scholarly journals Context-based Word Acquisition for Situated Dialogue in a Virtual World

2010 ◽  
Vol 37 ◽  
pp. 247-277 ◽  
Author(s):  
S. Qu ◽  
J. Y. Chai
Keyword(s):  
Virtual World ◽  
Language Production ◽  
Domain Knowledge ◽  
Contextual Information ◽  
Eye Gaze ◽  
Learning Approaches ◽  
New Words ◽  
Word Acquisition ◽  
Language Behavior ◽  
Situated Dialogue

To tackle the vocabulary problem in conversational systems, previous work has applied unsupervised learning approaches on co-occurring speech and eye gaze during interaction to automatically acquire new words. Although these approaches have shown promise, several issues related to human language behavior and human-machine conversation have not been addressed. First, psycholinguistic studies have shown certain temporal regularities between human eye movement and language production. While these regularities can potentially guide the acquisition process, they have not been incorporated in the previous unsupervised approaches. Second, conversational systems generally have an existing knowledge base about the domain and vocabulary. While the existing knowledge can potentially help bootstrap and constrain the acquired new words, it has not been incorporated in the previous models. Third, eye gaze could serve different functions in human-machine conversation. Some gaze streams may not be closely coupled with speech stream, and thus are potentially detrimental to word acquisition. Automated recognition of closely-coupled speech-gaze streams based on conversation context is important. To address these issues, we developed new approaches that incorporate user language behavior, domain knowledge, and conversation context in word acquisition. We evaluated these approaches in the context of situated dialogue in a virtual world. Our experimental results have shown that incorporating the above three types of contextual information significantly improves word acquisition performance.

Live-action mass-casualty training and virtual world training

2016 ◽  
Vol 60 (1) ◽  
pp. 2103-2107 ◽  
Author(s):  
Keith T. Shubeck ◽  
Scotty D. Craig ◽  
Xiangen Hu
Keyword(s):  
Virtual World ◽  
Domain Knowledge ◽  
Mass Casualty ◽  
Learning Technologies ◽  
Learning Needs ◽  
Web Based ◽  
Tutoring Systems ◽  
Aeromedical Evacuation ◽  
User Input ◽  
Live Action

Live-action training simulations with expert facilitators are considered by many to be the gold-standard in training environments. However, these training environments are expensive, provide many logistical challenges, and may not address the individual’s learning needs. Fortunately, advances in distance-based learning technologies have provided the foundation for inexpensive and effective learning environments that can simultaneously train and educate students on a much broader scale than live-action training environments. Specifically, intelligent tutoring systems (ITSs) have been proven to be very effective in improving learning outcomes. The Virtual Civilian Aeromedical Evacuation Sustainment Training (VCAEST) interface takes advantage of both of these technologies by enhancing a virtual world with a web-based ITS, AutoTutor LITE (Learning in Interactive Training Environments). AutoTutor LITE acts as a facilitator in the virtual world by providing just-in-time feedback, presenting essential domain knowledge, and by utilizing tutoring dialogues that automatically assess user input. This paper will discuss the results of an experimental evaluation of the VCAEST environment compared to an expert-led live-action training simulation.

Ensuring Students Engage with Ethical and Professional Practice Concepts

2009 ◽  
pp. 327-350
Author(s):  
J. Barrie Thompson
Keyword(s):  
Professional Practice ◽  
Teaching And Learning ◽  
Ethical Issues ◽  
Code Of Ethics ◽  
Contextual Information ◽  
Learning Approaches ◽  
International Model ◽  
Software Engineers ◽  
The Uk ◽  
The University

The teaching and learning of aspects related to ethics and professional practice present significant challenges to both staff and students as these topics are much more abstract than say software design and testing. The core of this chapter is an in-depth examination of how ethics and professional practice can be addressed in a very practical manner. To set the scene and provide contextual information the chapter commences with information on an international model of professionalism, a code of ethics for Software Engineers, and different teaching and learning approaches that can be employed when addressing ethical issues. The major part of the chapter is then devoted to detailing a particular teaching and leaning approach, which has been developed at the University of Sunderland in the UK. Finally conclusions, views on the present situation and future developments, and details of outstanding challenges are presented.

scholarly journals Literature mining for context-specific molecular relations using multimodal representations (COMMODAR)

2020 ◽  
Vol 21 (S5) ◽  
Author(s):  
Jaehyun Lee ◽  
Doheon Lee ◽  
Kwang Hyung Lee
Keyword(s):  
Biological Networks ◽  
Domain Knowledge ◽  
Contextual Information ◽  
Main Idea ◽  
Relation Extraction ◽  
Literature Mining ◽  
Computing Methodologies ◽  
Multimodal Representations ◽  
Relational Resources ◽  
Context Specific

Abstract Biological contextual information helps understand various phenomena occurring in the biological systems consisting of complex molecular relations. The construction of context-specific relational resources vastly relies on laborious manual extraction from unstructured literature. In this paper, we propose COMMODAR, a machine learning-based literature mining framework for context-specific molecular relations using multimodal representations. The main idea of COMMODAR is the feature augmentation by the cooperation of multimodal representations for relation extraction. We leveraged biomedical domain knowledge as well as canonical linguistic information for more comprehensive representations of textual sources. The models based on multiple modalities outperformed those solely based on the linguistic modality. We applied COMMODAR to the 14 million PubMed abstracts and extracted 9214 context-specific molecular relations. All corpora, extracted data, evaluation results, and the implementation code are downloadable at https://github.com/jae-hyun-lee/commodar. Ccs concepts • Computing methodologies~Information extraction • Computing methodologies~Neural networks • Applied computing~Biological networks.

scholarly journals Combined Self-Attention Mechanism for Chinese Named Entity Recognition in Military

2019 ◽  
Vol 11 (8) ◽  
pp. 180
Author(s):  
Fei Liao ◽  
Liangli Ma ◽  
Jingjing Pei ◽  
Linshan Tan
Keyword(s):  
Domain Knowledge ◽  
Short Term Memory ◽  
Contextual Information ◽  
Named Entity Recognition ◽  
Attention Mechanism ◽  
The Self ◽  
Entity Recognition ◽  
Named Entity ◽  
Vector Representations ◽  
The Military

Military named entity recognition (MNER) is one of the key technologies in military information extraction. Traditional methods for the MNER task rely on cumbersome feature engineering and specialized domain knowledge. In order to solve this problem, we propose a method employing a bidirectional long short-term memory (BiLSTM) neural network with a self-attention mechanism to identify the military entities automatically. We obtain distributed vector representations of the military corpus by unsupervised learning and the BiLSTM model combined with the self-attention mechanism is adopted to capture contextual information fully carried by the character vector sequence. The experimental results show that the self-attention mechanism can improve effectively the performance of MNER task. The F-score of the military documents and network military texts identification was 90.15% and 89.34%, respectively, which was better than other models.

Attentional priority of the agent in the acquisition of word reference

1985 ◽  
Vol 12 (1) ◽  
pp. 1-12 ◽  
Author(s):  
Janet Grace ◽  
George J. Suci
Keyword(s):  
Language Production ◽  
Nonsense Word ◽  
Event Perception ◽  
Word Acquisition ◽  
Response Recovery ◽  
The One ◽  
Modification Condition

ABSTRACTThe role of agent priority in event perception in word acquisition was investigated using 24 infants at the one-word stage of language production. Nonsense words were presented in narrations referring to agent, recipient or stationary nonsense puppet-actors in filmed events. The nonsense stimuli along with a sense word referring to a sense puppet were presented in a habituation series. Word acquisition was measured by the extent of response recovery to an incorrect pairing of a nonsense word with a sense referent, and by the number of infants accurately choosing named puppets. Both measures were significantly greater for puppets in agent roles than for other puppets. A speech modification condition (exaggerated intonation with repetition) held attention longer but did not facilitate acquisition.

scholarly journals A survey on Deep Learning Based Eye Gaze Estimation Methods

2021 ◽  
Vol 3 (3) ◽  
pp. 190-207
Author(s):  
S. K. B. Sangeetha
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Near Infrared ◽  
Eye Gaze ◽  
Infrared Image ◽  
Estimation Methods ◽  
Learning Technology ◽  
Learning Approaches ◽  
Gaze Tracking ◽  
Inference Models

In recent years, deep-learning systems have made great progress, particularly in the disciplines of computer vision and pattern recognition. Deep-learning technology can be used to enable inference models to do real-time object detection and recognition. Using deep-learning-based designs, eye tracking systems could determine the position of eyes or pupils, regardless of whether visible-light or near-infrared image sensors were utilized. For growing electronic vehicle systems, such as driver monitoring systems and new touch screens, accurate and successful eye gaze estimates are critical. In demanding, unregulated, low-power situations, such systems must operate efficiently and at a reasonable cost. A thorough examination of the different deep learning approaches is required to take into consideration all of the limitations and opportunities of eye gaze tracking. The goal of this research is to learn more about the history of eye gaze tracking, as well as how deep learning contributed to computer vision-based tracking. Finally, this research presents a generalized system model for deep learning-driven eye gaze direction diagnostics, as well as a comparison of several approaches.

scholarly journals Multi-label classification of research articles using Word2Vec and identification of similarity threshold

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ghulam Mustafa ◽  
Muhammad Usman ◽  
Lisu Yu ◽  
Muhammad Tanvir afzal ◽  
Muhammad Sulaiman ◽  
...  
Keyword(s):  
Digital Libraries ◽  
Domain Knowledge ◽  
Contextual Information ◽  
Threshold Value ◽  
Suggested Approach ◽  
General Terms ◽  
Statistical Measures ◽  
Current State ◽  
Average Accuracy ◽  
Domain Expertise

AbstractEvery year, around 28,100 journals publish 2.5 million research publications. Search engines, digital libraries, and citation indexes are used extensively to search these publications. When a user submits a query, it generates a large number of documents among which just a few are relevant. Due to inadequate indexing, the resultant documents are largely unstructured. Publicly known systems mostly index the research papers using keywords rather than using subject hierarchy. Numerous methods reported for performing single-label classification (SLC) or multi-label classification (MLC) are based on content and metadata features. Content-based techniques offer higher outcomes due to the extreme richness of features. But the drawback of content-based techniques is the unavailability of full text in most cases. The use of metadata-based parameters, such as title, keywords, and general terms, acts as an alternative to content. However, existing metadata-based techniques indicate low accuracy due to the use of traditional statistical measures to express textual properties in quantitative form, such as BOW, TF, and TFIDF. These measures may not establish the semantic context of the words. The existing MLC techniques require a specified threshold value to map articles into predetermined categories for which domain knowledge is necessary. The objective of this paper is to get over the limitations of SLC and MLC techniques. To capture the semantic and contextual information of words, the suggested approach leverages the Word2Vec paradigm for textual representation. The suggested model determines threshold values using rigorous data analysis, obviating the necessity for domain expertise. Experimentation is carried out on two datasets from the field of computer science (JUCS and ACM). In comparison to current state-of-the-art methodologies, the proposed model performed well. Experiments yielded average accuracy of 0.86 and 0.84 for JUCS and ACM for SLC, and 0.81 and 0.80 for JUCS and ACM for MLC. On both datasets, the proposed SLC model improved the accuracy up to 4%, while the proposed MLC model increased the accuracy up to 3%.

scholarly journals Redefining Wireless Communication for 6G:Signal Processing Meets Deep Learning with Deep Unfolding

2021 ◽  
Author(s):  
Anu Jagannath ◽  
Jithin Jagannath
Keyword(s):  
Signal Processing ◽  
Deep Learning ◽  
Wireless Communication ◽  
Communication Systems ◽  
Domain Knowledge ◽  
Physical Layer ◽  
Learning Approaches ◽  
Communication Architecture ◽  
Recent Emergence ◽  
Rate Improvement

The year 2019 witnessed the rollout of the 5G standard, which promises to offer significant data rate improvement over 4G. While 5G is still in its infancy, there has been an increased shift in the research community for communication technologies beyond 5G. The recent emergence of machine learning approaches for enhancing wireless communications and empowering them with much-desired intelligence holds immense potential for redefining wireless communication for 6G. The evolving communication systems will be bottlenecked in terms of latency, throughput, and reliability by the underlying signal processing at the physical layer. In this position paper, we motivate the need to redesign iterative signal processing algorithms by leveraging deep unfolding techniques to fulfill the physical layer requirements for 6G networks. To this end, we begin by presenting the service requirements and the key challenges posed by the envisioned 6G communication architecture. We outline the deficiencies of the traditional algorithmic principles and data-hungry deep learning (DL) approaches in the context of 6G networks. Specifically, deep unfolded signal processing is presented by sketching the interplay between domain knowledge and DL. The deep unfolded approaches reviewed in this article are positioned explicitly in the context of the requirements imposed by the next generation of cellular networks. Finally, this article motivates open research challenges to truly realize hardware-efficient edge intelligence for future 6G networks.<br>

scholarly journals Biomedical named entity recognition using deep neural networks with contextual information

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Hyejin Cho ◽  
Hyunju Lee
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Contextual Information ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Learning Approaches ◽  
Short Term ◽  
Term Memory ◽  
Named Entity ◽  
Long Short Term Memory

Abstract Background In biomedical text mining, named entity recognition (NER) is an important task used to extract information from biomedical articles. Previously proposed methods for NER are dictionary- or rule-based methods and machine learning approaches. However, these traditional approaches are heavily reliant on large-scale dictionaries, target-specific rules, or well-constructed corpora. These methods to NER have been superseded by the deep learning-based approach that is independent of hand-crafted features. However, although such methods of NER employ additional conditional random fields (CRF) to capture important correlations between neighboring labels, they often do not incorporate all the contextual information from text into the deep learning layers. Results We propose herein an NER system for biomedical entities by incorporating n-grams with bi-directional long short-term memory (BiLSTM) and CRF; this system is referred to as a contextual long short-term memory networks with CRF (CLSTM). We assess the CLSTM model on three corpora: the disease corpus of the National Center for Biotechnology Information (NCBI), the BioCreative II Gene Mention corpus (GM), and the BioCreative V Chemical Disease Relation corpus (CDR). Our framework was compared with several deep learning approaches, such as BiLSTM, BiLSTM with CRF, GRAM-CNN, and BERT. On the NCBI corpus, our model recorded an F-score of 85.68% for the NER of diseases, showing an improvement of 1.50% over previous methods. Moreover, although BERT used transfer learning by incorporating more than 2.5 billion words, our system showed similar performance with BERT with an F-scores of 81.44% for gene NER on the GM corpus and a outperformed F-score of 86.44% for the NER of chemicals and diseases on the CDR corpus. We conclude that our method significantly improves performance on biomedical NER tasks. Conclusion The proposed approach is robust in recognizing biological entities in text.

Sign in / Sign up

Export Citation Format

Share Document