检索结果-内蒙古大学图书馆

5th workshop on Clinical natural language processing, ClinicalNLP 2023. held at ACL 2023

作者： Naseem, Usman thapa, Surendrabikram Zhang, Qi Hu, Liang Masood, Anum Nasim, Mehwish University of Sydney Australia Virginia Tech United States Tongji University China DeepBlue Academy of Sciences China Norwegian University of Science and Technology Norway University of Western Australia Australia Flinders University Australia

ISBN: (纸本)9781959429883

graph-based techniques have gained traction for representing and analyzing data in various natural language processing (NLP) tasks. Knowledge graph-based language representation models have shown promising results in leveraging domain-specific knowledge for NLP tasks, particularly in the biomedical NLP field. However, such models have limitations, including knowledge noise and neglect of contextual relationships, leading to potential semantic errors and reduced accuracy. To address these issues, this paper proposes two novel methods. the first method combines knowledge graphbased language model with nearest-neighbor models to incorporate semantic and category information from neighboring instances. the second method involves integrating knowledge graph-based language model with graph neural networks (GNNs) to leverage feature information from neighboring nodes in the graph. Experiments on relation extraction (RE) and classification tasks in English and Chinese language datasets demonstrate significant performance improvements with both methods, highlighting their potential for enhancing the performance of language models and improving NLP applications in the biomedical domain. © 2023 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Sharing Parameter by Conjugation for Knowledge graph Embeddings in Complex Space 16

Sharing Parameter by Conjugation for Knowledge Graph Embeddi...

引用

16th workshop on graph-based methods for natural language processing, textgraphs 2022, in conjunction with the 29th International Conference on Computational Linguistics, COLING 2022

作者： Feng, Xincan Qu, Zhi Cheng, Yuchang Watanabe, Taro Yugami, Nobuhiro Natural Language Processing Laboratory Nara Institute of Science and Technology Japan Multilingual Knowledge Computing Laboratory Fujitsu Ltd Japan

A Knowledge graph (KG) is the directed graphical representation of entities and relations in the real world. KG can be applied in diverse natural language processing (NLP) tasks where knowledge is required. the need to scale up and complete KG automatically yields Knowledge graph Embedding (KGE), a shallow machine learning model that is suffering from memory and training time consumption issues. To mitigate the computational load, we propose a parameter-sharing method, i.e., using conjugate parameters for complex numbers employed in KGE models. Our method improves memory efficiency by 2x in relation embedding while achieving comparable performance to the state-of-the-art non-conjugate models, with faster, or at least comparable, training time. We demonstrated the generalizability of our method on two best-performing KGE models 5*E (Nayyeri et al., 2021) and ComplEx (Trouillon et al., 2016) on five benchmark datasets. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Classification based on Dynamic graph Attention Network

Speech Emotion Classification Based on Dynamic Graph Attenti...

引用

Electronic Communication and Artificial Intelligence (IWECAI), International workshop on

作者： Xu Shi Xianhua Dai School of Electronics and Information Technology Sun Yat-sen University Guangzhou P.R.China School of Cyber Science and Technology Sun Yat-sen University Shenzhen P.R.China

ISBN: (数字)9798350386943

ISBN: (纸本)9798350386950

With the development of artificial intelligence and natural language processing, speech emotion analysis technology has gradually gained widespread attention as an important research field. the complexity of speech emotion remains a challenging task, and traditional neural networks are limited by the construction of feature vectors, resulting in lower accuracy. In this paper, an end-to-end graph neural network is proposed. Firstly, the speech signals are segmented into spectra segments, taking into account that adjacent samples have similar distribution characteristics, thereby constructing a KNN graph based on spectral samples. then, through training the dynamic graph attention network, and finally, aggregating the classification categories through fully connected layers, the experimental results show higher classification accuracy on the open-source speech emotion dataset EMODB.

关键词： Human computer interaction Training Accuracy Nearest neighbor methods Vectors Robustness natural language processing

来源：评论

学校读者我要写书评

暂无评论

A graph based semi-supervised approach for analysis of derivational nouns in Sanskrit 11

A graph based semi-supervised approach for analysis of deriv...

引用

11th workshop on graph-based methods for natural language processing, textgraphs 2017, in conjunction with the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017

作者： Krishna, Amrith Satuluri, Pavankumar Ponnada, Harshavardhan Ahmed, Muneeb Arora, Gulab Hiware, Kaustubh Goyal, Pawan School of Linguistics and Literary Studies Chinmaya Vishwavidyapeeth CEG Campus India Dept. of Electrical Engineering Indian Institute of Technology BHU India Dept. of Computer Science and Engineering Indian Institute of Technology Kharagpur India

ISBN: (纸本)9781945626609

Derivational nouns are widely used in Sanskrit corpora and is a prevalent means of productivity in the language. Currently there exists no analyser that identifies the derivational nouns. We propose a semi supervised approach for identification of derivational nouns in Sanskrit. We not only identify the derivational words, but also link them to their corresponding source words. the novelty of our work is primarily in its design of the network structure for the task. the edge weights are featurised based on the phonetic, morphological, syntactic and the semantic similarity shared between the words to be identified. We find that our model is effective for the task, even when we employ a labelled dataset which is only 5 % to that of the entire dataset. © 2017 Association for Computational Linguistics

关键词： graphic methods

来源：评论

学校读者我要写书评

暂无评论

graph-based semi-supervised learning for natural language understanding 13

Graph-based semi-supervised learning for natural language un...

引用

13th workshop on graph-based methods for natural language processing, textgraphs 2019, in conjunction with the 2019 Conference on Empirical methods in natural language processing and 9th International Joint Conference on natural language processing, EMNLP-IJCNLP 2019

作者： Qiu, Zimeng Cho, Eunah Ma, Xiaochun Campbell, William M. Electrical and Computer Engineering Department Carnegie Mellon University United States Amazon Alexa AI

ISBN: (纸本)9781950737864

Semi-supervised learning is an efficient method to augment training data automatically from unlabeled data. Development of many natural language understanding (NLU) applications has a challenge where unlabeled data is relatively abundant while labeled data is rather limited. In this work, we propose transductive graphbased semi-supervised learning models as well as their inductive variants for NLU. We evaluate the approach's applicability using publicly available NLU data and models. In order to find similar utterances and construct a graph, we use a paraphrase detection model. Results show that applying the inductive graph-based semi-supervised learning can improve the error rate of the NLU model by 5%. © 2019 EMNLP-IJCNLP 2019 - graph-based methods for natural language processing - Proceedings of the 13th workshop. All rights reserved.

关键词： graphic methods

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

UNIMIB@NEEL-IT : Named entity recognition and linking of Italian tweets 3

UNIMIB@NEEL-IT : Named entity recognition and linking of Ita...

引用

3rd Italian Conference on Computational Linguistics, CLiC-it 2016 and 5th Evaluation Campaign of natural language processing and Speech Tools for Italian, EVALITA 2016

作者： Cecchini, Flavio Massimiliano Fersini, Elisabetta Manchanda, Pikakshi Messina, Enza Nozza, Debora Palmonari, Matteo Sas, Cezar University of Milano BicoccaMilan Italy

this paper describes the framework proposed by the UNIMIB Team for the task of Named Entity Recognition and Linking of Italian tweets (NEEL-IT). the proposed pipeline, which represents an entry level system, is composed of three main steps: (1) Named Entity Recognition using Conditional Random Fields, (2) Named Entity Linking by considering both Supervised and Neural-Network language models, and (3) NIL clustering by using a graph-based approach.

关键词： graphic methods

来源：评论

学校读者我要写书评

暂无评论

Understanding seed selection in bootstrapping 8

Understanding seed selection in bootstrapping

引用

8th workshop on graph-based methods for natural language processing, textgraphs 2013, at the Conference on Empirical methods in natural language processing, EMNLP 2013

作者： Ehara, Yo Sato, Issei Oiwa, Hidekazu Nakagawa, Hiroshi Graduate School of Information Science and Technology United States Information Technology Center University of Tokyo / 7-3-1 Hongo Bunkyo-ku Tokyo Japan JSPS Research Fellow Kojimachi Business Center Building 5-3-1 Kojimachi Chiyoda-ku Tokyo Japan

ISBN: (纸本)9781937284978

Bootstrapping has recently become the focus of much attention in natural language processing to reduce labeling cost. In bootstrapping, unlabeled instances can be harvested from the initial labeled "seed" set. the selected seed set affects accuracy, but how to select a good seed set is not yet clear. thus, an "iterative seeding" framework is proposed for bootstrapping to reduce its labeling cost. Our framework iteratively selects the unlabeled instance that has the best "goodness of seed" and labels the unlabeled instance in the seed set. Our framework deepens understanding of this seeding process in bootstrapping by deriving the dual problem. We propose a method called expected model rotation (EMR) that works well on not well-separated data which frequently occur as realistic data. Experimental results show that EMR can select seed sets that provide significantly higher mean reciprocal rank on realistic data than existing naive selection methods or random seed sets. © 2013 Association for Computational Linguistics

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

textgraphs 2010 - 2010 workshop on graph-based methods for natural language processing at the 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 - Proceedings of the workshop

TextGraphs 2010 - 2010 Workshop on Graph-Based Methods for N...

引用

2010 workshop on graph-based methods for natural language processing, textgraphs 2010 at the 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 - Proceedings of the workshop

ISBN: (纸本)1932432779

the proceedings contain 16 papers. the topics discussed include: graph-based clustering for computational linguistics: a survey;towards the automatic creation of a wordnet from a term-based lexical network;an investigation on the influence of frequency on the lexical organization of verbs;robust and efficient page rank for word sense disambiguation;hierarchical spectral partitioning of bipartite graphs to cluster dialects and identify distinguishing features;a character-based intersection graph approach to linguistic phylogeny;spectral approaches to learning in the graph domain;and cross-lingual comparison between distributionally determined word similarity networks.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Word sense induction by community detection

Word sense induction by community detection

引用

6th workshop on graph-based methods for natural language processing, textgraphs 2011

作者： Jurgens, David HRL Laboratories LLC Malibu CA United States Department of Computer Science Malibu University of California Los Angeles United States

ISBN: (纸本)9781937284008

Word Sense Induction (WSI) is an unsupervised approach for learning the multiple senses of a word. graph-based approaches to WSI frequently represent word co-occurrence as a graph and use the statistical properties of the graph to identify the senses. We reinterpret graph-basedWSI as community detection, a well studied problem in network science. the relations in the co-occurrence graph give rise to word communities, which distinguish senses. Our results show competitive performance on the SemEval-2010WSI Task. © 2011 the Association for Computational Linguistics.

关键词： graphic methods

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：