Papers with RDF
Neural data-to-text generation: A comparison between pipeline and end-to-end architectures (D19-1)
Copied to clipboard
| Challenge: | Traditionally, data-to-text applications have been designed using a modular pipeline architecture, in which the non-linguistic input data is converted into natural language through several intermediate transformations. |
| Approach: | They propose to use Gated-Recurrent Units and Transformer to implement neural pipelines for data-to-text generation. |
| Outcome: | The proposed models generalize better to unseen inputs and have better performance than the existing pipeline architectures. |
Promoting Graph Awareness in Linearized Graph-to-Text Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent applications of pretrained transformers to linearizations of graph inputs yield stateof-the-art results on graph-to-text tasks. |
| Approach: | They propose to use pretrained transformers to encode local graph structures . they find they can improve the quality of models' implicit graph encodings . |
| Outcome: | The proposed models can encode local graph structures and reconstruct corrupted inputs. |
ENT-DESC: Entity Description Generation by Exploring Knowledge Graph (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for knowledge-to-text generation use RDF triples or key-value pairs to generate a natural language description. |
| Approach: | They propose a large-scale dataset to facilitate the study of KG-to-text . they propose MGCN model architecture that incorporates aggregation methods to extract the rich graph information. |
| Outcome: | The proposed model can represent the original graph information more comprehensively and integrates multiple aggregation methods to extract the rich graph information. |
Building Literary Corpora for Computational Literary Analysis - A Prototype to Bridge the Gap between CL and DH (L18-1)
Copied to clipboard
| Challenge: | Literature analysis using corpus-based literary analysis is slow, says aaron s. e. . literary studies researchers should focus on the research practices of literary studies, he says . |
| Approach: | et al. show litText can extract text from a 20 million word corpus using SPARQL queries. |
| Outcome: | The proposed method uses a 20 million word corpus from English, German, Spanish, French and Italian texts and an example query to identify texts where animals behave like humans as it is the case in fables. |
Entity-Based Semantic Adequacy for Data-to-Text Generation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing pre-trained language models have improved the fluency of text generation systems, but semantic adequacy remains an unsolved issue. |
| Approach: | They propose an automatic evaluation metric to assess to what extent models that verbalise RDF graphs produce text that contains mentions of entities occurring in the input. |
| Outcome: | The proposed metric can be used to assess to what extent generation models verbalise RDF graphs produce text that contains mentions of the entities occurring in the input. |
LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing neural approaches to generate RDF-to-text are limited in their implementation. |
| Approach: | They propose a framework where the model is “trained” through collaborative interactions among multiple LLM agents rather than traditional backpropagation. |
| Outcome: | The proposed framework reduces hallucinations and fluency penalties on the WebNLG and OpenDialKG datasets. |
GTR-LSTM: A Triple Encoder for Sentence Generation from RDF Data (P18-1)
Copied to clipboard
| Challenge: | Knowledge bases are becoming an enabling resource for many applications including Q&A systems, recommender systems, and summarization tools. |
| Approach: | They propose a system to translate RDF triples into natural sentences using an encoder-decoder framework. |
| Outcome: | The proposed model outperforms the baseline model by 17.6%, 6.0%, and 16.4% in terms of BLEU, METEOR, and TER scores. |
Bridging Computational Lexicography and Corpus Linguistics: A Query Extension for OntoLex-FrAC (2024.lrec-main)
Copied to clipboard
| Challenge: | OntoLex is the dominant community standard for machine-readable lexical resources . it is currently extended with a designated module for Frequency, Attestations and Corpus-based Information . |
| Approach: | They propose a module for Frequency, Attestations and Corpus-based Information for OntoLex . the module enables RDF-based web services to exchange corpus queries dynamically . |
| Outcome: | The proposed module addresses the incorporation of corpus queries for linking dictionaries with corpus engines and enabling RDF-based web services to exchange corpus query data dynamically. |
ASPIRO: Any-shot Structured Parsing-error-Induced ReprOmpting for Consistent Data-to-Text Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Unlike previous methods, large language models produce entity-agnostic templates instead of copying the given example entities or validating/crafting the templates manually. |
| Approach: | They propose an approach for structured data verbalisation into short template sentences in zero to few-shot settings that prompts Large Language Models to directly produce entity-agnostic templates. |
| Outcome: | The proposed approach averages 66% parsing error rate reduction in generated verbalisations of RDF triples on the DART dataset. |
Neural Pipeline for Zero-Shot Data-to-Text Generation (2022.acl-long)
Copied to clipboard
| Challenge: | In data-to-text generation, training on in-domain data leads to overfitting and repeating training data noise. |
| Approach: | They propose to train pretrained language models on general-domain text-based operations by transforming single-item descriptions with modules trained on ordering, aggregation, and paragraph compression. |
| Outcome: | The proposed approach enables D2T generation from RDF triples in zero-shot settings. |
The LODeXporter: Flexible Generation of Linked Open Data Triples from NLP Frameworks for Automatic Knowledge Base Construction (L18-1)
Copied to clipboard
| Challenge: | Linked Open Data (LOD) principles are used to export natural language processing (NLP) results to graph-based knowledge base. |
| Approach: | They propose a method for exporting NLP results to a graph-based knowledge base using Linked Open Data principles. |
| Outcome: | The proposed method is available as an open source component for the GATE framework and is available on GitHub. |
LIdioms: A Multilingual Linked Idioms Data Set (L18-1)
Copied to clipboard
| Challenge: | Recent studies have focused on linguistic data sets that are bilingual on the Linguistic Linked Open Data (LLOD) 1 . |
| Approach: | They describe a multilingual RDF representation of idioms currently containing five languages . they use a model to structure the data and a method to link the data to well-known multilingual data sets such as BabelNet. |
| Outcome: | The proposed model complies with best practices according to Linguistic Linked Open Data Community. |
The ACoLi Dictionary Graph (2020.lrec-1)
Copied to clipboard
| Challenge: | ACoLi Dictionary Graph is a collection of multilingual open source dictionaries available in two machine-readable formats. |
| Approach: | They propose to map and harmonize ACoLi Dictionary Graph into a unified representation and a tabular data format to facilitate their use in NLP tasks. |
| Outcome: | The ACoLi Dictionary Graph is a collection of multilingual open source dictionaries available in two machine-readable formats. |
CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era (2025.acl-long)
Copied to clipboard
| Challenge: | Graphs are used for storing open-domain knowledge and domain-specific enterprise data. |
| Approach: | They propose to use property graph views on top of the underlying RDF graph to efficiently query LLMs. |
| Outcome: | The proposed graph views can be efficiently queried by LLMs using Cypher . the proposed graphs have a large schema, overlapping and ambiguous relation types and lack of normalization. |
RDF2PT: Generating Brazilian Portuguese Texts from RDF Data (L18-1)
Copied to clipboard
Diego Moussallem, Thiago Ferreira, Marcos Zampieri, Maria Claudia Cavalcanti, Geraldo Xexéo, Mariana Neves, Axel-Cyrille Ngonga Ngomo
| Challenge: | Existing approaches to generate natural language from RDF data have been proposed to generate texts in Brazilian Portuguese. |
| Approach: | They propose a rule-based approach to verbalize RDF data to Brazilian Portuguese language. |
| Outcome: | The proposed approach generates text similar to that generated by humans and can hence be easily understood. |
Ontology-Style Relation Annotation: A Case Study (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for Relation Extraction (RE) annotations use links between entities . a domain link connects the relation mention to the source entity while a range link connect the relation to the destination entity. |
| Approach: | They propose an Ontology-Style Relation (OSR) annotation approach to find relation mentions in relation annotations. |
| Outcome: | The proposed approach can be easily converted to Ontology RDF triples to populate an Ontologies. |
Defying Wikidata: Validation of Terminological Relations in the Web of Data (2020.lrec-1)
Copied to clipboard
| Challenge: | a new approach to validate terminological data retrieved from open encyclopaedic knowledge bases is needed . the legal domain is one of the most valuable areas of knowledge in the world . |
| Approach: | They propose to validate terminological data retrieved from open encyclopaedic knowledge bases by enriching them with information from existing resources in the Semantic Web. |
| Outcome: | The proposed method validates terms from open encyclopaedic knowledge bases in four languages. |
Retrieving Information from the French Lexical Network in RDF/OWL Format (L18-1)
Copied to clipboard
| Challenge: | a Java API to retrieve lexical information from the French Lexical Network is presented . RDF/OWL languages are not sufficient for a more detailed representation of linguistic information. |
| Approach: | They propose a Java API to retrieve lexical information from the French Lexical Network . this API was used in the identification of collocations in a french corpus of 1.8 million sentences . |
| Outcome: | The proposed API was used to identify collocations in a French corpus of 1.8 million sentences and in the semantic classification of these collocation. |
A Tree Extension for CoNLL-RDF (2020.lrec-1)
Copied to clipboard
| Challenge: | CoNLL-RDF provides a bridge for popular oneword-per-line formats . main reasons for their popularity are the simplicity of tables and tab-separated values . |
| Approach: | They propose a technology that provides a bridge between knowledge graphs and natural language processing. |
| Outcome: | The proposed technology provides a bridge for popular one-word-per-line formats . it provides native support for word-level annotations, but not phrase structures or text structure . |
Editing OntoLex-Lemon in VocBench 3 (2020.lrec-1)
Copied to clipboard
Manuel Fiorelli, Armando Stellato, Tiziano Lorenzetti, Andrea Turbati, Peter Schmitz, Enrico Francesconi, Najeh Hajlaoui, Brahim Batouche
| Challenge: | OntoLex-Lemon is a collection of RDF vocabularies for specifying the verbalization of ontologies in natural language. |
| Approach: | They propose to extend existing RDF editor to OntoLex-Lemon to provide more direct editing . they propose to use a model that allows for the verbalization of ontologies in natural language . |
| Outcome: | The proposed editor improves the ontology-lexicon interface and improves its flexibility. |
Fintan - Flexible, Integrated Transformation and Annotation eNgineering (2020.lrec-1)
Copied to clipboard
| Challenge: | Fintan is a platform for converting heterogeneous linguistic resources to RDF. |
| Approach: | They introduce Fintan for converting heterogeneous linguistic resources to RDF with its modular architecture, workflow management and visualization features. |
| Outcome: | The Fintan platform is designed to transform linguistic resources to graphs and graphs. |