Өзіндік назар аудару желілері
Related Papers
Double Path Networks for Sequence to Sequence Learning
AbstractEncoder-decoder based Sequence to Sequence learning (S2S) has made remarkable progress in recent years. Different network architectures have been used in the encoder/decoder. Among them, Convolutional Neural Networks (CNN) and …...
Assessing the Ability of Self-Attention Networks to Learn Word Order
AbstractSelf-attention networks (SAN) have attracted a lot of interests due to their high parallelization and strong performance on a variety of NLP tasks, e.g. machine translation. Due to the lack …...
Self-Attention Networks for Intent Detection
AbstractSelf-attention networks (SAN) have shown promising performance in various Natural Language Processing (NLP) scenarios, especially in machine translation. One of the main points of SANs is the strength of capturing …...
How Does Selective Mechanism Improve Self-Attention Networks?
AbstractSelf-attention networks (SANs) with selective mechanism has produced substantial improvements in various NLP tasks by concentrating on a subset of input words. However, the underlying reasons for their strong performance …...
Inducing Target-Specific Latent Structures for Aspect Sentiment Classification
AbstractAspect-level sentiment analysis aims to recognize the sentiment polarity of an aspect or a target in a comment. Recently, graph convolutional networks based on linguistic dependency trees have been studied …...
Self-Attention with Cross-Lingual Position Representation
AbstractPosition encoding (PE), an essential part of self-attention networks (SANs), is used to preserve the word order information for natural language processing tasks, generating fixed position indices for input sequences. …...
HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalizability
AbstractFine-tuning large pre-trained models with task-specific data has achieved great success in NLP. However, it has been demonstrated that the majority of information within the self-attention networks is redundant and …...
Self-Attention Networks Can Process Bounded Hierarchical Languages
AbstractDespite their impressive performance in NLP, self-attention networks were recently proved to be limited for processing formal languages with hierarchical structure, such as Dyck-k, the language consisting of well-nested parentheses …...