相关论文: AceParse: A Comprehensive Dataset with Diverse Str…
The exponential growth of scientific literature requires effective management and extraction of valuable insights. While existing scientific search engines excel at delivering search results based on relational databases, they often neglect…
Language models for scientific tasks are trained on text from scientific publications, most distributed as PDFs that require parsing. PDF parsing approaches range from inexpensive heuristics (for simple documents) to computationally…
Effective scientific communication depends on accurate citations that validate sources and guide readers to supporting evidence. Yet academic literature faces mounting challenges: semantic citation errors that misrepresent sources,…
As language models become capable of processing increasingly long and complex texts, there has been growing interest in their application within computational literary studies. However, evaluating the usefulness of these models for such…
In this paper, we propose a new system called ASET that allows users to perform structured explorations of text collections in an ad-hoc manner. The main idea of ASET is to use a new two-phase approach that first extracts a superset of…
Identifying suitable datasets for a research question remains challenging because existing dataset search engines rely heavily on metadata quality and keyword overlap, which often fail to capture the semantic intent of scientific…
The rapid expansion of scientific literature in computer science presents challenges in tracking research trends and extracting key insights. Existing datasets provide metadata but lack structured summaries that capture core contributions…
Identifying the intent of a citation in scientific papers (e.g., background information, use of methods, comparing results) is critical for machine reading of individual publications and automated analysis of the scientific literature. We…
In the contemporary information era, significantly accelerated by the advent of Large-scale Language Models, the proliferation of scientific literature is reaching unprecedented levels. Researchers urgently require efficient tools for…
Efficiently navigating and understanding academic papers is crucial for scientific progress. Traditional linear formats like PDF and HTML can cause cognitive overload and obscure a paper's hierarchical structure, making it difficult to…
The number of academic papers being published is increasing exponentially in recent years, and recommending adequate citations to assist researchers in writing papers is a non-trivial task. Conventional approaches may not be optimal, as the…
Large-scale data sets on scholarly publications are the basis for a variety of bibliometric analyses and natural language processing (NLP) applications. Especially data sets derived from publication's full-text have recently gained…
Most existing knowledge graphs (KGs) in academic domains suffer from problems of insufficient multi-relational information, name ambiguity and improper data format for large-scale machine processing. In this paper, we present AceKG, a new…
Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine…
Scientific literature is typically dense, requiring significant background knowledge and deep comprehension for effective engagement. We introduce SciDQA, a new dataset for reading comprehension that challenges LLMs for a deep understanding…
We present ACADATA, a high-quality parallel dataset for academic translation, that consists of two subsets: ACAD-TRAIN, which contains approximately 1.5 million author-generated paragraph pairs across 96 language directions and ACAD-BENCH,…
With the enrichment of literature resources, researchers are facing the growing problem of information explosion and knowledge overload. To help scholars retrieve literature and acquire knowledge successfully, clarifying the semantic…
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…
In the domain of Document AI, parsing semi-structured image form is a crucial Key Information Extraction (KIE) task. The advent of pre-trained multimodal models significantly empowers Document AI frameworks to extract key information from…
In this paper, we propose a method to automatically classify AI-related documents from large-scale literature databases, leading to the creation of an AI-related literature dataset, named DeepDiveAI. The dataset construction approach…