paper-with-me

홈 › Papers

Learning When to Concentrate or Divert Attention: Self-Adaptive Attention Temperature for Neural Machine Translation

2018-08-22 · EMNLP 2018 10 · Junyang Lin, Xu sun, Xuancheng Ren, Muyu Li, Qi Su

Most of the Neural Machine Translation (NMT) models are based on the sequence-to-sequence (Seq2Seq) model with an encoder-decoder framework equipped with the attention mechanism. However, the conventional attention mechanism treats the decoding at each time step equally with the same matrix, which is problematic since the softness of the attention for different types of words (e.g. content words and function words) should differ. Therefore, we propose a new model with a mechanism called Self-Adaptive Control of Temperature (SACT) to control the softness of attention by means of an attention temperature. Experimental results on the Chinese-English translation and English-Vietnamese translation demonstrate that our model outperforms the baseline models, and the analysis and the case study show that our model can attend to the most relevant elements in the source-side contexts and generate the translation of high quality.

📄 PDF Abstract BibTeX arXiv:1808.07374

Code (1)

lancopku/SACT pytorch

Tasks

DecoderMachine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

Tight Bounds for Answering Adaptively Chosen Concentrated Queries

2025-07-18 · Emma Rapoport, Edith Cohen, Uri Stemmer arxiv

Most work on adaptive data analysis assumes that samples in the dataset are independent. When correlations are allowed, even the non-adaptive setting can become intractable, unless some structural constraints are imposed…

Divert More Attention to Vision-Language Tracking

2022-07-03 · Mingzhe Guo, Zhipeng Zhang, Heng Fan, Liping Jing

Relying on Transformer for complex visual feature learning, object tracking has witnessed the new standard for state-of-the-arts (SOTAs). However, this advancement accompanies by larger training data and longer training …

Object Tracking

Few-shot Object Detection with Self-adaptive Attention Network for Remote Sensing Images

2020-09-26 · Zixuan Xiao, Wei Xue, Ping Zhong

In remote sensing field, there are many applications of object detection in recent years, which demands a great number of labeled data. However, we may be faced with some cases where only limited data are available. In t…

Few-Shot Object DetectionObjectobject-detectionObject Detection

Self-attention Networks Localize When QK-eigenspectrum Concentrates

2024-02-03 · Han Bao, Ryuichiro Hataya, Ryo Karakida

The self-attention mechanism prevails in modern machine learning. It has an interesting functionality of adaptively selecting tokens from an input sequence by modulating the degree of attention localization, which many r…

VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering

2025-12-12 · Zihu Wang, Boxun Xu, Yuxuan Xia, Peng Li arxiv

Large vision-language models (LVLMs) exhibit impressive ability to jointly reason over visual and textual inputs. However, they often produce outputs that are linguistically fluent but factually inconsistent with the vis…