paper-with-me

홈 › Papers

Combining semantic spaces along with structure and constraints (Combiner espaces s\'emantiques, structure et contraintes) [in French]

2014-07-01 · JEPTALNRECITAL 2014 7 · Adil El Ghali, Kaoutar El Ghali
📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Enhancing Domain Word Embedding via Latent Semantic Imputation

2019-05-21 · Shibo Yao, Dantong Yu, Keli Xiao

We present a novel method named Latent Semantic Imputation (LSI) to transfer external knowledge into semantic space for enhancing word embedding. The method integrates graph theory to extract the latent manifold structur…

ImputationLanguage ModelingLanguage Modelling

Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?

2026-06-22 · Nils Grandien, David Steinmann, Felix Friedrich, Kristian Kersting arxiv

Sparse autoencoders (SAEs) have become an important tool for unsupervised concept discovery in large models. To make the resulting feature spaces more interpretable and manageable, recent approaches have begun imposing h…

Towards Coordinated Robot Motions: End-to-End Learning of Motion Policies on Transform Trees

2020-12-24 · M. Asif Rana, Anqi Li, Dieter Fox, Sonia Chernova 외

Generating robot motion that fulfills multiple tasks simultaneously is challenging due to the geometric constraints imposed by the robot. In this paper, we propose to solve multi-task problems through learning structured…

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