Generation (RAG) where extensive supporting documents often introduce redundant content. This issue not only weakens…