scholarly journals Self-Paced Active Learning: Query the Right Thing at the Right Time

2019 ◽  
Vol 33 ◽  
pp. 5117-5124
Author(s):  
Ying-Peng Tang ◽  
Sheng-Jun Huang
Keyword(s):  
Active Learning ◽  
State Of The Art ◽  
Early Stage ◽  
Experimental Results ◽  
Learning Approach ◽  
Learning Methods ◽  
Batch Mode ◽  
Potential Value ◽  
The Right

Active learning queries labels from the oracle for the most valuable instances to reduce the labeling cost. In many active learning studies, informative and representative instances are preferred because they are expected to have higher potential value for improving the model. Recently, the results in self-paced learning show that training the model with easy examples first and then gradually with harder examples can improve the performance. While informative and representative instances could be easy or hard, querying valuable but hard examples at early stage may lead to waste of labeling cost. In this paper, we propose a self-paced active learning approach to simultaneously consider the potential value and easiness of an instance, and try to train the model with least cost by querying the right thing at the right time. Experimental results show that the proposed approach is superior to state-of-the-art batch mode active learning methods.

scholarly journals Loss-based active learning via double-branch deep network

2021 ◽  
Vol 18 (5) ◽  
pp. 172988142110449
Author(s):  
Qiang Fang ◽  
Xin Xu ◽  
Dengqing Tang
Keyword(s):  
Active Learning ◽  
Visual Recognition ◽  
State Of The Art ◽  
Experimental Results ◽  
Research Interest ◽  
Selection Strategy ◽  
Network Architectures ◽  
Data Annotation ◽  
Deep Network ◽  
Effectiveness And Efficiency

Due to the limitation of data annotation and the ability of dealing with label-efficient problems, active learning has received lots of research interest in recent years. Most of the existing approaches focus on designing a different selection strategy to achieve better performance for special tasks; however, the performance of the strategy still needs to be improved. In this work, we focus on improving the performance of active learning and propose a loss-based strategy that learns to predict target losses of unlabeled inputs to select the most uncertain samples, which is designed to learn a better selection strategy based on a double-branch deep network. Experimental results on two visual recognition tasks show that our approach achieves the state-of-the-art performance compared with previous methods. Moreover, our approach is also robust to different network architectures, biased initial labels, noisy oracles, or sampling budget sizes, and the complexity is also competitive, which demonstrates the effectiveness and efficiency of our proposed approach.

scholarly journals RefNet: A Reference-Aware Network for Background Based Conversation

2020 ◽  
Vol 34 (05) ◽  
pp. 8496-8503 ◽  
Author(s):  
Chuan Meng ◽  
Pengjie Ren ◽  
Zhumin Chen ◽  
Christof Monz ◽  
Jun Ma ◽  
...  
Keyword(s):  
Semantic Information ◽  
State Of The Art ◽  
Experimental Results ◽  
Background Information ◽  
Art Methods ◽  
The Right

Existing conversational systems tend to generate generic responses. Recently, Background Based Conversation (BBCs) have been introduced to address this issue. Here, the generated responses are grounded in some background information. The proposed methods for BBCs are able to generate more informative responses, however, they either cannot generate natural responses or have difficulties in locating the right background information. In this paper, we propose a Reference-aware Network (RefNet) to address both issues. Unlike existing methods that generate responses token by token, RefNet incorporates a novel reference decoder that provides an alternative way to learn to directly select a semantic unit (e.g., a span containing complete semantic information) from the background. Experimental results show that RefNet significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, indicating that RefNet can generate more appropriate and human-like responses.

scholarly journals Classifying Non-Sentential Utterances in Dialogue: A Machine Learning Approach

2007 ◽  
Vol 33 (3) ◽  
pp. 397-427 ◽  
Author(s):  
Raquel Fernández ◽  
Jonathan Ginzburg ◽  
Shalom Lappin
Keyword(s):  
Machine Learning ◽  
Pilot Study ◽  
Full Range ◽  
Learning Approach ◽  
Learning Methods ◽  
Fine Grained ◽  
Machine Learning Methods ◽  
Machine Learning Approach ◽  
The Right

In this article we use well-known machine learning methods to tackle a novel task, namely the classification of non-sentential utterances (NSUs) in dialogue. We introduce a fine-grained taxonomy of NSU classes based on corpus work, and then report on the results of several machine learning experiments. First, we present a pilot study focused on one of the NSU classes in the taxonomy—bare wh-phrases or “sluices”—and explore the task of disambiguating between the different readings that sluices can convey. We then extend the approach to classify the full range of NSU classes, obtaining results of around an 87% weighted F-score. Thus our experiments show that, for the taxonomy adopted, the task of identifying the right NSU class can be successfully learned, and hence provide a very encouraging basis for the more general enterprise of fully processing NSUs.

scholarly journals Campaign Simulation for American Government: An Active Learning Approach to Campaigns and Elections

2016 ◽  
Vol 49 (04) ◽  
pp. 872-875 ◽  
Author(s):  
Gayle Alberda
Keyword(s):  
Experimental Design ◽  
Active Learning ◽  
Learning Approach ◽  
American Government ◽  
Learning Methods ◽  
Campaigns And Elections ◽  
Traditional Lectures

ABSTRACTInstructors of American government are challenged with teaching students from a variety of disciplines. Utilizing active learning methods captures students in a manner traditional lectures cannot. For this study I employed an experimental design to assess a campaign simulation used in an Introduction to American Government course. Results show the simulation aided in students’ learning about campaigns and elections.

Query Expansion based on Central Tendency and PRF for Monolingual Retrieval

2016 ◽  
Vol 6 (4) ◽  
pp. 30-50
Author(s):  
Rekha Vaidyanathan ◽  
Sujoy Das ◽  
Namita Srivastava
Keyword(s):  
Statistical Method ◽  
Query Expansion ◽  
State Of The Art ◽  
The State ◽  
Experimental Results ◽  
Central Tendency ◽  
Relevant Document ◽  
Retrieval Engine ◽  
The Right ◽  
A Performance

Query Expansion is the process of selecting relevant words that are closest in meaning and context to that of the keyword(s) of query. In this paper, a statistical method of automatically selecting contextually related words for expansion, after identifying a pattern in their score, is proposed. Words appearing in top 10 relevant document is given a score w.r.t partitions they appear in. Proposed statistical method, identifies a pattern of central tendency in the high scores and selects the right group of words for query expansion. The objective of the method is to keep the expanded query with minimum words (light), and still give statistically significant MAP values compared to the original query. Experimental results show 17-21% improvement of MAP over the original unexpanded query as baseline but achieves a performance similar to that of the state of the art query expansion models - Bo1 and KL. FIRE 2011 Adhoc English and Hindi data for 50 topics each were used for experiments with Terrier as the Retrieval Engine.

Using Pre-trained Language Model to Enhance Active Learning for Sentence Matching

2022 ◽  
Vol 21 (2) ◽  
pp. 1-19
Author(s):  
Guirong Bai ◽  
Shizhu He ◽  
Kang Liu ◽  
Jun Zhao
Keyword(s):  
Active Learning ◽  
Language Model ◽  
Experimental Results ◽  
Language Models ◽  
Data Driven ◽  
Learning Approach ◽  
Sentence Matching ◽  
Learning Language

Active learning is an effective method to substantially alleviate the problem of expensive annotation cost for data-driven models. Recently, pre-trained language models have been demonstrated to be powerful for learning language representations. In this article, we demonstrate that the pre-trained language model can also utilize its learned textual characteristics to enrich criteria of active learning. Specifically, we provide extra textual criteria with the pre-trained language model to measure instances, including noise, coverage, and diversity. With these extra textual criteria, we can select more efficient instances for annotation and obtain better results. We conduct experiments on both English and Chinese sentence matching datasets. The experimental results show that the proposed active learning approach can be enhanced by the pre-trained language model and obtain better performance.

Query Expansion Based on Central Tendency and PRF for Monolingual Retrieval

2018 ◽  
pp. 479-501
Author(s):  
Rekha Vaidyanathan ◽  
Sujoy Das ◽  
Namita Srivastava
Keyword(s):  
Statistical Method ◽  
Query Expansion ◽  
State Of The Art ◽  
The State ◽  
Experimental Results ◽  
Central Tendency ◽  
Relevant Document ◽  
Retrieval Engine ◽  
The Right ◽  
A Performance

Query Expansion is the process of selecting relevant words that are closest in meaning and context to that of the keyword(s) of query. In this paper, a statistical method of automatically selecting contextually related words for expansion, after identifying a pattern in their score, is proposed. Words appearing in top 10 relevant document is given a score w.r.t partitions they appear in. Proposed statistical method, identifies a pattern of central tendency in the high scores and selects the right group of words for query expansion. The objective of the method is to keep the expanded query with minimum words (light), and still give statistically significant MAP values compared to the original query. Experimental results show 17-21% improvement of MAP over the original unexpanded query as baseline but achieves a performance similar to that of the state of the art query expansion models - Bo1 and KL. FIRE 2011 Adhoc English and Hindi data for 50 topics each were used for experiments with Terrier as the Retrieval Engine.

scholarly journals Collaboration Based Multi-Label Learning

2019 ◽  
Vol 33 ◽  
pp. 3550-3557 ◽  
Author(s):  
Lei Feng ◽  
Bo An ◽  
Shuo He
Keyword(s):  
Prior Knowledge ◽  
State Of The Art ◽  
Experimental Results ◽  
Sparse Reconstruction ◽  
Learning Approach ◽  
Hypothesis Space ◽  
Explicitly Correlated ◽  
Label Correlations ◽  
Novel Method ◽  
Model Training

It is well-known that exploiting label correlations is crucially important to multi-label learning. Most of the existing approaches take label correlations as prior knowledge, which may not correctly characterize the real relationships among labels. Besides, label correlations are normally used to regularize the hypothesis space, while the final predictions are not explicitly correlated. In this paper, we suggest that for each individual label, the final prediction involves the collaboration between its own prediction and the predictions of other labels. Based on this assumption, we first propose a novel method to learn the label correlations via sparse reconstruction in the label space. Then, by seamlessly integrating the learned label correlations into model training, we propose a novel multi-label learning approach that aims to explicitly account for the correlated predictions of labels while training the desired model simultaneously. Extensive experimental results show that our approach outperforms the state-of-the-art counterparts.

scholarly journals An Active Learning Approach with Uncertainty, Representativeness, and Diversity

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Tianxu He ◽  
Shukui Zhang ◽  
Jie Xin ◽  
Pengpeng Zhao ◽  
Jian Wu ◽  
...  
Keyword(s):  
Active Learning ◽  
Clustering Algorithm ◽  
Ad Hoc ◽  
State Of The Art ◽  
The Internet ◽  
Learning Approach ◽  
Learning Approaches ◽  
Learning Framework ◽  
Query Selection ◽  
The Internet Of Things

Big data from the Internet of Things may create big challenge for data classification. Most active learning approaches select either uncertain or representative unlabeled instances to query their labels. Although several active learning algorithms have been proposed to combine the two criteria for query selection, they are usually ad hoc in finding unlabeled instances that are both informative and representative and fail to take the diversity of instances into account. We address this challenge by presenting a new active learning framework which considers uncertainty, representativeness, and diversity creation. The proposed approach provides a systematic way for measuring and combining the uncertainty, representativeness, and diversity of an instance. Firstly, use instances’ uncertainty and representativeness to constitute the most informative set. Then, use the kernelk-means clustering algorithm to filter the redundant samples and the resulting samples are queried for labels. Extensive experimental results show that the proposed approach outperforms several state-of-the-art active learning approaches.

scholarly journals A Multi-Task Approach to Open Domain Suggestion Mining (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13817-13818
Author(s):  
Minni Jain ◽  
Maitree Leekha ◽  
Mononito Goswami
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Class Imbalance ◽  
Sampling Technique ◽  
Experimental Results ◽  
Single Domain ◽  
Learning Approach ◽  
Open Domain ◽  
Consumer Reviews ◽  
Multiple Domains

Consumer reviews online may contain suggestions useful for improving the target products and services. Mining suggestions is challenging because the field lacks large labelled and balanced datasets. Furthermore, most prior studies have only focused on mining suggestions in a single domain. In this work, we introduce a novel up-sampling technique to address the problem of class imbalance, and propose a multi-task deep learning approach for mining suggestions from multiple domains. Experimental results on a publicly available dataset show that our up-sampling technique coupled with the multi-task framework outperforms state-of-the-art open domain suggestion mining models in terms of the F-1 measure and AUC.

Sign in / Sign up

Export Citation Format

Share Document