Papers with commonsense inference
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. |