paper-with-me

홈 › Papers

Integrating Multi-Head Convolutional Encoders with Cross-Attention for Improved SPARQL Query Translation

2024-08-24 · Yi-Hui Chen, Eric Jui-Lin Lu, Kwan-Ho Cheng

The main task of the KGQA system (Knowledge Graph Question Answering) is to convert user input questions into query syntax (such as SPARQL). With the rise of modern popular encoders and decoders like Transformer and ConvS2S, many scholars have shifted the research direction of SPARQL generation to the Neural Machine Translation (NMT) architecture or the generative AI field of Text-to-SPARQL. In NMT-based QA systems, the system treats knowledge base query syntax as a language. It uses NMT-based translation models to translate natural language questions into query syntax. Scholars use popular architectures equipped with cross-attention, such as Transformer, ConvS2S, and BiLSTM, to train translation models for query syntax. To achieve better query results, this paper improved the ConvS2S encoder and added multi-head attention from the Transformer, proposing a Multi-Head Conv encoder (MHC encoder) based on the n-gram language model. The principle is to use convolutional layers to capture local hidden features in the input sequence with different receptive fields, using multi-head attention to calculate dependencies between them. Ultimately, we found that the translation model based on the Multi-Head Conv encoder achieved better performance than other encoders, obtaining 76.52\% and 83.37\% BLEU-1 (BiLingual Evaluation Understudy) on the QALD-9 and LC-QuAD-1.0 datasets, respectively. Additionally, in the end-to-end system experiments on the QALD-9 and LC-QuAD-1.0 datasets, we achieved leading results over other KGQA systems, with Macro F1-measures reaching 52\% and 66\%, respectively. Moreover, the experimental results show that with limited computational resources, if one possesses an excellent encoder-decoder architecture and cross-attention, experts and scholars can achieve outstanding performance equivalent to large pre-trained models using only general embeddings.

📄 PDF Abstract BibTeX arXiv:2408.13432

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Question AnsweringMachine TranslationNMTQuestion AnsweringTranslation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Tanh Activation 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Lookahead optimizer improves the performance of Convolutional Autoencoders for reconstruction of natural images

2020-12-03 · Sayan Nag

Autoencoders are a class of artificial neural networks which have gained a lot of attention in the recent past. Using the encoder block of an autoencoder the input image can be compressed into a meaningful representation…

Data CompressionDecoderDenoising

Enhancing Perception Capabilities of Multimodal LLMs with Training-Free Fusion

2024-12-02 · Zhuokun Chen, Jinwu Hu, Zeshuai Deng, Yufeng Wang 외

Multimodal LLMs (MLLMs) equip language models with visual capabilities by aligning vision encoders with language models. Existing methods to enhance the visual perception of MLLMs often involve designing more powerful vi…

Language ModelingLanguage Modelling

Unified CNNs and transformers underlying learning mechanism reveals multi-head attention modus vivendi

2025-01-22 · Ella Koresh, Ronit D. Gross, Yuval Meir, Yarden Tzach 외

Convolutional neural networks (CNNs) evaluate short-range correlations in input images which progress along the layers, whereas vision transformer (ViT) architectures evaluate long-range correlations, using repeated tran…

TopoFormer: Integrating Transformers and ConvLSTMs for Coastal Topography Prediction

2025-01-11 · Santosh Munian, Oktay Karakuş, William Russell, Gwyn Nelson

This paper presents \textit{TopoFormer}, a novel hybrid deep learning architecture that integrates transformer-based encoders with convolutional long short-term memory (ConvLSTM) layers for the precise prediction of topo…

Survey

Aftab: A Comprehensive Benchmark of CNN Encoders and Advanced Value Functions in Parallelized Q-Networks

2026-08-07 · Taha Shieenavaz, Shabnam Zareshahraki, Loris Nanni arxiv

Recent advancements in deep reinforcement learning have increasingly favored simplified, highly parallelized paradigms. Notably, the Parallelized Q-Network (PQN) algorithm enables off-policy value learning without relyin…

Computational EfficiencyRepresentation LearningReinforcement Learning