Technical notes: Syntax-aware Representation Learning With Pointer Networks

2019-03-17 · Matteo Grella

This is a work-in-progress report, which aims to share preliminary results of a novel sequence-to-sequence schema for dependency parsing that relies on a combination of a BiLSTM and two Pointer Networks (Vinyals et al., 2015), in which the final softmax function has been replaced with the logistic regression. The two pointer networks co-operate to develop a latent syntactic knowledge, by learning the lexical properties of "selection" and the lexical properties of "selectability", respectively. At the moment and without fine-tuning, the parser implementation gets a UAS of 93.14% on the English Penn-treebank (Marcus et al., 1993) annotated with Stanford Dependencies: 2-3% under the SOTA but yet attractive as a baseline of the approach.

📄 PDF Abstract BibTeX arXiv:1903.07161

Code (0)

등록된 구현이 없습니다.

Tasks

Dependency Parsing regression Representation Learning

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음

Tanh Activation 설명 없음

LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Encoder-decoder based unified semantic role labeling with label-aware syntax

2021-05-18 · Conference 2021 5 · Hao Fei, Fei Li, Bobo Li, Donghong Ji

Currently the unified semantic role labeling (SRL) that achieves predicate identification and argument role labeling in an end-to-end manner has received growing interests. Recent works show that leveraging the syntax kn…

Decoder Semantic Role Labeling

PR2: Peephole Raw Pointer Rewriting with LLMs for Translating C to Safer Rust

2025-05-07 · YiFei Gao, Chengpeng Wang, Pengxiang Huang, Xuwei Liu 외

There has been a growing interest in translating C code to Rust due to Rust's robust memory and thread safety guarantees. Tools such as C2RUST enable syntax-guided transpilation from C to semantically equivalent Rust cod…

C++ code

Code Completion using Neural Attention and Byte Pair Encoding

2020-04-14 · Youri Arkesteijn, Nikhil Saldanha, Bastijn Kostense

In this paper, we aim to do code completion based on implementing a Neural Network from Li et. al.. Our contribution is that we use an encoding that is in-between character and word encoding called Byte Pair Encoding (BP…

Code Completion

Population Genetics and Evolution

2018-03-22

These lecture notes introduce key concepts of mathematical population genetics within the most elementary setting and describe a few recent applications to microbial evolution experiments. Pointers to the literature for …

Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction

2026-05-07 · Feifei Li, Qi Song, Chi Zhang, Rui Huang arxiv

Dense 3D reconstruction from continuous image streams requires both accurate geometric aggregation and stable long-term memory management. Recent feed-forward reconstruction frameworks integrate observations through pers…

3D Reconstruction