Explain Yourself! Leveraging Language Models for Commonsense Reasoning

@inproceedings{Rajani2019ExplainYL,
  title={Explain Yourself! Leveraging Language Models for Commonsense Reasoning},
  author={Nazneen Rajani and Bryan McCann and Caiming Xiong and Richard Socher},
  booktitle={ACL},
  year={2019}
}
Deep learning models perform poorly on tasks that require commonsense reasoning, which often necessitates some form of world-knowledge or reasoning over information not immediately present in the input. [...] Key Method We use CoS-E to train language models to automatically generate explanations that can be used during training and inference in a novel Commonsense Auto-Generated Explanation (CAGE) framework. CAGE improves the state-of-the-art by 10% on the challenging CommonsenseQA task.Expand
Rationale-Inspired Natural Language Explanations with Commonsense
TLDR
This work introduces a unified framework, called REXC (Rationale-inspired Explanations with Commonsense), that extracts rationales as a set of features most responsible for the predictions, expands the extractive rationales using available commonsense resources, and uses the expanded knowledge to generate NLEs. Expand
Prompting Contrastive Explanations for Commonsense Reasoning Tasks
TLDR
Inspired by the contrastive nature of human explanations, large pretrained language models are used to complete explanation prompts which contrast alternatives according to the key attribute(s) required to justify the correct answer. Expand
Align, Mask and Select: A Simple Method for Incorporating Commonsense Knowledge into Language Representation Models
TLDR
Experimental results demonstrate that pre-training models using the proposed approach followed by fine-tuning achieve significant improvements over previous state-of-the-art models on two commonsense-related benchmarks, including CommonsenseQA and Winograd Schema Challenge. Expand
iReason: Multimodal Commonsense Reasoning using Videos and Natural Language with Interpretability
TLDR
iReason, a framework that infers visual-semantic commonsense knowledge using both videos and natural language captions is proposed, and it is shown that iReason outperforms the state-of-the-art multimodal causality models. Expand
SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning
TLDR
SALKG, a simple framework for learning from KG explanations of both coarse and fine granularity, is proposed, which trains KG-augmented models to solve the task by focusing on KG information highlighted by the explanations as salient. Expand
Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings
TLDR
The largest and most fine-grained explainable NLI crowdsourcing study to date reveals that even large differences in automatic performance scores do neither reflect in human ratings of label, explanation, commonsense nor grammar correctness. Expand
Does BERT Solve Commonsense Task via Commonsense Knowledge?
TLDR
This work proposes two attention-based methods to analyze commonsense knowledge inside BERT, and finds that attention heads successfully capture the structured commonsenseknowledge encoded in ConceptNet, which helps BERT solve commonsense tasks directly. Expand
Team Solomon at SemEval-2020 Task 4: Be Reasonable: Exploiting Large-scale Language Models for Commonsense Reasoning
TLDR
This paper has developed a system that leverages commonsense knowledge from pretrained language models trained on huge corpus such as RoBERTa, GPT2, etc and validates the reasonability of a given statement against the backdrop of Commonsense knowledge acquired by these models and generates a logical reason to support its decision. Expand
LIREx: Augmenting Language Inference with Relevant Explanation
TLDR
Qualitative analysis shows that LIREx generates flexible, faithful, and relevant NLEs that allow the model to be more robust to spurious explanations, and achieves significantly better performance than previous studies when transferred to the out-of-domain MultiNLI data set. Expand
Flexible Generation of Natural Language Deductions
TLDR
PARAPATTERN is a method for building models to generate deductive inferences from diverse natural language inputs without direct human supervision, and achieves 85% validity on examples of the ‘substitution’ operation from EntailmentBank without the use of any in-domain training data. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 29 REFERENCES
Improving Question Answering by Commonsense-Based Pre-Training
TLDR
Results show that incorporating commonsense-based function improves the baseline on three question answering tasks that require commonsense reasoning and leverages useful evidence from an external commonsense knowledge base, which is missing in existing neural network models. Expand
A Simple Method for Commonsense Reasoning
TLDR
Key to this method is the use of language models, trained on a massive amount of unlabled data, to score multiple choice questions posed by commonsense reasoning tests, which outperform previous state-of-the-art methods by a large margin. Expand
e-SNLI: Natural Language Inference with Natural Language Explanations
TLDR
The Stanford Natural Language Inference dataset is extended with an additional layer of human-annotated natural language explanations of the entailment relations, which can be used for various goals, such as obtaining full sentence justifications of a model’s decisions, improving universal sentence representations and transferring to out-of-domain NLI datasets. Expand
CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge
TLDR
This work presents CommonsenseQA: a challenging new dataset for commonsense question answering, which extracts from ConceptNet multiple target concepts that have the same semantic relation to a single source concept. Expand
A large annotated corpus for learning natural language inference
TLDR
The Stanford Natural Language Inference corpus is introduced, a new, freely available collection of labeled sentence pairs, written by humans doing a novel grounded task based on image captioning, which allows a neural network-based model to perform competitively on natural language inference benchmarks for the first time. Expand
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
TLDR
A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks. Expand
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
TLDR
A benchmark of nine diverse NLU tasks, an auxiliary dataset for probing models for understanding of specific linguistic phenomena, and an online platform for evaluating and comparing models, which favors models that can represent linguistic knowledge in a way that facilitates sample-efficient learning and effective knowledge-transfer across tasks. Expand
SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference
TLDR
This paper introduces the task of grounded commonsense inference, unifying natural language inference and commonsense reasoning, and proposes Adversarial Filtering (AF), a novel procedure that constructs a de-biased dataset by iteratively training an ensemble of stylistic classifiers, and using them to filter the data. Expand
A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories
TLDR
A new framework for evaluating story understanding and script learning: the `Story Cloze Test’, which requires a system to choose the correct ending to a four-sentence story, and a new corpus of 50k five- Sentence commonsense stories, ROCStories, to enable this evaluation. Expand
Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
TLDR
It is shown how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought vectors on a wide range of transfer tasks. Expand
...
1
2
3
...