Self Attended Stack-Pointer Networks for Learning Long Term Dependencies
We propose a novel deep neural architecture for dependency parsing, which is built upon a Transformer Encoder (Vaswani et al. 2017) and a Stack Pointer Network (Ma et al. 2018). We first encode each sentence using a Transformer Network and then the dependency graph is generated by a Stack Pointer Network by selecting the head of each word in the sentence through a head selection process. We evaluate our model on Turkish and English treebanks. The results show that our trasformer-based model learns long term dependencies efficiently compared to sequential models such as recurrent neural networks. Our self attended stack pointer network improves UAS score around 6% upon the LSTM based stack pointer (Ma et al. 2018) for Turkish sentences with a length of more than 20 words.
Code (0)
등록된 구현이 없습니다.
Tasks
Dependency ParsingSentenceSimilar Papers 제목 키워드 기반
Stack-Pointer Networks for Dependency Parsing
We introduce a novel architecture for dependency parsing: \emph{stack-pointer networks} (\textbf{\textsc{StackPtr}}). Combining pointer networks~\citep{vinyals2015pointer} with an internal stack, the proposed model first…
Dependency ParsingSentenceLeft-to-Right Dependency Parsing with Pointer Networks
We propose a novel transition-based algorithm that straightforwardly parses sentences from left to right by building n attachments, with n being the length of the input sentence. Similarly to the recent stack-pointer par…
Dependency ParsingSentenceLeft-to-Right Dependency Parsing with Pointer Networks
We propose a novel transition-based algorithm that straightforwardly parses sentences from left to right by building $n$ attachments, with $n$ being the length of the input sentence. Similarly to the recent stack-pointer…
Dependency ParsingSentenceDilateFormer: Multi-Scale Dilated Transformer for Visual Recognition
As a de facto solution, the vanilla Vision Transformers (ViTs) are encouraged to model long-range dependencies between arbitrary image patches while the global attended receptive field leads to quadratic computational co…
Instance Segmentationobject-detectionObject DetectionSemantic SegmentationDo-It-Yourself Single Camera 3D Pointer Input Device
We present a new algorithm for single camera 3D reconstruction, or 3D input for human-computer interfaces, based on precise tracking of an elongated object, such as a pen, having a pattern of colored bands. To configure …
3D Reconstruction