Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities

1 code implementation • 27 Feb 2019 • Geewook Kim, Akifumi Okuno, Kazuki Fukui, Hidetoshi Shimodaira

In addition to the parameters of neural networks, we optimize the weights of the inner product by allowing positive and negative values.

Graph Embedding Model Selection +1

Word-like character n-gram embedding

1 code implementation • WS 2018 • Geewook Kim, Kazuki Fukui, Hidetoshi Shimodaira

We propose a new word embedding method called \textit{word-like character} n\textit{-gram embedding}, which learns distributed representations of words by embedding word-like character n-grams.

Segmentation Word Embeddings

Segmentation-free Compositional $n$-gram Embedding

2 code implementations • NAACL 2019 • Geewook Kim, Kazuki Fukui, Hidetoshi Shimodaira

We propose a new type of representation learning method that models words, phrases and sentences seamlessly.

Representation Learning Segmentation +1

Spectral Graph-Based Method of Multimodal Word Embedding

no code implementations • WS 2017 • Kazuki Fukui, Takamasa Oshikiri, Hidetoshi Shimodaira

In this paper, we propose a novel method for multimodal word embedding, which exploit a generalized framework of multi-view spectral graph embedding to take into account visual appearances or scenes denoted by words in a corpus.

Graph Embedding Image Retrieval +6

Cross-Lingual Word Representations via Spectral Graph Embeddings

1 code implementation • ACL 2016 • Takamasa Oshikiri, Kazuki Fukui, Hidetoshi Shimodaira

Information Retrieval Word Embeddings