相关论文: Generating Multilingual Documents from a Knowledge…

Generating natural and informative texts has been a long-standing problem in NLP. Much effort has been dedicated into incorporating pre-trained language models (PLMs) with various open-world knowledge, such as knowledge graphs or wiki…

The paper discusses the basic principles and the architecture of the software toolkit for constructing knowledge-based systems which can be used cooperatively over computer networks and also embedded into larger software systems in…

This article describes a fully automated, credible autocoding chain for control systems. The framework generates code, along with guarantees of high level functional properties which can be independently verified. It relies on domain…

In this paper, we describe the construction of TeKnowbase, a knowledge-base of technical concepts in computer science. Our main information sources are technical websites such as Webopedia and Techtarget as well as Wikipedia and online…

Most prior work on task-oriented dialogue systems are restricted to a limited coverage of domain APIs, while users oftentimes have domain related requests that are not covered by the APIs. In this paper, we propose to expand coverage of…

Document intelligence automates the extraction of information from documents and supports many business applications. Recent self-supervised learning methods on large-scale unlabeled document datasets have opened up promising directions…

While general-purpose large language models (LLMs) demonstrate proficiency on multiple tasks within the domain of translation, approaches based on open LLMs are competitive only when specializing on a single task. In this paper, we propose…

The production process of data-centric infographics entails problems related to a disconnection between the supporting software environments. We investigate those problems and redesigns this process following the model-driven paradigm. We…

The context of the reported research is the documentation of software technologies such as object/relational mappers, web-application frameworks, or code generators. We assume that documentation should model a macroscopic view on usage…

Recent developments in controlled natural language editors for knowledge engineering (KE) have given rise to expectations that they will make KE tasks more accessible and perhaps even enable non-engineers to build knowledge bases. This…

Quantum chromodynamics (QCD) has yielded a vast literature spanning distinct phenomena. We construct a corpus of papers and build a generative model. This model holds promise for accelerating the capability of scientists to consolidate…

Multimodal systems, which process multiple input types such as text, audio, and images, are becoming increasingly prevalent in software systems, enabled by the huge advancements in Machine Learning. This triggers the need to easily define…

In the last years' digitalization process, the creation and management of documents in various domains, particularly in Public Administration (PA), have become increasingly complex and diverse. This complexity arises from the need to handle…

EuroVoc is a multilingual thesaurus that was built for organizing the legislative documentary of the European Union institutions. It contains thousands of categories at different levels of specificity and its descriptors are targeted by…

We propose V-Doc, a question-answering tool using document images and PDF, mainly for researchers and general non-deep learning experts looking to generate, process, and understand the document visual question answering tasks. The V-Doc…

Current task-oriented dialog (TOD) systems mostly manage structured knowledge (e.g. databases and tables) to guide the goal-oriented conversations. However, they fall short of handling dialogs which also involve unstructured knowledge (e.g.…

Documenting frameworks provides its users and maintainers useful information on that software's architecture, design, and customization. Despite documentation's importance, the process of creating and maintaining it is considered to imply…

Interfaces that support multi-lingual content can reach a broader community. We wish to extend the reach of CITIDEL, a digital library for computing education materials, to support multiple languages. By doing so, we hope that it will…

To retrieve and compare scientific data of simulations and experiments in materials science, data needs to be easily accessible and machine readable to qualify and quantify various materials science phenomena. The recent progress in open…

Multi-modal document pre-trained models have proven to be very effective in a variety of visually-rich document understanding (VrDU) tasks. Though existing document pre-trained models have achieved excellent performance on standard…