• Corpus ID: 234097495

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

  title={CO-NNECT: A Framework for Revealing Commonsense Knowledge Paths as Explicitations of Implicit Knowledge in Texts},
  author={Maria Becker and Katharina Korfhage and Debjit Paul and Anette Frank},
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… 

Figures and Tables from this paper

CoSe-Co: Text Conditioned Generative CommonSense Contextualizer
A CommonSense Contextualizer conditioned on sentences as input is proposed to make it generically usable in tasks for generating knowledge relevant to the overall context of input text and demonstrates its applicability in improving performance of a baseline model for paraphrase generation task.
Dialogue System Augmented with Commonsense Knowledge
This work proposes usage of structured knowledge base ConceptNet for knowledge-grounded dialogue generation and novel knowledge extraction algorithm is proposed which is then used to incorporate knowledge into existing dialogue datasets.
LPAttack: A Feasible Annotation Scheme for Capturing Logic Pattern of Attacks in Arguments
In argumentative discourse, persuasion is often achieved by refuting or attacking others arguments. Attacking is not always straightforward and often comprise complex rhetorical moves such that


Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering
This paper augments a general commonsense QA framework with a knowledgeable path generator by extrapolating over existing paths in a KG with a state-of-the-art language model, which learns to connect a pair of entities in text with a dynamic, and potentially novel, multi-hop relational path.
Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question Answering
This paper presents a novel approach that generates contextually-relevant symbolic knowledge structures on demand using generative neural commonsense knowledge models and achieves significant performance boosts over pretrained language models and vanilla knowledge models, all while providing interpretable reasoning paths for its predictions.
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
This investigation reveals promising results when implicit knowledge from deep pre-trained language models is transferred to generate explicit knowledge in commonsense knowledge graphs, and suggests that using generative commonsense models for automatic commonsense KB completion could soon be a plausible alternative to extractive methods.
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
This paper proposes a textual inference framework for answering commonsense questions, which effectively utilizes external, structured commonsense knowledge graphs to perform explainable inferences.
Reconstructing Implicit Knowledge with Language Models
Manual and automatic evaluation of the generations shows that by refining language models as proposed, they can generate coherent and grammatically sound sentences that explicate implicit knowledge which connects sentence pairs in texts – on both in-domain and out-of-domain test data.
ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
A new version of the linked open data resource ConceptNet is presented that is particularly well suited to be used with modern NLP techniques such as word embeddings, with state-of-the-art results on intrinsic evaluations of word relatedness that translate into improvements on applications of word vectors, including solving SAT-style analogies.
Argumentative Relation Classification with Background Knowledge
This paper proposes an unsupervised graph-based ranking method that extracts relevant multi-hop knowledge from a background knowledge resource and is integrated into a neural argumentative relation classifier via an attention-based gating mechanism.
Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs
A novel method to extract, rank, filter and select multi-hop relation paths from a commonsense knowledge resource to interpret the expression of sentiment in terms of their underlying human needs is presented.
Commonsense Knowledge Base Completion
This work develops neural network models for scoring tuples on arbitrary phrases and evaluates them by their ability to distinguish true held-out tuples from false ones and finds strong performance from a bilinear model using a simple additive architecture to model phrases.
Enriching Argumentative Texts with Implicit Knowledge
A process for obtaining high-quality implied knowledge annotations for German argumentative microtexts, in the form of simple natural language statements, which is characterized by a high proportion of generic sentences and a majority of it can be mapped to common sense knowledge relations.