Papers with commonsense inference

10 papers
KARNA at COIN Shared Task 1: Bidirectional Encoder Representations from Transformers with relational knowledge for machine comprehension with common sense (D19-60)

Copied to clipboard

Challenge: Using Bidirectional Encoder Representations from Transformers(BERT) and external relational knowledge from ConceptNet, we are able to achieve an accuracy of 73.3 % on the official test data.
Approach: They propose a model that uses Bidirectional Encoder Representations from Transformers and ConceptNet to tackle the problem of commonsense inference in natural language processing.
Outcome: The proposed model achieves 73.3 % accuracy on the official test data.
Narrative Theory for Computational Narrative Understanding (2021.emnlp-main)

Copied to clipboard

Challenge: a growing body of theoretical work on narrative has been focused on the field of natural language processing . this position paper aims to provide a unifying framework for the computational study of narrative .
Approach: They propose to introduce dominant theoretical frameworks to the NLP community and situate current research within distinct narratological traditions.
Outcome: The proposed framework would allow for new empirical questions and applications in the field of natural language processing.
Event2Mind: Commonsense Inference on Events, Intents, and Reactions (P18-1)

Copied to clipboard

Challenge: Using a crowdsourced corpus of 25,000 event phrases, we construct a new task that uses commonsense reasoning to reason about the likely intents and reactions of the event participants.
Approach: They construct a crowdsourced corpus of 25,000 event phrases and use them to construct 'commonsense inference' they demonstrate that neural encoder-decoder models can compose embedding representations of previously unseen events and reason about the likely intents and reactions of the event participants.
Outcome: The proposed task can be used to uncover implicit gender inequality in movie scripts.
Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense Inference (2022.findings-acl)

Copied to clipboard

Challenge: Existing approaches to commonsense inference lack coverage and expressive diversity of commonsensense knowledge graphs.
Approach: They propose a framework that contrasts sets of semantically similar and dissimilar events . they propose 'solar' framework that can be used to learn commonsense inference .
Outcome: The proposed framework outperforms the state-of-the-art commonsense transformer on commonsensense inference by 1.84% on average among 8 metrics.
DiffuCOMET: Contextual Commonsense Knowledge Diffusion (2024.acl-long)

Copied to clipboard

Challenge: Recent methods for identifying contextually relevant commonsense inferences are weak . knowledge models are trained to verbalize tuples from general commonsens knowledge graphs .
Approach: They develop a series of knowledge models that leverage diffusion to reconstruct semantic connections between narrative contexts and relevant commonsense knowledge.
Outcome: The proposed model improves on two benchmarks, ComFact and WebNLG+, to measure commonsense diversity and contextual relevance.
Diagnosing the First-Order Logical Reasoning Ability Through LogicNLI (2021.emnlp-main)

Copied to clipboard

Challenge: Existing studies have focused on diagnosing LMs' reasoning abilities in natural language understanding tasks.
Approach: They propose a diagnostic method for first-order logic reasoning with a proposed benchmark, LogicNLI.
Outcome: The proposed method disentangles the target FOL reasoning from commonsense inference and can be used to diagnose LMs from four perspectives: accuracy, robustness, generalization, and interpretability.
MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding (2021.naacl-main)

Copied to clipboard

Challenge: a new method for generating metaphors is proposed to generate literal sentences . human evaluations show that our best model generates metaphors better than three well-crafted baselines 66% of the time on average.
Approach: They propose a method to automatically construct a parallel corpus by transforming literal sentences to metaphorical ones using commonsense inference and masked language modeling.
Outcome: The proposed method generates metaphors better than baselines 66% of the time on average.
HellaSwag: Can a Machine Really Finish Your Sentence? (P19-1)

Copied to clipboard

Challenge: Existing commonsense models struggle to perform inferences that are trivial for humans, but are often misclassified by state-of-the-art models.
Approach: They propose a dataset that is adversarial to state-of-the-art commonsense reasoning and use it to build a model that is surprisingly robust.
Outcome: The proposed dataset is compared with existing models and scaled up towards a critical 'Goldilocks zone' wherein generated text is ridiculous to humans, yet often misclassified by state-of-the-art models.
Mapping Texts to Scripts: An Entailment Study (L18-1)

Copied to clipboard

Challenge: Script knowledge is crucial for text understanding systems, providing a basis for commonsense inference.
Approach: They propose to map event mentions in a text to script events using crowdsourced event descriptions.
Outcome: The proposed model improves the performance of text-to-script mapping systems by integrating paraphrase sets with crowdsourced event descriptions.
Downstream Datasets Make Surprisingly Good Pretraining Corpora (2023.acl-long)

Copied to clipboard

Challenge: a dominant practice is to fine tune large pretrained transformer models using smaller downstream datasets . performance gains are not always attributable to the use of external data in massive amounts .
Approach: They propose to use the same (downstream) training data for pretraining and finetuning to compare models.
Outcome: The proposed model outperforms standard pretraining on the BookWiki corpus on 7 and 5 datasets.

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