Challenge: a large-scale, general-domain dataset is needed for knowledge graph-to-text generation . data collection is expensive and data-intensive, making it difficult to get good annotation .
Approach: They propose to use a large-scale, general-domain dataset to generate unsupervised text from knowledge graphs.
Outcome: The proposed dataset has 1.3M text and graph examples, and is a benchmark for future research . good annotation is expensive and difficult to get, and it's difficult to check quality .

Similar Papers

WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections (2021.findings-acl)

Copied to clipboard

Challenge: Existing datasets for data-to-text generation focus on single-sentence generation or long-form generation.
Approach: They create a dataset that pairs Wikipedia sections with tabular data and various metadata.
Outcome: The proposed dataset can generate fluent and high quality texts but struggle with coherence and factuality.
An Unsupervised Joint System for Text Generation from Knowledge Graphs and Semantic Parsing (2020.emnlp-main)

Copied to clipboard

Challenge: Knowledge graphs (KGs) vary greatly from one domain to another, resulting in a lack of domain-specific parallel graph-text data.
Approach: They propose an unsupervised approach to graph-to-text generation and text-to graph knowledge extraction using WebNLG v2.1 and a new benchmark leveraging scene graphs from Visual Genome.
Outcome: The proposed approach outperforms baselines on WebNLG v2.1 and a new benchmark leveraging scene graphs from Visual Genome.
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.
TaKG: A New Dataset for Paragraph-level Table-to-Text Generation Enhanced with Knowledge Graphs (2022.findings-aacl)

Copied to clipboard

Challenge: Existing table-to-text generation benchmarks have some limitations, such as E2E and ToTTo focusing on singlesentence generation tasks.
Approach: They propose a new table-to-text generation dataset called TaKG that uses a set of knowledge graphs to enhance table input.
Outcome: The proposed model outperforms existing models for short-text generation tasks and shows reliable performance on long-text generated across a variety of metrics.
Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training (2021.naacl-main)

Copied to clipboard

Challenge: Existing work on data-to-text generation focused on domain-specific benchmark datasets.
Approach: They use a KG-Wikipedia text aligned corpus to verbalize the entire English Wikidata KG . they show that this approach can be used to integrate structured KGs and natural language corpora .
Outcome: The proposed method improves on open domain QA and the LAMA knowledge probe.
Chart-to-Text: A Large-Scale Benchmark for Chart Summarization (2022.acl-long)

Copied to clipboard

Challenge: Inferring key insights from charts can be challenging and time-consuming.
Approach: They propose a task where the goal is to explain a chart and summarize key takeaways from it in natural language.
Outcome: The proposed model produces fluent summaries but suffers from hallucinations and factual errors . the proposed model is compared with other models and can be used to generate BLEU scores .
SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation (2021.findings-emnlp)

Copied to clipboard

Challenge: Generating texts in scientific papers requires not only capturing the content contained within the given input but also frequently acquiring the external information called context.
Approach: They propose a task of context-aware text generation in the scientific domain to exploit the contributions of context in generated texts.
Outcome: The proposed dataset comprehensively benchmarks the efficacy of the proposed dataset in generating description and paragraph.
Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic Consistency (2022.findings-naacl)

Copied to clipboard

Challenge: Existing knowledge graph-to-text generation methods focus on sequence-to sequence generation, but the linearized order of KG is obtained through a heuristic search without data-driven optimization.
Approach: They propose to generate easy-to-understand sentences from the knowledge graph . they incorporate part-of-speech syntactic tags to constrain the positions to copy words from the KG and employ a semantic context scoring function to evaluate the semantic fitness for each word in its local context.
Outcome: The proposed method achieves state-of-the-art on two datasets, WebNLG and DART, and achieves high consistency.
Structural Information Preserving for Graph-to-Text Generation (2020.acl-main)

Copied to clipboard

Challenge: Existing models that mess up or drop the core structural information of input graphs are lacking in graph-to-text generation.
Approach: They propose to leverage richer training signals to guide a graph-to-text generation model by focusing on autoencoding losses and back-propagating the losses to better calibrate the model.
Outcome: Experiments on two benchmarks show the proposed model over a state-of-the-art model . two types of autoencoding losses are used to back-propagate the model based on multitask training .
GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation (2022.coling-1)

Copied to clipboard

Challenge: Recent improvements in KG-to-text generation are due to additional pre-training tasks . these tasks require extensive computational resources while only suggesting marginal improvements.
Approach: They propose a mask structure to capture neighborhood information and a type encoder that adds a bias to the graph-attention weights depending on the connection type.
Outcome: The proposed model outperforms state-of-the-art models while requiring no additional pre-training tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations