Related papers: Efficient EUD Parsing
Edge computing is a distributed computing paradigm that brings computation and data storage closer to the user's geographical location to improve response times and save bandwidth. It also helps to power a variety of applications requiring…
Classically, planning tasks are studied as a two-step process: plan creation and plan execution. In situations where plan creation is slow (for example, due to expensive information access or complex constraints), a natural speed-up tactic…
We present Entropy Adaptive Decoding (EAD), a novel approach for efficient language model inference that dynamically switches between different-sized models based on prediction uncertainty. By monitoring rolling entropy in model logit…
We present a novel and systematic method, called Superfast Selection, for selecting the "optimal split" for decision tree and feature selection algorithms over tabular data. The method speeds up split selection on a single feature by…
We propose a novel constituency parsing model that casts the parsing problem into a series of pointing tasks. Specifically, our model estimates the likelihood of a span being a legitimate tree constituent via the pointing score…
Given the proximity of many wireless users and their diversity in consuming local resources (e.g., data-plans, computation and energy resources), device-to-device (D2D) resource sharing is a promising approach towards realizing a sharing…
Computational efficiency is a major bottleneck in using classic graph-based approaches for semi-supervised learning on datasets with a large number of unlabeled examples. Known techniques to improve efficiency typically involve an…
In this paper, we present an ensemble approach for the NL4Opt competition subtask 1(NER task). For this task, we first fine tune the pretrained language models based on the competition dataset. Then we adopt differential learning rates and…
Training general agents to follow complex instructions (tasks) in intricate environments (levels) remains a core challenge in reinforcement learning. Random sampling of task-level pairs often produces unsolvable combinations, highlighting…
This paper describes the NiuTrans system for the WMT21 translation efficiency task (http://statmt.org/wmt21/efficiency-task.html). Following last year's work, we explore various techniques to improve efficiency while maintaining translation…
Real-time semantic segmentation plays an important role in practical applications such as self-driving and robots. Most semantic segmentation research focuses on improving estimation accuracy with little consideration on efficiency. Several…
The need to identify graphs with small structural distances from a query arises in domains such as biology, chemistry, recommender systems, and social network analysis. Among several methods for measuring inter-graph distance, Graph Edit…
Neural Architecture Search (NAS) has shown excellent results in designing architectures for computer vision problems. NAS alleviates the need for human-defined settings by automating architecture design and engineering. However, NAS methods…
This paper builds off recent work from Kiperwasser & Goldberg (2016) using neural attention in a simple graph-based dependency parser. We use a larger but more thoroughly regularized parser than other recent BiLSTM-based approaches, with…
The ability to perform pixel-wise semantic segmentation in real-time is of paramount importance in mobile applications. Recent deep neural networks aimed at this task have the disadvantage of requiring a large number of floating point…
Intermediate-task transfer can benefit a wide range of NLP tasks with properly selected source datasets. However, it is computationally infeasible to experiment with all intermediate transfer combinations, making choosing a useful source…
As illustrated by the emergence of a class of new languages and runtimes, it is expected that a large portion of the programs to run on extreme scale computers will need to be written as graphs of event-driven tasks (EDTs). EDT runtime…
Modern language models (LMs) increasingly require two critical resources: computational resources and data resources. Data selection techniques can effectively reduce the amount of training data required for fine-tuning LMs. However, their…
We propose an efficient neural framework for sentence-level discourse analysis in accordance with Rhetorical Structure Theory (RST). Our framework comprises a discourse segmenter to identify the elementary discourse units (EDU) in a text,…
Diffusion models have emerged as the mainstream approach for visual generation. However, these models typically suffer from sample inefficiency and high training costs. Consequently, methods for efficient finetuning, inference and…