paper-with-me

홈 › Papers

Semantic Vector Spaces for Broadening Consideration of Consequences

2018-02-23 · Douglas Summers Stay

Reasoning systems with too simple a model of the world and human intent are unable to consider potential negative side effects of their actions and modify their plans to avoid them (e.g., avoiding potential errors). However, hand-encoding the enormous and subtle body of facts that constitutes common sense into a knowledge base has proved too difficult despite decades of work. Distributed semantic vector spaces learned from large text corpora, on the other hand, can learn representations that capture shades of meaning of common-sense concepts and perform analogical and associational reasoning in ways that knowledge bases are too rigid to perform, by encoding concepts and the relations between them as geometric structures. These have, however, the disadvantage of being unreliable, poorly understood, and biased in their view of the world by the source material. This chapter will discuss how these approaches may be combined in a way that combines the best properties of each for understanding the world and human intentions in a richer way.

📄 PDF Abstract BibTeX arXiv:1802.08554

Code (0)

등록된 구현이 없습니다.

Tasks

Common Sense Reasoning

Similar Papers 제목 키워드 기반

Discrete Semantic States and Hamiltonian Dynamics in LLM Embedding Spaces

2025-12-29 · Timo Aukusti Laine arxiv

We investigate the structure of Large Language Model (LLM) embedding spaces using mathematical concepts, particularly linear algebra and the Hamiltonian formalism, drawing inspiration from analogies with quantum mechanic…

Reducing DNN Properties to Enable Falsification with Adversarial Attacks

2021-05-27 · IEEE/ACM 43rd International Conference on Software Engineering (ICSE) 2021 5 · David Shriver, Sebastian Elbaum, Matthew B. Dwyer

Deep Neural Networks (DNN) are increasingly being deployed in safety-critical domains, from autonomous vehicles to medical devices, where the consequences of errors demand techniques that can provide stronger guarantees …

Adversarial AttackAutonomous Vehicles

Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints

2017-06-01 · Nikola Mrkšić, Ivan Vulić, Diarmuid Ó Séaghdha, Ira Leviant 외

We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources. Attract-Repel facilitates the use of constraints from mono- and cross-l…

Dialogue State TrackingSemantic SimilaritySemantic Textual Similarity

Semantic Specialization of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints

2017-01-01 · TACL 2017 1 · Nikola Mrk{\v{s}}i{\'c}, Ivan Vuli{\'c}, Diarmuid {\'O} S{\'e}aghdha, Ira Leviant 외

We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources. Attract-Repel facilitates the use of constraints from mono- and cross-l…

Dialogue State TrackingRepresentation LearningSemantic SimilaritySemantic Textual Similarity

Vector spaces as Kripke frames

2019-08-15 · Giuseppe Greco, Fei Liang, Michael Moortgat, Alessandra Palmigiano 외

In recent years, the compositional distributional approach in computational linguistics has opened the way for an integration of the \emph{lexical} aspects of meaning into Lambek's type-logical grammar program. This appr…