Related papers: Consistency Guided Knowledge Retrieval and Denoisi…

With the rapid progress of large language models (LLMs) and the huge amount of text they generated, it becomes more and more impractical to manually distinguish whether a text is machine-generated. Given the growing use of LLMs in social…

We investigate the usefulness of generative Large Language Models (LLMs) in generating training data for cross-encoder re-rankers in a novel direction: generating synthetic documents instead of synthetic queries. We introduce a new dataset,…

Document-level Relation Extraction (DocRE) involves identifying relations between entities across multiple sentences in a document. Evidence sentences, crucial for precise entity pair relationships identification, enhance focus on essential…

Generative retrieval (GR) reformulates information retrieval (IR) by framing it as the generation of document identifiers (docids), thereby enabling end-to-end optimization and seamless integration with generative language models (LMs).…

Document-level event argument extraction (DEAE) is essential for knowledge acquisition, aiming to extract participants of events from documents . In the zero-shot setting, existing methods employ LLMs to generate synthetic data to address…

In the current digitalization era, capturing and effectively representing knowledge is crucial in most real-world scenarios. In this context, knowledge graphs represent a potent tool for retrieving and organizing a vast amount of…

Automatic Term Extraction (ATE) is a critical component in downstream NLP tasks such as document tagging, ontology construction and patent analysis. Current state-of-the-art methods require expensive human annotation and struggle with…

Semantic matching is a mainstream paradigm of zero-shot relation extraction, which matches a given input with a corresponding label description. The entities in the input should exactly match their hypernyms in the description, while the…

For Relation Extraction (RE), the manual annotation of training data may be prohibitively expensive, since the sentences that contain the target relations in texts can be very scarce and difficult to find. It is therefore beneficial to…

Researchers produce thousands of scholarly documents containing valuable technical knowledge. The community faces the laborious task of reading these documents to identify, extract, and synthesize information. To automate information…

Large Language Models (LLMs) have swiftly emerged as vital resources for different applications in the biomedical and healthcare domains; however, these models encounter issues such as generating inaccurate information or hallucinations.…

Large Language Models (LLMs) have transformed listwise document reranking by enabling global reasoning over candidate sets, yet single models often struggle to balance fine-grained relevance scoring with holistic cross-document analysis. We…

Document-level relation extraction (DocRE) aims to extract relations between entities from unstructured document text. Compared to sentence-level relation extraction, it requires more complex semantic understanding from a broader text…

Zero-shot information extraction (IE) aims to build IE systems from the unannotated text. It is challenging due to involving little human intervention. Challenging but worthwhile, zero-shot IE reduces the time and effort that data labeling…

In table-text open-domain question answering, a retriever system retrieves relevant evidence from tables and text to answer questions. Previous studies in table-text open-domain question answering have two common challenges: firstly, their…

Unstructured data formats account for over 80% of the data currently stored, and extracting value from such formats remains a considerable challenge. In particular, current approaches for managing unstructured documents do not support…

The rapid expansion of publicly-available medical data presents a challenge for clinicians and researchers alike, increasing the gap between the volume of scientific literature and its applications. The steady growth of studies and findings…

The goal of document-level relation extraction (RE) is to identify relations between entities that span multiple sentences. Recently, incomplete labeling in document-level RE has received increasing attention, and some studies have used…

Extracting relations from scientific literature is a fundamental task in biomedical NLP because entities and relations among them drive hypothesis generation and knowledge discovery. As literature grows rapidly, relation extraction (RE) is…

Recognizing entities in texts is a central need in many information-seeking scenarios, and indeed, Named Entity Recognition (NER) is arguably one of the most successful examples of a widely adopted NLP task and corresponding NLP technology.…