paper-with-me

Papers

Learning Structure-Aware Representations of Dependent Types

2024-02-03 · Konstantinos Kogkalidis, Orestis Melkonian, Jean-Philippe Bernardy

Agda is a dependently-typed programming language and a proof assistant, pivotal in proof formalization and programming language theory. This paper extends the Agda ecosystem into machine learning territory, and, vice versa, makes Agda-related resources available to machine learning practitioners. We introduce and release a novel dataset of Agda program-proofs that is elaborate and extensive enough to support various machine learning applications -- the first of its kind. Leveraging the dataset's ultra-high resolution, which details proof states at the sub-type level, we propose a novel neural architecture targeted at faithfully representing dependently-typed programs on the basis of structural rather than nominal principles. We instantiate and evaluate our architecture in a premise selection setup, where it achieves promising initial results, surpassing strong baselines.

📄 PDF Abstract BibTeX arXiv:2402.02104

Code (2)

konstantinosKokos/neural-agda 공식 구현 pytorch
konstantinoskokos/quill 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition

2024-11-18 · CVPR 2025 1 · Yang Chen, Jingcai Guo, Song Guo, DaCheng Tao

Zero-shot skeleton action recognition is a non-trivial task that requires robust unseen generalization with prior knowledge from only seen classes and shared semantics. Existing methods typically build the skeleton-seman…

Action Recognition

NARA: Anchor-Conditioned Relation-Aware Contextualization of Heterogeneous Geoentities

2026-05-12 · Jina Kim, Gengchen Mai, Lingyi Zhao, Khurram Shafique 외 arxiv

Geospatial foundation models have primarily focused on raster data such as satellite imagery, where self-supervised learning has been widely studied. Vector geospatial data instead represent the world as discrete geoenti…

Self-Supervised LearningRepresentation Learning

An Empirical Study of Span Representations in Argumentation Structure Parsing

2019-07-01 · ACL 2019 7 · Tatsuki Kuribayashi, Hiroki Ouchi, Naoya Inoue, Paul Reisert 외

For several natural language processing (NLP) tasks, span representation design is attracting considerable attention as a promising new technique; a common basis for an effective design has been established. With such ba…

Semi-Supervised Deep Learning for Multiplex Networks

2021-10-05 · Anasua Mitra, Priyesh Vijayan, Ranbir Sanasam, Diganta Goswami 외

Multiplex networks are complex graph structures in which a set of entities are connected to each other via multiple types of relations, each relation representing a distinct layer. Such graphs are used to investigate man…

Deep LearningRepresentation Learning

Does BERT agree? Evaluating knowledge of structure dependence through agreement relations

2019-08-26 · Geoff Bacon, Terry Regier

Learning representations that accurately model semantics is an important goal of natural language processing research. Many semantic phenomena depend on syntactic structure. Recent work examines the extent to which state…

Sensitivity