paper-with-me

홈 › Papers

Adversarial Training for Commonsense Inference

2020-05-17 · WS 2020 7 · Lis Pereira, Xiaodong Liu, Fei Cheng, Masayuki Asahara, Ichiro Kobayashi

We propose an AdversariaL training algorithm for commonsense InferenCE (ALICE). We apply small perturbations to word embeddings and minimize the resultant adversarial risk to regularize the model. We exploit a novel combination of two different approaches to estimate these perturbations: 1) using the true label and 2) using the model prediction. Without relying on any human-crafted features, knowledge bases, or additional datasets other than the target datasets, our model boosts the fine-tuning performance of RoBERTa, achieving competitive results on multiple reading comprehension datasets that require commonsense inference.

📄 PDF Abstract BibTeX arXiv:2005.08156

Code (1)

archinetai/vat-pytorch pytorch

Tasks

Reading ComprehensionWord Embeddings

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음
Multi-Head Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference

2018-08-16 · EMNLP 2018 10 · Rowan Zellers, Yonatan Bisk, Roy Schwartz, Yejin Choi

Given a partial description like "she opened the hood of the car," humans can reason about the situation and anticipate what might come next ("then, she examined the engine"). In this paper, we introduce the task of grou…

Common Sense ReasoningMultiple-choiceNatural Language InferenceQuestion Answering

Adversarial Transformer Language Models for Contextual Commonsense Inference

2023-02-10 · Pedro Colon-Hernandez, Henry Lieberman, Yida Xin, Claire Yin 외

Contextualized or discourse aware commonsense inference is the task of generating coherent commonsense assertions (i.e., facts) from a given story, and a particular sentence from that story. Some problems with the task a…

Knowledge GraphsLanguage ModelingLanguage ModellingSentence

CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm

2022-10-12 · Hongming Zhang, Yintong Huo, Yanai Elazar, Yangqiu Song 외

Recently, the community has achieved substantial progress on many commonsense reasoning benchmarks. However, it is still unclear what is learned from the training process: the knowledge, inference capability, or both? We…

Question AnsweringTask 2

HellaSwag: Can a Machine Really Finish Your Sentence?

2019-05-19 · ACL 2019 7 · Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi 외

Recent work by Zellers et al. (2018) introduced a new task of commonsense natural language inference: given an event description such as "A woman sits at a piano," a machine must select the most likely followup: "She set…

HellaSwagNatural Language InferenceSentenceSentence Completion

Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium

2026-05-11 · Qingxin Xiao, Peilin Zhao, Yangyang Zhao, Lingwei Dang 외 arxiv

During MLLM decoding, attention often abnormally concentrates on irrelevant image tokens. While existing research dismisses this as invalid noise and forcibly redirects attention to compel focusing on key image informati…