检索结果-内蒙古大学图书馆

1st ACM International workshop on Multimodal Conversational AI, MuCAI 2020

作者： Popovic, Ilja Culibrk, Dubravko Mirkovic, Milan Vukmirovic, Srdjan Cinteraction Novi Sad Serbia University of Novi Sad and Cinteraction Novi Sad Serbia

ISBN: (纸本)9781450381567

Conversational emotion and sentiment analysis approaches rely on natural language Understanding (NLU) and audio processing components to achieve the goal of detecting emotions and sentiment based on what is being said. While there has been marked progress in pushing the state-of-the-art of theses methods on benchmark multimodal data sets, such as the Multimodal EmotionLines Dataset (MELD), the advances still seem to lag behind what has been achieved in the domain of mainstream Automatic Speech Recognition (ASR) and NLU applications and we were unable to identify any widely used products, services or production-ready systems that would enable the user to reliably detect emotions from audio recordings of multi-party conversations. Published, state-of-the-art scientific studies of multi-view emotion recognition seem to take it for granted that a human-generated or edited transcript is available as input to the NLU modules, providing no information of what happens in a realistic application scenario, where audio only is available and the NLU processing has to rely on text generated by ASR. Motivated by this insight, we present a study designed to evaluate the possibility of applying widely-used state-of-the-art commercial ASR products as the initial audio processing component in an emotion-from-speech detection system. We propose an approach which relies on commercially available products and services, such as Google Speech-to-Text, Mozilla DeepSpeech and the NVIDIA NeMo toolkit to process the audio and applies state-of-the-art NLU approaches for emotion recognition, in order to quickly create a robust, production-ready emotion-from-speech detection system applicable to multi-party conversations. © 2020 ACM.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Identifying personal experience tweets of medication effects using pre-trained RoBERTa language model and its updating 11

Identifying personal experience tweets of medication effects...

引用

11th International workshop on Health Text Mining and Information Analysis, LOUHI 2020, co-located with EMNLP 2020

作者： Zhu, Minghao Song, Youzhe Jin, Ge Jiang, Keyuan Donghua University Shanghai China Purdue University Northwest HammondIN United States

ISBN: (纸本)9781952148811

Post-market surveillance, the practice of monitoring the safe use of pharmaceutical drugs is an important part of pharmacovigilance. Being able to collect personal experience related to pharmaceutical product use could help us gain insight into how the human body reacts to different medications. Twitter, a popular social media service, is being considered as an important alternative data source for collecting personal experience information with medications. Identifying personal experience tweets is a challenging classification task in natural language processing. In this study, we utilized three methods based on Facebook's Robustly Optimized BERT Pretraining Approach (RoBERTa) to predict personal experience tweets related to medication use: the first one combines the pre-trained RoBERTa model with a classifier, the second combines the updated pre-trained RoBERTa model using a corpus of unlabeled tweets with a classifier, and the third combines the RoBERTa model that was trained with our unlabeled tweets from scratch with the classifier too. Our results show that all of these approaches outperform the published methods (Word Embedding + LSTM) in classification performance (p © 2020 Association for Computational Linguistics

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Data-driven Learning to Predict WAN Network Traffic 3

Data-driven Learning to Predict WAN Network Traffic

引用

3rd International workshop on Systems and Network Telemetry and Analytics (SNTA)

作者： Krishnaswamy, Nandini Kiran, Mariam Singh, Kunal Mohammed, Bashir Lawrence Berkeley Natl Lab Berkeley CA 94720 USA Univ Calif Berkeley EECS Berkeley CA USA

ISBN: (纸本)9781450379809

In this paper, we explore both statistical and deep learning approaches for multi-step predictions in WAN traffic traces. Estimating future traffic can help improve link usage and optimize bandwidth utilization. In this paper, we study real network traces from a real WAN research network. We use Fourier analysis to present variation among the traffic traces, extracting daily and weekly peak frequencies per trace. We also develop statistical time-series methods, ARIMA and Holt-Winters, and three LSTM-based approaches with various neural network architectures (Simple, Stacked and S2S LSTM), to forecast and compare the accuracies between them. With efforts to find a data-driven learning solution, we find that deep learning approaches can learn traffic patterns and provide more accurate predictions than ARIMA and Holt-Winters. Our results show that predictions are improved at an average of 70% or more. We further discuss the challenges of building these, their deployment and how these can help improve network utilization for future planning problems.

关键词： intent-based networking natural language processing smart instrumentation

来源：评论

学校读者我要写书评

暂无评论

Deep learning with language models improves named entity recognition for PharmaCoNER

引用

BMC BIOINFORMATICS 2021年第SUPPL 1期22卷 602-602页

作者： Sun, Cong Yang, Zhihao Wang, Lei Zhang, Yin Lin, Hongfei Wang, Jian Dalian Univ Technol Sch Comp Sci & Technol Dalian Peoples R China Beijing Inst Hlth Adm & Med Informat Beijing Peoples R China

Background The recognition of pharmacological substances, compounds and proteins is essential for biomedical relation extraction, knowledge graph construction, drug discovery, as well as medical question answering. Although considerable efforts have been made to recognize biomedical entities in English texts, to date, only few limited attempts were made to recognize them from biomedical texts in other languages. PharmaCoNER is a named entity recognition challenge to recognize pharmacological entities from Spanish texts. Because there are currently abundant resources in the field of natural language processing, how to leverage these resources to the PharmaCoNER challenge is a meaningful study. methods Inspired by the success of deep learning with language models, we compare and explore various representative BERT models to promote the development of the PharmaCoNER task. Results The experimental results show that deep learning with language models can effectively improve model performance on the PharmaCoNER dataset. Our method achieves state-of-the-art performance on the PharmaCoNER dataset, with a max F1-score of 92.01%. Conclusion For the BERT models on the PharmaCoNER dataset, biomedical domain knowledge has a greater impact on model performance than the native language (i.e., Spanish). The BERT models can obtain competitive performance by using WordPiece to alleviate the out of vocabulary limitation. The performance on the BERT model can be further improved by constructing a specific vocabulary based on domain knowledge. Moreover, the character case also has a certain impact on model performance.

关键词： Named entity recognition NER language model BERT Text mining

来源：评论

学校读者我要写书评

暂无评论

A comparative study of approaches for the diachronic analysis of the Italian language 4

A comparative study of approaches for the diachronic analysi...

引用

4th workshop on natural language for Artificial Intelligence, NL4AI 2020

作者： Cassotti, Pierluigi Basile, Pierpaolo De Gemmis, Marco Semeraro, Giovanni Department of Computer Science University of Bari Aldo Moro Via E. Orabona 4 Bari70126 Italy

In recent years, there has been a significant increase in interest in lexical semantic change detection. Many are the existing approaches, data used, and evaluation strategies to detect semantic drift. Most of those approaches rely on diachronic word embeddings. Some of them are created as post-processing of static word embeddings, while others produce dynamic word embeddings where vectors share the same geometric space for all time slices. The large majority of the methods use English as the target language for the diachronic analysis, while other languages remain under-explored. In this work, we compare state-of-the-art approaches in computational historical linguistics to evaluate the pros and cons of each model, and we present the results of an in-depth analysis conducted using an Italian diachronic corpus. Specifically, several approaches based on both static embeddings and dynamic ones are implemented and evaluated by using the Kronos-It dataset. We train all word embeddings on the Italian Google n-gram corpus. The main result of the evaluation is that all approaches fail to significantly reduce the number of false-positive change points, which confirms that lexical semantic change is still a challenging task. Copyright ©2020 for this paper by its authors.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Hybrid question answering system based on natural language processing and SPARQL query 1

Hybrid question answering system based on natural language p...

引用

Joint 1st International workshop on the Semantic Descriptor, Semantic Modeling and Mapping for Humanlike Perception and Navigation of Mobile Robots toward Large Scale Long-Term Autonomy and the 3rd International workshop on the Applications of Knowledge Representation and Semantic Technologies in Robotics, SDMM 2019 and AnSWeR 2019

作者： Rajosoa, Mickael Hantach, Rim Abbes, Sarra Ben Calvez, Philippe CSAI LAB ENGIE France

Chatbot is a conversational agent that communicates with users based on natural language. It is founded on a question answering system which tries to understand the intent of the user. Several chatbot methods deal with a model based template of question answering. However, these approaches are not able to cope with various questions and can affect the quality of the results. To address this issue, we propose a new semantic question answering approach combining natural language processing (NLP) methods and Semantic Web techniques to analyze user’s question and transform it into SPARQL query. An ontology has been developed to represent the domain knowledge of the chatbot. Experimentations show that our approach outperforms state of the art methods. Copyright © by the paper’s authors.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

The Learner Data Institute: Big Data, Research Challenges, & Science Convergence in Educational Data Science EDM 2020 workshop Description 13

The Learner Data Institute: Big Data, Research Challenges, &...

引用

13th International Conference on Educational Data Mining, EDM 2020

作者： Rus, Vasile Fancsali, Stephen E. University of Memphis United States Carnegie Learning Inc. United States

ISBN: (纸本)9781733673617

We describe a half-day online workshop for researchers interested in learning about—and contributing to—the work of the Learner Data Institute (LDI), an initiative funded by the U.S. National Science Foundation (NSF) and based at the Institute for Intelligent Systems, University of Memphis, in collaboration with Carnegie Learning, Inc., and other partners. LDI’s mission is to foster and support science convergence to address major challenges in learning with technology (online and blended) through an expanding, global network of expert panels, school-based practitioners, interdisciplinary research teams, and task-oriented special interest groups. Founding members of the LDI have been working together to plan mechanisms and processes for building shared understanding, and for exploring methods of extracting and packaging actionable knowledge from the massive datasets generated by current computer-supported instructional systems and from the stores of text, sound, graphics, video, and other data modalities that are rapidly accumulating on cloud-based servers around the world. The community at large is invited to participate in the workshop to hear about our work, help us refine our ideas through paper and talk contributions, and explore how they too can become involved in this important new enterprise. © 2020 proceedings of the 13th International Conference on Educational Data Mining, EDM 2020. All rights reserved.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Development of the Speech-to-Text Chatbot Interface based on Google API 8

Development of the Speech-to-Text Chatbot Interface Based on...

引用

8th International Conference on Mathematics, Information Technologies, Education (MoMLeT and DS)

作者： Shakhovska, Nataliya Basystiuk, Oleh Shakhovska, Khrystyna Lviv Polytech Natl Univ UA-79013 Lvov Ukraine

The paper describes possibilities, which are provided by open APIs, and how to use them for creating unified interfaces using the example of our bot based on Google API. In last decade AI technologies became widespread and easy to implement and use. One of the most perspective technology in the AI field is speech recognition as part of natural language processing. New speech recognition technologies and methods will become a central part of future life because they save a lot of communication time, replacing common texting with voice/audio. In addition, this paper explores the advantages and disadvantages of well- known chatbots. The method of their improvement is built. The algorithms of Rabin-Karp and Knut-Pratt are used. The time complexity of proposed algorithm is compared with existed one.

关键词： natural language processing speech-to-text Google API Python Flask chatbot hashing time complexity prefix-function

来源：评论

学校读者我要写书评

暂无评论

Reflex Intellectual Text processing Systems: natural language Text Addressing 8

Reflex Intellectual Text Processing Systems: Natural Languag...

引用

8th International Conference on Mathematics, Information Technologies, Education (MoMLeT and DS)

作者： Lenkov, Serhii Kubyavka, Mykola Kubiavka, Liubov Lenkov, Yevhen Shevchuk, Valerii Kyiv Natl Taras Shevchenko Univ Mil Inst Kiev Ukraine Kyiv Natl Taras Shevchenko Univ Kiev Ukraine Cent Res Inst Armed Forces Kiev Ukraine Univ State Fiscal Serv Irpin Ukraine

The article describes the method of automatic response to the content of the text of the message, which was based on a probabilistic-reflexive approach. The reflexive approach provided the choice of the most probable response to the set of input influences, with known probabilities of choosing the response for each input effect, as well as some combinations of input influences, and the method developed on its basis allowed to automatically determine the destination of the analyzed text.

关键词： Information Technology natural language text reflexive approach methods of information management

来源：评论

学校读者我要写书评

暂无评论

Happy together: Learning and understanding appraisal from natural language 2

Happy together: Learning and understanding appraisal from na...

引用

2nd workshop on Affective Content Analysis, AffCon 2019

作者： Rajendran, Arun Zhang, Chiyu Abdul-Mageed, Muhammad Natural Language Processing Lab University of British Columbia Canada

In this paper, we explore various approaches for learning two types of appraisal components from happy language. We focus on 'agency' of the author and the 'sociality' involved in happy moments based on the HappyDB dataset. We develop models based on deep neural networks for the task, including uni- and bi-directional long short-term memory networks, with and without attention. We also experiment with a number of novel embedding methods, such as embedding from neural machine translation (as in CoVe) and embedding from language models (as in ELMo). We compare our results to those acquired by several traditional machine learning methods. Our best models achieve 87.97% accuracy on agency and 93.13% accuracy on sociality, both of which are significantly higher than our baselines. © 2019 CEUR-WS. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：