# Text-To-KG Alignment: Comparing Current Methods on Classification Tasks

arXiv: https://arxiv.org/abs/2306.02871 · HTML: https://mlsanity.com/paper/2306.02871/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 5 Jun 2023.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [Knowledge Enhanced Contextual Word Representations](https://mlsanity.com/paper/1909.04164/) (2019)
- [Revisiting Few-sample BERT Fine-tuning](https://mlsanity.com/paper/2006.05987/) (2020)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [GreaseLM: Graph REASoning Enhanced Language Models for Question Answering](https://mlsanity.com/paper/2201.08860/) (2022)
- [Deep Bidirectional Language-Knowledge Graph Pretraining](https://mlsanity.com/paper/2210.09338/) (2022)
- [Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering](https://mlsanity.com/paper/2005.00646/) (2020)
- [KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering](https://mlsanity.com/paper/2110.04330/) (2021)
- [Story Ending Generation with Incremental Encoding and Commonsense Knowledge](https://mlsanity.com/paper/1808.10113/) (2018)
- [TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases](https://mlsanity.com/paper/2210.12925/) (2022)
- [ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning](https://mlsanity.com/paper/2104.07644/) (2021)
- [Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers](https://mlsanity.com/paper/2005.11787/) (2020)
- [Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering](https://mlsanity.com/paper/2005.00691/) (2020)
- [When Choosing Plausible Alternatives, Clever Hans can be Clever](https://mlsanity.com/paper/1911.00225/) (2019)
- [JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering](https://mlsanity.com/paper/2112.02732/) (2021)
- [Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks](https://mlsanity.com/paper/2105.05457/) (2021)
- [Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks](https://mlsanity.com/paper/2010.10044/) (2020)
- [ComFact: A Benchmark for Linking Contextual Commonsense Knowledge](https://mlsanity.com/paper/2210.12678/) (2022)
- [Identify, Align, and Integrate: Matching Knowledge Graphs to Commonsense Reasoning Tasks](https://mlsanity.com/paper/2104.10193/) (2021)
- [COPA-SSE: Semi-structured Explanations for Commonsense Reasoning](https://mlsanity.com/paper/2201.06777/) (2022)
- [LM-CORE: Language Models with Contextually Relevant External Knowledge](https://mlsanity.com/paper/2208.06458/) (2022)

## Built on by (most cited first, 2 of 2)

- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [Compositional Generalization with Grounded Language Models](https://mlsanity.com/paper/2406.04989/) (2024)

## Abstract (arXiv)

In contrast to large text corpora, knowledge graphs (KG) provide dense and structured representations of factual information. This makes them attractive for systems that supplement or ground the knowledge found in pre-trained language models with an external knowledge source. This has especially been the case for classification tasks, where recent work has focused on creating pipeline models that retrieve information from KGs like ConceptNet as additional context. Many of these models consist of multiple components, and although they differ in the number and nature of these parts, they all have in common that for some given text query, they attempt to identify and retrieve a relevant subgraph from the KG. Due to the noise and idiosyncrasies often found in KGs, it is not known how current methods compare to a scenario where the aligned subgraph is completely relevant to the query. In this work, we try to bridge this knowledge gap by reviewing current approaches to text-to-KG alignment and evaluating them on two datasets where manually created graphs are available, providing insights into the effectiveness of current methods.