paper-with-me

홈 › Papers

Underspecification and interpretive parallelism in Dependent Type Semantics

2019-06-01 · WS 2019 6 · Yusuke Kubota, Koji Mineshima, Robert Levine, Daisuke Bekki
📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Vocal Bursts Type Prediction

Similar Papers 제목 키워드 기반

Towards meta-interpretive learning of programming language semantics

2019-07-20 · Sándor Bartha, James Cheney

We introduce a new application for inductive logic programming: learning the semantics of programming languages from example evaluations. In this short paper, we explored a simplified task in this domain using the Metago…

Inductive logic programming

Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST!

2024-02-19 · Frank Wildenburg, Michael Hanna, Sandro Pezzelle

In everyday language use, speakers frequently utter and interpret sentences that are semantically underspecified, namely, whose content is insufficient to fully convey their message or interpret them univocally. For exam…

Sentence

Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization

2026-05-27 · Aarik Gulaya arxiv

If an AI agent makes decisions on a person's behalf, those decisions must align with its user. We introduce representational accuracy to measure how faithfully a system captures a person's interpretation. An interpretive…

Visualizing Transferred Knowledge: An Interpretive Model of Unsupervised Domain Adaptation

2023-03-04 · Wenxiao Xiao, Zhengming Ding, Hongfu Liu

Many research efforts have been committed to unsupervised domain adaptation (DA) problems that transfer knowledge learned from a labeled source domain to an unlabeled target domain. Various DA methods have achieved remar…

Domain AdaptationUnsupervised Domain Adaptation

A neural anisotropic view of underspecification in deep learning

2021-04-29 · Guillermo Ortiz-Jimenez, Itamar Franco Salazar-Reque, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli 외

The underspecification of most machine learning pipelines means that we cannot rely solely on validation performance to assess the robustness of deep learning systems to naturally occurring distribution shifts. Instead, …

Deep LearningFairnessInductive Bias