Text Generation from Knowledge Graphs with Graph Transformers (N19-1)

Copied to clipboard

Challenge: Existing methods for generating text with structured inputs are expensive and require manual annotation.
Approach: They propose a graph transforming encoder which leverages relational structure of knowledge graphs without imposing linearization or hierarchical constraints.
Outcome: The proposed system produces more informative texts than competing methods.

Similar Papers

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.
Knowledge Graph Generation From Text (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for generating text from text are limited due to non-unique graph representation, complex node structure, large output spaces and limited parallel training data.
Approach: They propose a novel end-to-end multi-stage Knowledge Graph generation system from textual inputs that separates the overall process into two stages.
Outcome: The proposed system outperforms existing methods on a WebNLG 2020 Challenge dataset and on TekGen datasets.
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.
AMR-To-Text Generation with Graph Transformer (2020.tacl-1)

Copied to clipboard

Challenge: Abstract meaning representation (AMR)-to-text generation is challenging task for natural language processing.
Approach: They propose a graph-to-sequence model that directly encodes AMR graphs and learns node representations.
Outcome: The proposed model outperforms the current state-of-the-art neural approach by 1.5 BLEU points on LDC2015E86 and 4.8 BLUE points on the LDC2017T10 and achieves new state- of-the art performance.
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.
Bi-Directional Multi-Granularity Generation Framework for Knowledge Graph-to-Text with Large Language Model (2024.acl-short)

Copied to clipboard

Challenge: Existing methods generate whole text based on all KG triples at once and may incorporate incorrect KG Triples for each sentence.
Approach: They propose a bi-directional multi-granularity generation framework that generates graph-level sentences based on KG triples instead of the whole text at a time.
Outcome: The proposed framework achieves state-of-the-art in benchmark dataset WebNLG and further analysis shows the efficiency of different modules.
Generating Knowledge Graph Paths from Textual Definitions using Sequence-to-Sequence Models (N19-1)

Copied to clipboard

Challenge: a novel method for mapping unrestricted text to knowledge graph entities is proposed . a proof-of-concept experiment has encouraging results comparable to those of state-of the-art systems.
Approach: They propose a method for mapping unrestricted text to knowledge graph entities by framing the task as a sequence-to-sequence problem.
Outcome: The proposed method produces highly interpretable predictions comparable to state-of-the-art systems.
Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs (D19-1)

Copied to clipboard

Challenge: Current approaches extract portions of web text as input to Sequence-to-Sequence models . a problem is generating relevant knowledge from noisy and redundant input such as webpages .
Approach: They propose to restructure free text into local knowledge graphs that are linearized into sequences . they propose to encode the graph as a sequence and then linearize it into a structured sequence .
Outcome: The proposed method compresses web search information and reduces redundancy . it can be used for open-domain question answering and multi-document summarization tasks .
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 .
Structure-aware Knowledge Graph-to-text Generation with Planning Selection and Similarity Distinction (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods to generate knowledge graph-to-text (KG-to) text rely on pre-trained language models to bridge the gap between the different structures of the input KG and the target text.
Approach: They propose a method that integrates graph structure-aware modules with pre-trained language models to capture the intricate topology information present in the KG.
Outcome: The proposed model captures the topology information present in the knowledge graph and distinguishes similar input KGs through contrastive learning techniques.

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