# CO-NNECT: A Framework for Revealing Commonsense Knowledge Paths as Explicitations of Implicit Knowledge in Texts

arXiv: https://arxiv.org/abs/2105.03157 · HTML: https://mlsanity.com/paper/2105.03157/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 7 May 2021.

## Builds on (most cited first, 16 of 16)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [Enriching Pre-trained Language Model with Entity Information for Relation Classification](https://mlsanity.com/paper/1905.08284/) (2019)
- [Attention Guided Graph Convolutional Networks for Relation Extraction](https://mlsanity.com/paper/1906.07510/) (2019)
- [The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrants](https://mlsanity.com/paper/1708.01425/) (2017)
- [Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering](https://mlsanity.com/paper/2005.00691/) (2020)
- [Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning](https://mlsanity.com/paper/1509.01692/) (2015)
- [Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs](https://mlsanity.com/paper/1904.00676/) (2019)
- [Social Commonsense Reasoning with Multi-Head Knowledge Attention](https://mlsanity.com/paper/2010.05587/) (2020)
- [Dynamic Integration of Background Knowledge in Neural NLU Systems](https://mlsanity.com/paper/1706.02596/) (2017)
- [Implicit Knowledge in Argumentative Texts: An Annotated Corpus](https://mlsanity.com/paper/1912.10161/) (2019)
- [Assessing the Difficulty of Classifying ConceptNet Relations in a Multi-Label Classification Setting](https://mlsanity.com/paper/1905.05538/) (2019)

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

- [CoSe-Co: Text Conditioned Generative CommonSense Contextualizer](https://mlsanity.com/paper/2206.05706/) (2022)
- [LPAttack: A Feasible Annotation Scheme for Capturing Logic Pattern of Attacks in Arguments](https://mlsanity.com/paper/2204.01512/) (2022)

## Abstract (arXiv)

In this work we leverage commonsense knowledge in form of knowledge paths to establish connections between sentences, as a form of explicitation of implicit knowledge. Such connections can be direct (singlehop paths) or require intermediate concepts (multihop paths). To construct such paths we combine two model types in a joint framework we call Co-nnect: a relation classifier that predicts direct connections between concepts; and a target prediction model that generates target or intermediate concepts given a source concept and a relation, which we use to construct multihop paths. Unlike prior work that relies exclusively on static knowledge sources, we leverage language models finetuned on knowledge stored in ConceptNet, to dynamically generate knowledge paths, as explanations of implicit knowledge that connects sentences in texts. As a central contribution we design manual and automatic evaluation settings for assessing the quality of the generated paths. We conduct evaluations on two argumentative datasets and show that a combination of the two model types generates meaningful, high-quality knowledge paths between sentences that reveal implicit knowledge conveyed in text.