Improving item cold-start recommendation via model-agnostic conditional variational autoencoder
Embedding & MLP has become a paradigm for modern large-scale recommendation
system. However, this paradigm suffers from the cold-start problem which will seriously …
system. However, this paradigm suffers from the cold-start problem which will seriously …
Hierarchical multi-marginal optimal transport for network alignment
Finding node correspondence across networks, namely multi-network alignment, is an
essential prerequisite for joint learning on multiple networks. Despite great success in …
essential prerequisite for joint learning on multiple networks. Despite great success in …
Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport
Answering complex queries on knowledge graphs is important but particularly challenging
because of the data incompleteness. Query embedding methods address this issue by …
because of the data incompleteness. Query embedding methods address this issue by …
A new dataset and efficient baselines for document-level text simplification in German
AR Gonzales, N Spring, T Kew… - Proceedings of the …, 2021 - aclanthology.org
The task of document-level text simplification is very similar to summarization with the
additional difficulty of reducing complexity. We introduce a newly collected data set of …
additional difficulty of reducing complexity. We introduce a newly collected data set of …
RAPO: An adaptive ranking paradigm for bilingual lexicon induction
Bilingual lexicon induction induces the word translations by aligning independently trained
word embeddings in two languages. Existing approaches generally focus on minimizing the …
word embeddings in two languages. Existing approaches generally focus on minimizing the …
Sufficient dimension reduction for classification using principal optimal transport direction
Sufficient dimension reduction is used pervasively as a supervised dimension reduction
approach. Most existing sufficient dimension reduction methods are developed for data with …
approach. Most existing sufficient dimension reduction methods are developed for data with …
Bilingual lexicon induction for low-resource languages using graph matching via optimal transport
Bilingual lexicons form a critical component of various natural language processing
applications, including unsupervised and semisupervised machine translation and …
applications, including unsupervised and semisupervised machine translation and …
Unsupervised sentence textual similarity with compositional phrase semantics
Abstract Measuring Sentence Textual Similarity (STS) is a classic task that can be applied to
many downstream NLP applications such as text generation and retrieval. In this paper, we …
many downstream NLP applications such as text generation and retrieval. In this paper, we …
WDEA: The Structure and Semantic Fusion with Wasserstein Distance for Low-Resource Language Entity Alignment
Entity Alignment (EA) aims to identify pairs of entities from two distinct language knowledge
graphs (KGs) that represent the same real-world objects. Current EA methods have …
graphs (KGs) that represent the same real-world objects. Current EA methods have …
A Novel Unsupervised Approach for Cross-Lingual Word Alignment in Low Isomorphic Embedding Spaces
Q Tao, Z Xiong, B Han, X Fan… - IEEE/ACM Transactions on …, 2023 - ieeexplore.ieee.org
Cross-lingual word alignment is the task for word translation between monolingual word
embedding spaces of two different languages. Recent work is mostly based on supervised …
embedding spaces of two different languages. Recent work is mostly based on supervised …