scholarly journals Document Summarization Based on Coverage with Noise Injection and Word Association

Information ◽  
2020 ◽  
Vol 11 (11) ◽  
pp. 536
Author(s):  
Heechan Kim ◽  
Soowon Lee
Keyword(s):  
Language Processing ◽  
Word Association ◽  
State Of The Art ◽  
The State ◽  
Daily Mail ◽  
Document Summarization ◽  
The Third ◽  
Word Sequence ◽  
Noise Injection ◽  
Automatic Document Summarization

Automatic document summarization is a field of natural language processing that is rapidly improving with the development of end-to-end deep learning models. In this paper, we propose a novel summarization model that consists of three methods. The first is a coverage method based on noise injection that makes the attention mechanism select only important words by defining previous context information as noise. This alleviates the problem that the summarization model generates the same word sequence repeatedly. The second is a word association method to update the information of each word by comparing the information of the current step with the information of all previous decoding steps. According to following words, this catches a change in the meaning of the word that has been already decoded. The third is a method using a suppression loss function that explicitly minimizes the probabilities of non-answer words. The proposed summarization model showed good performance on some recall-oriented understudy for gisting evaluation (ROUGE) metrics compared to the state-of-the-art models in the CNN/Daily Mail summarization task, and the results were achieved with very few learning steps compared to the state-of-the-art models.

Health Informatics Education in the Third World

1989 ◽  
Vol 28 (04) ◽  
pp. 270-272 ◽  
Author(s):  
O. Rienhoff
Keyword(s):  
Developing Countries ◽  
Health Informatics ◽  
Third World ◽  
State Of The Art ◽  
The State ◽  
Collaboration Network ◽  
Educational Tools ◽  
The Third ◽  
The Third World

Abstract:The state of the art is summarized showing many efforts but only few results which can serve as demonstration examples for developing countries. Education in health informatics in developing countries is still mainly dealing with the type of health informatics known from the industrialized world. Educational tools or curricula geared to the matter of development are rarely to be found. Some WHO activities suggest that it is time for a collaboration network to derive tools and curricula within the next decade.

scholarly journals Progressive Boundary Refinement Network for Temporal Action Detection

2020 ◽  
Vol 34 (07) ◽  
pp. 11612-11619
Author(s):  
Qinying Liu ◽  
Zilei Wang
Keyword(s):  
State Of The Art ◽  
The State ◽  
Action Detection ◽  
Fine Grained ◽  
The Third ◽  
One Stage ◽  
The Family ◽  
Main Components ◽  
Temporal Action ◽  
Boundary Refinement

Temporal action detection is a challenging task due to vagueness of action boundaries. To tackle this issue, we propose an end-to-end progressive boundary refinement network (PBRNet) in this paper. PBRNet belongs to the family of one-stage detectors and is equipped with three cascaded detection modules for localizing action boundary more and more precisely. Specifically, PBRNet mainly consists of coarse pyramidal detection, refined pyramidal detection, and fine-grained detection. The first two modules build two feature pyramids to perform the anchor-based detection, and the third one explores the frame-level features to refine the boundaries of each action instance. In the fined-grained detection module, three frame-level classification branches are proposed to augment the frame-level features and update the confidence scores of action instances. Evidently, PBRNet integrates the anchor-based and frame-level methods. We experimentally evaluate the proposed PBRNet and comprehensively investigate the effect of the main components. The results show PBRNet achieves the state-of-the-art detection performances on two popular benchmarks: THUMOS'14 and ActivityNet, and meanwhile possesses a high inference speed.

scholarly journals Title-Guided Encoding for Keyphrase Generation

2019 ◽  
Vol 33 ◽  
pp. 6268-6275 ◽  
Author(s):  
Wang Chen ◽  
Yifan Gao ◽  
Jiani Zhang ◽  
Irwin King ◽  
Michael R. Lyu
Keyword(s):  
Language Processing ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Relevant Information ◽  
The State ◽  
Main Body ◽  
Generation Task ◽  
Leading Role ◽  
Very High

Keyphrase generation (KG) aims to generate a set of keyphrases given a document, which is a fundamental task in natural language processing (NLP). Most previous methods solve this problem in an extractive manner, while recently, several attempts are made under the generative setting using deep neural networks. However, the state-of-the-art generative methods simply treat the document title and the document main body equally, ignoring the leading role of the title to the overall document. To solve this problem, we introduce a new model called Title-Guided Network (TG-Net) for automatic keyphrase generation task based on the encoderdecoder architecture with two new features: (i) the title is additionally employed as a query-like input, and (ii) a titleguided encoder gathers the relevant information from the title to each word in the document. Experiments on a range of KG datasets demonstrate that our model outperforms the state-of-the-art models with a large margin, especially for documents with either very low or very high title length ratios.

scholarly journals Using Natural Language Processing and Artificial Intelligence to Explore the Nutrition and Sustainability of Recipes and Food

2021 ◽  
Vol 3 ◽  
Author(s):  
Marieke van Erp ◽  
Christian Reynolds ◽  
Diana Maynard ◽  
Alain Starke ◽  
Rebeca Ibáñez Martín ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Domain Knowledge ◽  
State Of The Art ◽  
Interdisciplinary Approach ◽  
Comprehensive Analysis ◽  
The State ◽  
Use Cases

In this paper, we discuss the use of natural language processing and artificial intelligence to analyze nutritional and sustainability aspects of recipes and food. We present the state-of-the-art and some use cases, followed by a discussion of challenges. Our perspective on addressing these is that while they typically have a technical nature, they nevertheless require an interdisciplinary approach combining natural language processing and artificial intelligence with expert domain knowledge to create practical tools and comprehensive analysis for the food domain.

scholarly journals A Constraint-Based Hypergraph Partitioning Approach to Coreference Resolution

2013 ◽  
Vol 39 (4) ◽  
pp. 847-884 ◽  
Author(s):  
Emili Sapena ◽  
Lluís Padró ◽  
Jordi Turmo
Keyword(s):  
Language Processing ◽  
State Of The Art ◽  
The State ◽  
Classification Model ◽  
Coreference Resolution ◽  
World Knowledge ◽  
Relaxation Labeling ◽  
Hypergraph Partitioning ◽  
Lack Of Information ◽  
New Information

This work is focused on research in machine learning for coreference resolution. Coreference resolution is a natural language processing task that consists of determining the expressions in a discourse that refer to the same entity. The main contributions of this article are (i) a new approach to coreference resolution based on constraint satisfaction, using a hypergraph to represent the problem and solving it by relaxation labeling; and (ii) research towards improving coreference resolution performance using world knowledge extracted from Wikipedia. The developed approach is able to use an entity-mention classification model with more expressiveness than the pair-based ones, and overcome the weaknesses of previous approaches in the state of the art such as linking contradictions, classifications without context, and lack of information evaluating pairs. Furthermore, the approach allows the incorporation of new information by adding constraints, and research has been done in order to use world knowledge to improve performances. RelaxCor, the implementation of the approach, achieved results at the state-of-the-art level, and participated in international competitions: SemEval-2010 and CoNLL-2011. RelaxCor achieved second place in CoNLL-2011.

scholarly journals Improving the state-of-the-art in Thai semantic similarity using distributional semantics and ontological information

PLoS ONE ◽  
2021 ◽  
Vol 16 (2) ◽  
pp. e0246751
Author(s):  
Ponrudee Netisopakul ◽  
Gerhard Wohlgenannt ◽  
Aleksei Pulich ◽  
Zar Zar Hlaing
Keyword(s):  
Semantic Similarity ◽  
Language Processing ◽  
English Language ◽  
State Of The Art ◽  
Word Sense Disambiguation ◽  
Similarity Score ◽  
The State ◽  
Word Sense ◽  
Word Level ◽  
High Fraction

Research into semantic similarity has a long history in lexical semantics, and it has applications in many natural language processing (NLP) tasks like word sense disambiguation or machine translation. The task of calculating semantic similarity is usually presented in the form of datasets which contain word pairs and a human-assigned similarity score. Algorithms are then evaluated by their ability to approximate the gold standard similarity scores. Many such datasets, with different characteristics, have been created for English language. Recently, four of those were transformed to Thai language versions, namely WordSim-353, SimLex-999, SemEval-2017-500, and R&G-65. Given those four datasets, in this work we aim to improve the previous baseline evaluations for Thai semantic similarity and solve challenges of unsegmented Asian languages (particularly the high fraction of out-of-vocabulary (OOV) dataset terms). To this end we apply and integrate different strategies to compute similarity, including traditional word-level embeddings, subword-unit embeddings, and ontological or hybrid sources like WordNet and ConceptNet. With our best model, which combines self-trained fastText subword embeddings with ConceptNet Numberbatch, we managed to raise the state-of-the-art, measured with the harmonic mean of Pearson on Spearman ρ, by a large margin from 0.356 to 0.688 for TH-WordSim-353, from 0.286 to 0.769 for TH-SemEval-500, from 0.397 to 0.717 for TH-SimLex-999, and from 0.505 to 0.901 for TWS-65.

scholarly journals Beyond the “Third Wave of Positive Psychology”: Challenges and Opportunities for Future Research

2022 ◽  
Vol 12 ◽  
Author(s):  
Marié P. Wissing
Keyword(s):  
Positive Psychology ◽  
State Of The Art ◽  
Well Being ◽  
The State ◽  
Future Research ◽  
Complex Nature ◽  
Third Wave ◽  
Health And Wellness ◽  
The Third ◽  
Challenges And Opportunities

The positive psychology (PP) landscape is changing, and its initial identity is being challenged. Moving beyond the “third wave of PP,” two roads for future research and practice in well-being studies are discerned: The first is the state of the art PP trajectory that will (for the near future) continue as a scientific (sub)discipline in/next to psychology (because of its popular brand name). The second trajectory (main focus of this manuscript) links to pointers described as part of the so-called third wave of PP, which will be argued as actually being the beginning of a new domain of inter- or transdisciplinary well-being studies in its own right. It has a broader scope than the state of the art in PP, but is more delineated than in planetary well-being studies. It is in particular suitable to understand the complex nature of bio-psycho-social-ecological well-being, and to promote health and wellness in times of enormous challenges and changes. A unique cohering focus for this post-disciplinary well-being research domain is proposed. In both trajectories, future research will have to increase cognizance of metatheoretical assumptions, develop more encompassing theories to bridge the conceptual fragmentation in the field, and implement methodological reforms, while keeping context and the interwovenness of the various levels of the scientific text in mind. Opportunities are indicated to contribute to the discourse on the identity and development of scientific knowledge in mainstream positive psychology and the evolving post-disciplinary domain of well-being studies.

Sign in / Sign up

Export Citation Format

Share Document