检索结果-内蒙古大学图书馆

Conference on Empirical methods in natural language processing (EMNLP)

作者： Nema, Preksha Khapra, Mitesh M. Indian Inst Technol Madras Dept Comp Sci & Engn Madras Tamil Nadu India Indian Inst Technol Madras Robert Bosch Ctr Data Sci & Artificial Intelligen Madras Tamil Nadu India

ISBN: (纸本)9781948087841

There has always been criticism for using n-gram based similarity metrics, such as BLEU, NIST, etc, for evaluating the performance of NLG systems. However, these metrics continue to remain popular and are recently being used for evaluating the performance of systems which automatically generate questions from documents, knowledge graphs, images, etc. Given the rising interest in such automatic question generation (AQG) systems, it is important to objectively examine whether these metrics are suitable for this task. In particular, it is important to verify whether such metrics used for evaluating AQG systems focus on answerability of the generated question by preferring questions which contain all relevant information such as question type (Wh-types), entities, relations, etc. In this work, we show that current automatic evaluation metrics based on n-gram similarity do not always correlate well with human judgments about answerability of a question. To alleviate this problem and as a first step towards better evaluation metrics for AQG, we introduce a scoring function to capture answerability and show that when this scoring function is integrated with existing metrics, they correlate significantly better with human judgments. The scripts and data developed as a part of this work are made publicly available.(1)

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Parallel Data-Local Training for Optimizing Word2Vec Embeddings for Word and graph Embeddings

Parallel Data-Local Training for Optimizing Word2Vec Embeddi...

引用

IEEE/ACM workshop on Machine Learning in High Performance Computing Environments (MLHPC)

作者： Gordon E. Moon Denis Newman-Griffis Jinsung Kim Aravind Sukumaran-Rajam Eric Fosler-Lussier P. Sadayappan Computer Science and Engineering The Ohio State University Columbus OH U.S.A. School of Computing University of Utah Salt Lake City UT U.S.A.

ISBN: (纸本)9781728159867

The Word2Vec model is a neural network-based unsupervised word embedding technique widely used in applications such as natural language processing, bioinformatics and graph mining. As Word2Vec repeatedly performs Stochastic Gradient Descent (SGD) to minimize the objective function, it is very compute-intensive. However, existing methods for parallelizing Word2Vec are not optimized enough for data locality to achieve high performance. In this paper, we develop a parallel data-locality-enhanced Word2Vec algorithm based on Skip-gram with a novel negative sampling method that decouples loss calculation with positive and negative samples; this allows us to efficiently reformulate matrix-matrix operations for the negative samples over the sentence. Experimental results demonstrate our parallel implementations on multi-core CPUs and GPUs achieve significant performance improvement over the existing state-of-the-art parallel Word2Vec implementations while maintaining evaluation quality. We also show the utility of our Word2Vec implementation within the Node2Vec algorithm which accelerates embedding learning for large graphs.

关键词： Parallel machine learning Unsupervised learning Learning latent representations Parallel word2Vec Node2Vec Word embedding graph embedding Unsupervised learning Word Parallel Lines performance boost matrix calculation locality data Line graph Objective function HIGH-PERFORMANCE

来源：评论

学校读者我要写书评

暂无评论

Improving rare disease classification using imperfect knowledge graph

引用

BMC MEDICAL INFORMATICS AND DECISION MAKING 2019年第1期19卷 238-238页

作者： Li, Xuedong Wang, Yue Wang, Dongwu Yuan, Walter Peng, Dezhong Mei, Qiaozhu Sichuan Univ Coll Comp Sci Chengdu Peoples R China Univ North Carolina Chapel Hill Sch Informat & Lib Sci Chapel Hill NC USA MobLab Inc Pasadena CA USA Univ Michigan Sch Informat Ann Arbor MI 48109 USA

Background: Accurately recognizing rare diseases based on symptom description is an important task in patient triage, early risk stratification, and target therapies. However, due to the very nature of rare diseases, the lack of historical data poses a great challenge to machine learning-based approaches. On the other hand, medical knowledge in automatically constructed knowledge graphs (KGs) has the potential to compensate the lack of labeled training examples. This work aims to develop a rare disease classification algorithm that makes effective use of a knowledge graph, even when the graph is imperfect. Method: We develop a text classification algorithm that represents a document as a combination of a "bag of words" and a "bag of knowledge terms," where a "knowledge term" is a term shared between the document and the subgraph of KG relevant to the disease classification task. We use two Chinese disease diagnosis corpora to evaluate the algorithm. The first one, HaoDaiFu, contains 51,374 chief complaints categorized into 805 diseases. The second data set, ChinaRe, contains 86,663 patient descriptions categorized into 44 disease categories. Results: On the two evaluation data sets, the proposed algorithm delivers robust performance and outperforms a wide range of baselines, including resampling, deep learning, and feature selection approaches. Both classification-based metric (macro-averaged F-1 score) and ranking-based metric (mean reciprocal rank) are used in evaluation. Conclusion: Medical knowledge in large-scale knowledge graphs can be effectively leveraged to improve rare diseases classification models, even when the knowledge graph is incomplete.

关键词： Rare disease diagnosis Knowledge graph Machine learning Text classification Extremely imbalanced data

来源：评论

学校读者我要写书评

暂无评论

Automatic processing of Code-mixed Social Media Content

Automatic Processing of Code-mixed Social Media Content

引用

作者： Utsab Barman Dublin City University

学位级别：博士

Code-mixing or language-mixing is a linguistic phenomenon where multiple language mix together during conversation. Standard natural language processing (NLP) tools such as part-of-speech (POS) tagger and parsers perform poorly because such tools are generally trained with monolingual content. Thus there is a need for code-mixed NLP. This research focuses on creating a code-mixed corpus in English- Hindi-Bengali and using it to develop a world-level language identifier and a POS tagger for such code-mixed content. The first target of this research is word-level language identification. A data set of romanised and code-mixed content written in English, Hindi and Bengali was created and annotated. Word-level language iden- tification (LID) was performed on this data using dictionaries and machine learn- ing techniques. We find that among a dictionary-based system, a character-n-gram based linear model, a character-n-gram based first order Conditional Random Fields (CRF) and a recurrent neural network in the form of a Long Short Term Memory (LSTM) that consider words as well as characters, LSTM outperformed the other methods. We also took part in the first workshop of Computational Approaches to Code-Switching, EMNLP, 2014 where we achieved the highest token-level accuracy in the word-level language identification task of Nepali-English. The second target of this research is part-of-speech (POS) tagging. POS tagging methods for code- mixed data (e. g. pipeline and stacked systems and LSTM-based neural models) have been implemented, among them, neural approach outperformed the other approach. Further, we investigate building a joint model to perform language identification and POS tagging jointly. We compare between a factorial CRF (FCRF) based joint model and three LSTM-based multi-task models for word-level language identifi- cation and POS tagging. The neural models achieve good accuracy in language identification and POS tagging by outperforming the FCRF approach. F

关键词：

来源：评论

学校读者我要写书评

暂无评论

graph-based Bilingual Word Embedding for Statistical Machine Translation

引用

ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE language INFORMATION processing 2018年第4期17卷 1–23页

作者： Wang, Rui Zhao, Hai Ploux, Sabine Lu, Bao-Liang Utiyama, Masao Sumita, Eiichiro Shanghai Jiao Tong Univ 800 Dong Chuan Rd Shanghai 200240 Peoples R China Natl Inst Informat & Commun Technol Tokyo Japan Natl Ctr Sci Res 67 Blvd Pinel F-69675 Bron France Natl Inst Informat & Commun Technol 3-5 HikaridaiSeika Cho Kyoto 6190289 Japan

Bilingual word embedding has been shown to be helpful for Statistical Machine Translation (SMT). However, most existing methods suffer from two obvious drawbacks. first, they only focus on simple contexts such as an entire document or a fixed-sized sliding window to build word embedding and ignore latent useful information from the selected context. Second, the word sense but not the word should be the minimal semantic unit;however, most existing methods still use word representation. To overcome these drawbacks, this article presents a novel graph-based Bilingual Word Embedding (GBWE) method that projects bilingual word senses into a multidimensional semantic space. first, a bilingual word co-occurrence graph is constructed using the co-occurrence and pointwise mutual information between the words. Then, maximum complete subgraphs (cliques), which play the role of a minimal unit for bilingual sense representation, are dynamically extracted according to the contextual information. Consequently, correspondence analysis, principal component analyses, and neural networks are used to summarize the clique-word matrix into lower dimensions to build the embedding model. Without contextual information, the proposed GBWE can be applied to lexical translation. In addition, given contextual information, GBWE is able to give a dynamic solution for bilingual word representations, which can be applied to phrase translation and generation. Empirical results show that GBWE can enhance the performance of lexical translation, as well as Chinese/French-to-English and Chinese-to-Japanese phrase-based SMT tasks (IWSLT, NTCIR, NIST, and WAT).

关键词： Statistical machine translation bilingual word embedding lexical translation

来源：评论

学校读者我要写书评

暂无评论

Evaluating Syntactic Properties of Seq2seq Output with a Broad Coverage HPSG: A Case Study on Machine Translation 1

Evaluating Syntactic Properties of Seq2seq Output with a Bro...

引用

1st workshop on BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, co-located with the 2018 Conference on Empirical methods in natural language processing, EMNLP 2018

作者： Wei, Johnny Tian-Zheng Pham, Khiem Dillon, Brian O'Connor, Brendan College of Natural Sciences University of Massachusetts Amherst United States Department of Computer Science San Jose State University United States Department of Linguistics University of Massachusetts Amherst United States College of Information and Computer Sciences University of Massachusetts Amherst United States

ISBN: (纸本)9781948087711

Sequence to sequence (seq2seq) models are often employed in settings where the target output is natural language. However, the syntactic properties of the language generated from these models are not well understood. We explore whether such output belongs to a formal and realistic grammar, by employing the English Resource Grammar (ERG), a broad coverage, linguistically precise HPSG-based grammar of English. From a French to English parallel corpus, we analyze the parseability and grammatical constructions occurring in output from a seq2seq translation model. Over 93% of the model translations are parseable, suggesting that it learns to generate conforming to a grammar. The model has trouble learning the distribution of rarer syntactic rules, and we pinpoint several constructions that differentiate translations between the references and our model. © 2018 Association for Computational Linguistics

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Exploiting semantic patterns over biomedical knowledge graphs for predicting treatment and causative relations

引用

JOURNAL OF BIOMEDICAL INFORMATICS 2018年 82卷 189-199页

作者： Bakal, Gokhan Talari, Preetham Kakani, Elijah, V Kavuluru, Ramakanth Univ Kentucky Dept Internal Med Div Biomed Informat Lexington KY 40506 USA Univ Kentucky Dept Comp Sci Lexington KY 40506 USA Univ Kentucky Dept Internal Med Div Hosp Med Lexington KY 40506 USA

Background: Identifying new potential treatment options for medical conditions that cause human disease burden is a central task of biomedical research. Since all candidate drugs cannot be tested with animal and clinical trials, in vitro approaches are first attempted to identify promising candidates. Likewise, identifying different causal relations between biomedical entities is also critical to understand biomedical processes. Generally, natural language processing (NLP) and machine learning are used to predict specific relations between any given pair of entities using the distant supervision approach. Objective: To build high accuracy supervised predictive models to predict previously unknown treatment and causative relations between biomedical entities based only on semantic graph pattern features extracted from biomedical knowledge graphs. methods: We used 7000 treats and 2918 causes hand-curated relations from the UMLS Metathesaurus to train and test our models. Our graph pattern features are extracted from simple paths connecting biomedical entities in the SemMedDB graph (based on the well-known SemMedDB database made available by the U.S. National Library of Medicine). Using these graph patterns connecting biomedical entities as features of logistic regression and decision tree models, we computed mean performance measures (precision, recall, F-score) over 100 distinct 80-20% train-test splits of the datasets. For all experiments, we used a positive:negative class imbalance of 1:10 in the test set to model relatively more realistic scenarios. Results: Our models predict treats and causes relations with high F-scores of 99% and 90% respectively. Logistic regression model coefficients also help us identify highly discriminative patterns that have an intuitive interpretation. We are also able to predict some new plausible relations based on false positives that our models scored highly based on our collaborations with two physician co-authors. Finally, our dec

关键词： Information extraction Relation prediction Semantic graph patterns

来源：评论

学校读者我要写书评

暂无评论

proceedings of Textgraphs@NAACL-HLT 2016: The 10th workshop on graph-based methods for natural language processing

Proceedings of TextGraphs@NAACL-HLT 2016: The 10th Workshop ...

引用

10th workshop on graph-based methods for natural language processing, Textgraphs 2016, in conjunction with the 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human language Technologies, NAACL-HLT 2016

ISBN: (纸本)9781941643884

The proceedings contain 6 papers. The topics discussed include: embedding senses for efficient graph-based word sense disambiguation;context tailoring for text normalization;cross-lingual question answering using common semantic space;network motifs may improve quality assessment of text documents;better together: combining language and social interactions into a shared representation;and visualization of dynamic reference graphs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The WebEngine - A Fully Integrated, Decentralised Web Search Engine 18

The WebEngine - A Fully Integrated, Decentralised Web Search...

引用

2nd International Conference on natural language processing and Information Retrieval (NLPIR)

作者： Kubek, Mario M. Unger, Herwig Univ Hagen Chair Commun Networks Univ Str 27 Hagen Germany

ISBN: (纸本)9781450365512

This paper presents a basic, new concept for decentralised web search which addresses major shortcomings of current web search engines. Its methods are characterised by their local working principles, making it possible to employ them on diverse hardware configurations. The concept's implementation in form of an interactive, librarian-inspired peer to -peer software client, called 'WebEngine', is elaborated on in detail. This software extends and interconnects common web servers creating and forming a decentralised web search system on top of the existing web structure while for the first time combining modern text analysis techniques with novel and efficient search functions as well as approaches for the semantically induced P2P-network construction and its flexible management. This way, an alternative, fully integrated and powerful web search engine under the motto `The Web is its own search engine.' is built making the web searchable without any central authority.

关键词： WebEngine web search engine P2P-system co-occurrence graph librarian of the web

来源：评论

学校读者我要写书评

暂无评论

Boosting Text Classification Performance on Sexist Tweets by Text Augmentation and Text Generation Using a Combination of Knowledge graphs 2

Boosting Text Classification Performance on Sexist Tweets by...

引用

2nd workshop on Abusive language Online, ALW 2018, co-located with EMNLP 2018

作者： Sharifirad, Sima Jafarpour, Borna Matwin, Stan Department of Computer Science Dalhousie University Halifax Canada Huawei Technology Toronto Canada

ISBN: (纸本)9781948087681

Text classification models have been heavily utilized for a slew of interesting natural language processing problems. Like any other machine learning model, these classifiers are very dependent on the size and quality of the training dataset. Insufficient and imbalanced datasets will lead to poor performance. An interesting solution to poor datasets is to take advantage of the world knowledge in the form of knowledge graphs to improve our training data. In this paper, we use ConceptNet and Wikidata to improve sexist tweet classification by two methods (1) text augmentation and (2) text generation. In our text generation approach, we generate new tweets by replacing words using data acquired from ConceptNet relations in order to increase the size of our training set, this method is very helpful with frustratingly small datasets, preserves the label and increases diversity. In our text augmentation approach, the number of tweets remains the same but their words are augmented (concatenation) with words extracted from their ConceptNet relations and their description extracted from Wikidata. In our text augmentation approach, the number of tweets in each class remains the same but the range of each tweet increases. Our experiments show that our approach improves sexist tweet classification significantly in our entire machine learning models. Our approach can be readily applied to any other small dataset size like hate speech or abusive language and text classification problem usinganymachine learning model. © 2018 Association for Computational Linguistics

关键词： Knowledge graph

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：