Contrastive Self-Supervised Learning for Commonsense Reasoning
- URL: http://arxiv.org/abs/2005.00669v1
- Date: Sat, 2 May 2020 00:39:09 GMT
- Title: Contrastive Self-Supervised Learning for Commonsense Reasoning
- Authors: Tassilo Klein and Moin Nabi
- Abstract summary: We propose a self-supervised method to solve Pronoun Disambiguation and Winograd Challenge problems.
Our approach exploits the characteristic structure of training corpora related to so-called "trigger" words.
- Score: 26.68818542540867
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose a self-supervised method to solve Pronoun Disambiguation and
Winograd Schema Challenge problems. Our approach exploits the characteristic
structure of training corpora related to so-called "trigger" words, which are
responsible for flipping the answer in pronoun disambiguation. We achieve such
commonsense reasoning by constructing pair-wise contrastive auxiliary
predictions. To this end, we leverage a mutual exclusive loss regularized by a
contrastive margin. Our architecture is based on the recently introduced
transformer networks, BERT, that exhibits strong performance on many NLP
benchmarks. Empirical results show that our method alleviates the limitation of
current supervised approaches for commonsense reasoning. This study opens up
avenues for exploiting inexpensive self-supervision to achieve performance gain
in commonsense reasoning tasks.
Related papers
- Hierarchical Decomposition of Prompt-Based Continual Learning:
Rethinking Obscured Sub-optimality [55.88910947643436]
Self-supervised pre-training is essential for handling vast quantities of unlabeled data in practice.
HiDe-Prompt is an innovative approach that explicitly optimize the hierarchical components with an ensemble of task-specific prompts and statistics.
Our experiments demonstrate the superior performance of HiDe-Prompt and its robustness to pre-training paradigms in continual learning.
arXiv Detail & Related papers (2023-10-11T06:51:46Z) - Goodhart's Law Applies to NLP's Explanation Benchmarks [57.26445915212884]
We critically examine two sets of metrics: the ERASER metrics (comprehensiveness and sufficiency) and the EVAL-X metrics.
We show that we can inflate a model's comprehensiveness and sufficiency scores dramatically without altering its predictions or explanations on in-distribution test inputs.
Our results raise doubts about the ability of current metrics to guide explainability research, underscoring the need for a broader reassessment of what precisely these metrics are intended to capture.
arXiv Detail & Related papers (2023-08-28T03:03:03Z) - Counterfactuals of Counterfactuals: a back-translation-inspired approach
to analyse counterfactual editors [3.4253416336476246]
We focus on the analysis of counterfactual, contrastive explanations.
We propose a new back translation-inspired evaluation methodology.
We show that by iteratively feeding the counterfactual to the explainer we can obtain valuable insights into the behaviour of both the predictor and the explainer models.
arXiv Detail & Related papers (2023-05-26T16:04:28Z) - Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models [81.01397924280612]
Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations.
We introduce Iter-CoT (Iterative bootstrapping in Chain-of-Thoughts Prompting), an iterative bootstrapping approach for selecting exemplars and generating reasoning chains.
arXiv Detail & Related papers (2023-04-23T13:54:39Z) - Understanding and Constructing Latent Modality Structures in Multi-modal
Representation Learning [53.68371566336254]
We argue that the key to better performance lies in meaningful latent modality structures instead of perfect modality alignment.
Specifically, we design 1) a deep feature separation loss for intra-modality regularization; 2) a Brownian-bridge loss for inter-modality regularization; and 3) a geometric consistency loss for both intra- and inter-modality regularization.
arXiv Detail & Related papers (2023-03-10T14:38:49Z) - Reinforcement Learning with a Terminator [80.34572413850186]
We learn the parameters of the TerMDP and leverage the structure of the estimation problem to provide state-wise confidence bounds.
We use these to construct a provably-efficient algorithm, which accounts for termination, and bound its regret.
arXiv Detail & Related papers (2022-05-30T18:40:28Z) - Probing as Quantifying the Inductive Bias of Pre-trained Representations [99.93552997506438]
We present a novel framework for probing where the goal is to evaluate the inductive bias of representations for a particular task.
We apply our framework to a series of token-, arc-, and sentence-level tasks.
arXiv Detail & Related papers (2021-10-15T22:01:16Z) - Attention-based Contrastive Learning for Winograd Schemas [27.11678023496321]
This paper investigates whether contrastive learning can be extended to Transfomer attention to tackle the Winograd Challenge.
We propose a novel self-supervised framework, leveraging a contrastive loss directly at the level of self-attention.
arXiv Detail & Related papers (2021-09-10T21:10:22Z) - Feedback in Imitation Learning: Confusion on Causality and Covariate
Shift [12.93527098342393]
We argue that conditioning policies on previous actions leads to a dramatic divergence between "held out" error and performance of the learner in situ.
We analyze existing benchmarks used to test imitation learning approaches.
We find, in a surprising contrast with previous literature, that naive behavioral cloning provides excellent results.
arXiv Detail & Related papers (2021-02-04T20:18:56Z) - Representation Learning via Invariant Causal Mechanisms [19.0976564154636]
Self-supervised learning has emerged as a strategy to reduce the reliance on costly supervised signal by pretraining representations only using unlabeled data.
We show how data augmentations can be more effectively utilized through explicit invariance constraints on the proxy classifiers employed during pretraining.
We propose a novel self-supervised objective, Representation Learning via In Causvariantal Mechanisms (ReLIC) that enforces invariant prediction of proxy targets across augmentations.
arXiv Detail & Related papers (2020-10-15T17:53:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.