Related papers: Jointly Identifying and Fixing Inconsistent Readin…

Multi-task learning (MTL) has been widely used in recommender systems, wherein predicting each type of user feedback on items (e.g, click, purchase) are treated as individual tasks and jointly trained with a unified model. Our key…

Massive knowledge graphs like Wikidata attempt to capture world knowledge about multiple entities. Recent approaches concentrate on automatically enriching these KGs from text. However a lot of information present in the form of natural…

Automatic Keyphrase Extraction involves identifying essential phrases in a document. These keyphrases are crucial in various tasks such as document classification, clustering, recommendation, indexing, searching, summarization, and text…

Question generation (QG) is to generate natural and grammatical questions that can be answered by a specific answer for a given context. Previous sequence-to-sequence models suffer from a problem that asking high-quality questions requires…

Clinical studies often require understanding elements of a patient's narrative that exist only in free text clinical notes. To transform notes into structured data for downstream use, these elements are commonly extracted and normalized to…

Definition bias is a negative phenomenon that can mislead models. Definition bias in information extraction appears not only across datasets from different domains but also within datasets sharing the same domain. We identify two types of…

Dynamic relation repair aims to efficiently validate and repair the instances for knowledge graph enhancement (KGE), where KGE captures missing relations from unstructured data and leads to noisy facts to the knowledge graph. With the…

Fine-Grained Change Detection and Regression Analysis are essential in many applications of ArtificialIntelligence. In practice, this task is often challenging owing to the lack of reliable ground truth information andcomplexity arising…

This paper investigates various Transformer architectures on the WikiReading Information Extraction and Machine Reading Comprehension dataset. The proposed dual-source model outperforms the current state-of-the-art by a large margin. Next,…

Recent studies have revealed that reading comprehension (RC) systems learn to exploit annotation artifacts and other biases in current datasets. This prevents the community from reliably measuring the progress of RC systems. To address this…

In contrast to large text corpora, knowledge graphs (KG) provide dense and structured representations of factual information. This makes them attractive for systems that supplement or ground the knowledge found in pre-trained language…

In this paper, we introduce KAG-Thinker, which upgrade KAG to a multi-turn interactive thinking and deep reasoning framework powered by a dedicated parameter-light large language model (LLM). Our approach constructs a structured thinking…

Knowledge Base Question Answering (KBQA) aims to answer natural language questions with the help of an external knowledge base. The core idea is to find the link between the internal knowledge behind questions and known triples of the…

Relational databases are often fragmented across organizations, creating data silos that hinder distributed data management and mining. Collaborative learning (CL) -- techniques that enable multiple parties to train models jointly without…

Extracting entities and relations from unstructured text has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in identifying overlapping relations with shared entities. Prior works show…

Retrieval-Augmented Generation (RAG) improves large language models by retrieving external knowledge, often truncated into smaller chunks due to the input context window, which leads to information loss, resulting in response hallucinations…

Knowledge Graphs (KGs), and Linked Open Data in particular, enable the generation and exchange of more and more information on the Web. In order to use and reuse these data properly, the presence of accountability information is essential.…

The knowledge base in a retrieval-augmented generation (RAG) system is typically assembled once and never revised, even though the facts a query requires are often fragmented across documents and buried in irrelevant content. We argue that…

Knowledge Graphs (KGs) store structured factual knowledge by linking entities through relationships, crucial for many applications. These applications depend on the KG's factual accuracy, so verifying facts is essential, yet challenging.…

While increasingly complex approaches to question answering (QA) have been proposed, the true gain of these systems, particularly with respect to their expensive training requirements, can be inflated when they are not compared to adequate…