scholarly journals Lifelong Domain Word Embedding via Meta-Learning

2018 ◽  
Author(s):  
Hu Xu ◽  
Bing Liu ◽  
Lei Shu ◽  
Philip S. Yu
Keyword(s):  
Lifelong Learning ◽  
Large Scale ◽  
General Purpose ◽  
Word Embedding ◽  
Experimental Results ◽  
Word Embeddings ◽  
High Quality ◽  
Domain Specific ◽  
The Past ◽  
Meta Learning

Learning high-quality domain word embeddings is important for achieving good performance in many NLP tasks. General-purpose embeddings trained on large-scale corpora are often sub-optimal for domain-specific applications. However, domain-specific tasks often do not have large in-domain corpora for training high-quality domain embeddings. In this paper, we propose a novel lifelong learning setting for domain embedding. That is, when performing the new domain embedding, the system has seen many past domains, and it tries to expand the new in-domain corpus by exploiting the corpora from the past domains via meta-learning. The proposed meta-learner characterizes the similarities of the contexts of the same word in many domain corpora, which helps retrieve relevant data from the past domains to expand the new domain corpus. Experimental results show that domain embeddings produced from such a process improve the performance of the downstream tasks.

scholarly journals Grounding Action Descriptions in Videos

2013 ◽  
Vol 1 ◽  
pp. 25-36 ◽  
Author(s):  
Michaela Regneri ◽  
Marcus Rohrbach ◽  
Dominikus Wetzel ◽  
Stefan Thater ◽  
Bernt Schiele ◽  
...  
Keyword(s):  
Natural Language ◽  
Recent Work ◽  
Visual Information ◽  
General Purpose ◽  
Experimental Results ◽  
High Quality ◽  
Improve Model ◽  
Model Predictions ◽  
Static Images

Recent work has shown that the integration of visual information into text-based models can substantially improve model predictions, but so far only visual information extracted from static images has been used. In this paper, we consider the problem of grounding sentences describing actions in visual information extracted from videos. We present a general purpose corpus that aligns high quality videos with multiple natural language descriptions of the actions portrayed in the videos, together with an annotation of how similar the action descriptions are to each other. Experimental results demonstrate that a text-based model of similarity between actions improves substantially when combined with visual information from videos depicting the described actions.

scholarly journals Lifelong Learning of Topics and Domain-Specific Word Embeddings

2021 ◽  
Author(s):  
Xiaorui Qin ◽  
Yuyin Lu ◽  
Yufu Chen ◽  
Yanghui Rao
Keyword(s):  
Lifelong Learning ◽  
Word Embeddings ◽  
Domain Specific

scholarly journals Obtaining High-Quality Label by Distinguishing between Easy and Hard Items in Crowdsourcing

2017 ◽  
Author(s):  
Wei Wang ◽  
Xiang-Yu Guo ◽  
Shao-Yuan Li ◽  
Yuan Jiang ◽  
Zhi-Hua Zhou
Keyword(s):  
Large Scale ◽  
Experimental Results ◽  
Training Set ◽  
High Quality ◽  
Quality Label ◽  
Large Scale Data ◽  
Voluntary Workers ◽  
Scale Data

Crowdsourcing systems make it possible to hire voluntary workers to label large-scale data by offering them small monetary payments. Usually, the taskmaster requires to collect high-quality labels, while the quality of labels obtained from the crowd may not satisfy this requirement. In this paper, we study the problem of obtaining high-quality labels from the crowd and present an approach of learning the difficulty of items in crowdsourcing, in which we construct a small training set of items with estimated difficulty and then learn a model to predict the difficulty of future items. With the predicted difficulty, we can distinguish between easy and hard items to obtain high-quality labels. For easy items, the quality of their labels inferred from the crowd could be high enough to satisfy the requirement; while for hard items, the crowd could not provide high-quality labels, it is better to choose a more knowledgable crowd or employ specialized workers to label them. The experimental results demonstrate that the proposed approach by learning to distinguish between easy and hard items can significantly improve the label quality.

scholarly journals Controlled growth of 2D ultrathin Ga2O3 crystals on liquid metal

2021 ◽  
Author(s):  
Menghan Li ◽  
Lin Li ◽  
Yixuan Fan ◽  
Le Huang ◽  
Dechao Geng ◽  
...  
Keyword(s):  
Liquid Metal ◽  
Surface Chemistry ◽  
Metal Oxides ◽  
Electronic Structures ◽  
Large Scale ◽  
Controlled Growth ◽  
High Quality ◽  
The Past

2D metal oxides (2DMOs) has drawn intensive interests in the past few years owing to their rich surface chemistry and unique electronic structures. Striving for large-scale and high-quality novel 2DMOs...

Genetic Parallel Programming: Design and Implementation

2006 ◽  
Vol 14 (2) ◽  
pp. 129-156 ◽  
Author(s):  
Sin Man Cheang ◽  
Kwong Sak Leung ◽  
Kin Hong Lee
Keyword(s):  
Integrated Circuits ◽  
Parallel Programming ◽  
High Speed ◽  
Large Scale ◽  
General Purpose ◽  
Computational Effort ◽  
Parallel Programs ◽  
Experimental Results ◽  
Benchmark Problems ◽  
Problem Solution

This paper presents a novel Genetic Parallel Programming (GPP) paradigm for evolving parallel programs running on a Multi-Arithmetic-Logic-Unit (Multi-ALU) Processor (MAP). The MAP is a Multiple Instruction-streams, Multiple Data-streams (MIMD), general-purpose register machine that can be implemented on modern Very Large-Scale Integrated Circuits (VLSIs) in order to evaluate genetic programs at high speed. For human programmers, writing parallel programs is more difficult than writing sequential programs. However, experimental results show that GPP evolves parallel programs with less computational effort than that of their sequential counterparts. It creates a new approach to evolving a feasible problem solution in parallel program form and then serializes it into a sequential programif required. The effectiveness and efficiency of GPP are investigated using a suite of 14 well-studied benchmark problems. Experimental results show that GPP speeds up evolution substantially.

Automated Subject Indexing of Domain Specific Collections Using Word Embeddings and General Purpose Thesauri

2019 ◽  
pp. 103-114
Author(s):  
Michalis Sfakakis ◽  
Leonidas Papachristopoulos ◽  
Kyriaki Zoutsou ◽  
Giannis Tsakonas ◽  
Christos Papatheodorou
Keyword(s):  
General Purpose ◽  
Word Embeddings ◽  
Domain Specific ◽  
Subject Indexing

scholarly journals Character n-Gram Embeddings to Improve RNN Language Models

2019 ◽  
Vol 33 ◽  
pp. 5074-5082 ◽  
Author(s):  
Sho Takase ◽  
Jun Suzuki ◽  
Masaaki Nagata
Keyword(s):  
Neural Network ◽  
Machine Translation ◽  
Recurrent Neural Network ◽  
Language Model ◽  
Language Modeling ◽  
Word Embedding ◽  
Experimental Results ◽  
Language Models ◽  
Word Embeddings ◽  
N Gram

This paper proposes a novel Recurrent Neural Network (RNN) language model that takes advantage of character information. We focus on character n-grams based on research in the field of word embedding construction (Wieting et al. 2016). Our proposed method constructs word embeddings from character ngram embeddings and combines them with ordinary word embeddings. We demonstrate that the proposed method achieves the best perplexities on the language modeling datasets: Penn Treebank, WikiText-2, and WikiText-103. Moreover, we conduct experiments on application tasks: machine translation and headline generation. The experimental results indicate that our proposed method also positively affects these tasks

scholarly journals Socialized Word Embeddings

2017 ◽  
Author(s):  
Ziqian Zeng ◽  
Yichun Yin ◽  
Yangqiu Song ◽  
Ming Zhang
Keyword(s):  
Social Media ◽  
Social Relationship ◽  
Large Scale ◽  
Language Use ◽  
Personal Characteristics ◽  
Word Embedding ◽  
Word Embeddings ◽  
Regularization Term ◽  
Local User

Word embeddings have attracted a lot of attention. On social media, each user’s language use can be significantly affected by the user’s friends. In this paper, we propose a socialized word embedding algorithm which can consider both user’s personal characteristics of language use and the user’s social relationship on social media. To incorporate personal characteristics, we propose to use a user vector to represent each user. Then for each user, the word embeddings are trained based on each user’s corpus by combining the global word vectors and local user vector. To incorporate social relationship, we add a regularization term to impose similarity between two friends. In this way, we can train the global word vectors and user vectors jointly. To demonstrate the effectiveness, we used the latest large-scale Yelp data to train our vectors, and designed several experiments to show how user vectors affect the results.

General-purpose statistical translation engine and domain specific texts

Terminology ◽  
2004 ◽  
Vol 10 (1) ◽  
pp. 131-153 ◽  
Author(s):  
Philippe Langlais ◽  
Michael Carl
Keyword(s):  
Error Rate ◽  
Statistical Machine Translation ◽  
Real Life ◽  
General Purpose ◽  
Word Error Rate ◽  
Accurate Evaluation ◽  
Domain Specific ◽  
The Past ◽  
The One ◽  
Open Question

The past decade has witnessed exciting work in the field of Statistical Machine Translation (SMT). However, accurate evaluation of its potential in real-life contexts is still an open question. In this study, we investigate the behavior of an SMT engine faced with a corpus far different from the one it has been trained on. We show that terminological databases are obvious resources that should be used to boost the performance of a statistical engine. We propose and evaluate one way of integrating terminology into a SMT engine which yields a significant reduction in word error rate.

Detecting “DeepFakes” in H.264 Video Data Using Compression Ghost Artifacts

2020 ◽  
Vol 2020 (4) ◽  
pp. 116-1-116-7
Author(s):  
Raphael Antonius Frick ◽  
Sascha Zmudzinski ◽  
Martin Steinebach
Keyword(s):  
Image Forensics ◽  
Video Data ◽  
Experimental Results ◽  
Video Sequences ◽  
The Internet ◽  
Video Content ◽  
High Quality ◽  
The Public

In recent years, the number of forged videos circulating on the Internet has immensely increased. Software and services to create such forgeries have become more and more accessible to the public. In this regard, the risk of malicious use of forged videos has risen. This work proposes an approach based on the Ghost effect knwon from image forensics for detecting forgeries in videos that can replace faces in video sequences or change the mimic of a face. The experimental results show that the proposed approach is able to identify forgery in high-quality encoded video content.

Sign in / Sign up

Export Citation Format

Share Document