Lexical knowledge enhanced text matching via distilled word sense disambiguation

Review Computer Science, Artificial Intelligence

Recent progress in leveraging deep learning methods for question answering

Tianyong Hao et al.

Summary: This paper provides a systematic review of recent developments in deep learning methods for question answering, covering methods, datasets, and applications, and discussing network structure characteristics, method innovations, and effectiveness. The survey is expected to contribute to summarizing recent research progress and future research directions in deep learning methods for question answering.

NEURAL COMPUTING & APPLICATIONS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Knowledge base question answering via path matching

Chunxiao Fan et al.

Summary: Knowledge base question answering (KBQA) refers to combining the information in the knowledge base to obtain an answer for an objective question. Most existing methods involve adding hand-crafted features or constraints to improve model performance, resulting in complex KBQA systems with limited improvement. This work presents a novel method that avoids using hand-crafted features or constraints, transforming the problem into a text matching task. The Path Matching Model (PMM) is employed to match the question and a series of edges in the knowledge base (KB). On the WebQuestions benchmark, the method achieves a 3% improvement compared to the state-of-the-art approach.

KNOWLEDGE-BASED SYSTEMS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Frame-based Multi-level Semantics Representation for text matching

Shaoru Guo et al.

Summary: This paper introduces a Frame-based Multi-level Semantics Representation (FMSR) model, which utilizes frame knowledge and attention mechanisms to extract multi-level semantic information within sentences for text matching tasks. Experimental results show that the FMSR model outperforms state-of-the-art technologies in text matching tasks.

KNOWLEDGE-BASED SYSTEMS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

EDS-MEMBED: Multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses

Eniafe Festus Ayetiran et al.

Summary: Multi-sense embeddings aim to represent each word by their distinct senses to resolve the conflation of meanings of words in different contexts. Previous works often overlook the impact and usefulness of semantic relations offered by lexical resources.

KNOWLEDGE-BASED SYSTEMS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

gMatch: Knowledge base question answering via semantic matching

Jie Jiao et al.

Summary: This paper proposes a novel semantic matching-based approach to address the ineffectiveness of queries in knowledge base question answering. By extracting subgraphs of the knowledge base to model the query intention of input questions and conducting semantic matching in the knowledge base, the inefficiency of queries is effectively reduced.

KNOWLEDGE-BASED SYSTEMS (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

An Enhanced Convolutional Inference Model with Distillation for Retrieval-Based QA

Shuangyong Song et al.

Summary: An enhanced convolutional inference model, StructBert-ECIM, is proposed in this paper with StructBert distillation to achieve a balance between accuracy and efficiency.

DATABASE SYSTEMS FOR ADVANCED APPLICATIONS (DASFAA 2021), PT III (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence