Search Results for author: Xiaowang Zhang

Found 8 papers, 1 papers with code

Re-embedding Difficult Samples via Mutual Information Constrained Semantically Oversampling for Imbalanced Text Classification

no code implementations EMNLP 2021 Jiachen Tian, Shizhan Chen, Xiaowang Zhang, Zhiyong Feng, Deyi Xiong, Shaojuan Wu, Chunliu Dou

Difficult samples of the minority class in imbalanced text classification are usually hard to be classified as they are embedded into an overlapping semantic region with the majority class.

text-classification Text Classification

Attribute Simulation for Item Embedding Enhancement in Multi-interest Recommendation

no code implementations29 Nov 2023 Yaokun Liu, Xiaowang Zhang, Minghui Zou, Zhiyong Feng

Although multi-interest recommenders have achieved significant progress in the matching stage, our research reveals that existing models tend to exhibit an under-clustered item embedding space, which leads to a low discernibility between items and hampers item retrieval.

Attribute

Modeling Global Semantics for Question Answering over Knowledge Bases

no code implementations5 Jan 2021 Peiyun Wu, Yunjie Wu, Linjuan Wu, Xiaowang Zhang, Zhiyong Feng

Existing semantic parsing approaches mainly focus on relations matching with paying less attention to the underlying internal structure of questions (e. g., the dependencies and relations between all entities in a question) to select the query graph.

Question Answering Semantic Parsing

TrQuery: An Embedding-based Framework for Recommanding SPARQL Queries

no code implementations16 Jun 2018 Lijing Zhang, Xiaowang Zhang, Zhiyong Feng

In this paper, we present an embedding-based framework (TrQuery) for recommending solutions of a SPARQL query, including approximate solutions when exact querying solutions are not available due to incompleteness or inconsistencies of real-world RDF data.

Graph Matching

On the satisfiability problem for SPARQL patterns

no code implementations5 Jun 2014 Xiaowang Zhang, Jan Van den Bussche, François Picalausa

The satisfiability problem for SPARQL patterns is undecidable in general, since the expressive power of SPARQL 1. 0 is comparable with that of the relational algebra.

Cannot find the paper you are looking for? You can Submit a new open access paper.