PaperMetrixEvidence-aware discovery
EN
Interface language English EN العربية AR Türkçe TR
Create account
Researcher profile

Liang Sun

6 papers in the PaperMetrix corpus

Publications

Papers by this author

  1. Parse Imputation for Dependency Annotations

    2015

    Jason Mielens, Liang Sun, Jason Baldridge. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

  2. Fill it up: Exploiting partial dependency annotations in a minimum spanning tree parser

    2016 · arXiv (Cornell University)

    Unsupervised models of dependency parsing typically require large amounts of clean, unlabeled data plus gold-standard part-of-speech tags. Adding indirect supervision (e.g. language universals and rules) can help, but we show that obtaining small amounts of …

  3. FusionSF: Fuse Heterogeneous Modalities in a Vector Quantized Framework for Robust Solar Power Forecasting

    2024 · arXiv (Cornell University)

    Accurate solar power forecasting is crucial to integrate photovoltaic plants into the electric grid, schedule and secure the power grid safety. This problem becomes more demanding for those newly installed solar plants which lack sufficient …

  4. Soft Shared Multi-Task Convolutional Network Based on the Attention Mechanism

    2023

    Rolling bearings are widely used and related to production safety, so bearing health status management is very important. In the bearing health management, fault diagnosis is the core problem, and residual lifetime (RUL) prediction is …

  5. Implementation of SLB for Public Cloud

    2024

    The large-scale migration and deployment of services to public clouds pose new challenges to the reliability and elastic scalability of public clouds. Server Load Balancing (SLB), as a traffic distribution technology, can route network service …

  6. LLM-Oriented Information Retrieval: A Denoising-First Perspective

    2026 · Rare & Special e-Zone (The Hong Kong University of Science and Technology)

    Modern information retrieval (IR) is no longer consumed primarily by humans but increasingly by large language models (LLMs) via retrieval-augmented generation (RAG) and agentic search. Unlike human users, LLMs are constrained by limited attention budgets …