Filters








2,050 Hits in 4.6 sec

Zero-Shot Cross-Lingual Abstractive Sentence Summarization through Teaching Generation and Attention

Xiangyu Duan, Mingming Yin, Min Zhang, Boxing Chen, Weihua Luo
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Experiments on cross-lingual ASSUM task show that our proposed method is significantly better than pipeline baselines and previous works, and greatly enhances the cross-lingual performances closer to the  ...  We release the code and data at https://github.com/KelleyYin/ Cross-lingual-Summarization.  ...  the joint research project of Alibaba and Soochow University.  ... 
doi:10.18653/v1/p19-1305 dblp:conf/acl/DuanYZCL19 fatcat:fugwbh5lvbegnhi4c2ykise5ce

D4.8 Pilot IV: First Report

Katharina Allgaier, Susana Veríssimo, Matthias Orlikowski, Mattias Hartung
2020 Zenodo  
into drug development and evaluation.  ...  As experts in what it is like to live with their condition, patients are uniquely positioned to inform the understanding of the therapeutic context for drug development and evaluation".  ...  Section 5 presents two experiments on cross-lingual transfer of sentiment analysis and cross-lingual concept detection.  ... 
doi:10.5281/zenodo.5744621 fatcat:bx2le6g2yrdu5ah5kj4wmwfq6u

Semantic Interoperability for Cross-lingual and cross-document Event Detection

Piek Vossen, Egoitz Laparra, German Rigau, Itziar Aldabe
2015 Proceedings of the The 3rd Workshop on EVENTS: Definition, Detection, Coreference, and Representation  
We report on the cross-lingual cross-document event and entity extraction comparing the Spanish and Dutch output with respect to English.  ...  Furthermore, we use a common RDF model to represent instances of events and normalised entities and dates.  ...  This work was supported by the European Union's 7th Framework Programme via the News-Reader (ICT-316404) project and by the SKATER Spanish project (TIN2012-38584-C06-02) with European Regional Development  ... 
doi:10.3115/v1/w15-0814 dblp:conf/aclevents/VossenLRA15 fatcat:cjsnc55sujf5nlauqp5b4nr2q4

LLOD-Driven Bilingual Word Embeddings Rivaling Cross-Lingual Transformers in Quality of Life Concept Detection from French Online Health Communities [chapter]

Katharina Allgaier, Susana Veríssimo, Sherry Tan, Matthias Orlikowski, Matthias Hartung
2021 Applications and Practices in Ontology Design, Extraction, and Reasoning  
In a combined configuration, our models rival the performance of state-of-the-art cross-lingual transformers, despite being of considerably lower model complexity.  ...  Furthermore, in a comparative evaluation we find that our models based on bilingual word embeddings exhibit a high degree of complementarity with an approach that integrates machine translation and rule-based  ...  Acknowledgments This work was funded by the Prêt-à-LLOD project within the European Union's Horizon 2020 research and innovation programme under grant agreement no. 825182.  ... 
doi:10.3233/ssw210037 fatcat:nvmixudmg5gy5naedlaezqlkbi

LLOD-driven Bilingual Word Embeddings Rivaling Cross-lingual Transformers in Quality of Life Concept Detection from French Online Health Communities

Katharina Allgaier, Susana Veríssimo, Sherry Tan, Matthias Orlikowski, Matthias Hartung
2021 Zenodo  
In a combined configuration, our models rival the performance of state-of- the-art cross-lingual transformers, despite being of considerably lower model complexity.  ...  Furthermore, in a comparative evaluation we find that our models based on bilingual word embeddings exhibit a high degree of complementarity with an approach that integrates machine translation and rule-based  ...  Acknowledgments This work was funded by the Prêt-à-LLOD project within the European Union's Horizon 2020 research and innovation programme under grant agreement no. 825182.  ... 
doi:10.5281/zenodo.5011771 fatcat:3t6upx3orjcxzirw5vqsdwp3wu

Towards Fully Bilingual Deep Language Modeling [article]

Li-Hsin Chang, Sampo Pyysalo, Jenna Kanerva, Filip Ginter
2020 arXiv   pre-print
cross-lingual transfer remain monolingual.  ...  We collect pre-training data, create a Finnish-English bilingual BERT model and evaluate its performance on datasets used to evaluate the corresponding monolingual models.  ...  The English BERT was evaluated on GLUE, the Stanford Question Answering Dataset (SQuAD) (Rajpurkar et al., 2016) , and the Situations With Adversarial Generations dataset (Zellers et al., 2018) .  ... 
arXiv:2010.11639v1 fatcat:cyhje6sutfdgxglxepemmsy4rq

Natural Language Processing Chains Inside a Cross-lingual Event-Centric Knowledge Pipeline for European Union Under-resourced Languages [article]

Diego Alves, Gaurish Thakkar, Marko Tadić
2020 arXiv   pre-print
These chains are part of the first step of an event-centric knowledge processing pipeline whose aim is to process multilingual media information about major events that can cause an impactin Europe and  ...  Due to the differences in terms of availability of language resources for each language, we have built this strategy in three steps, starting with processing chains for the well-resourced languages and  ...  the first step of its Knowledge Processing Pipeline.  ... 
arXiv:2010.12433v1 fatcat:cowt73oidzcjncwn2ty5xfsrwm

Improving patch-based scene text script identification with ensembles of conjoined networks [article]

Lluis Gomez, Anguelos Nicolaou, Dimosthenis Karatzas
2017 arXiv   pre-print
In addition, we propose a new public benchmark dataset for the evaluation of multi-lingual scene text end-to-end reading systems.  ...  and an off-the-shelf OCR engine.  ...  Acknowledgment This project was supported by the Spanish project TIN2014-52072-P, the fellowship RYC-2009-05031, and the Catalan government scholarship 2014FI B1-0017.  ... 
arXiv:1602.07480v2 fatcat:ayqfeitjonao3mfjuvhbudfm3a

NCLS: Neural Cross-Lingual Summarization

Junnan Zhu, Qian Wang, Yining Wang, Yu Zhou, Jiajun Zhang, Shaonan Wang, Chengqing Zong
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
Moreover, we propose to further improve NCLS by incorporating two related tasks, monolingual summarization and machine translation, into the training process of CLS under multi-task learning.  ...  Cross-lingual summarization (CLS) is the task to produce a summary in one particular language for a source document in a different language.  ...  We thank Xina Fu, Jinliang Lu, and Sikai Liu for conducting human evaluation.  ... 
doi:10.18653/v1/d19-1302 dblp:conf/emnlp/ZhuWWZZWZ19 fatcat:slbwq35gizhafixzqphqei3d7i

NCLS: Neural Cross-Lingual Summarization [article]

Junnan Zhu, Qian Wang, Yining Wang, Yu Zhou, Jiajun Zhang, Shaonan Wang, Chengqing Zong
2019 arXiv   pre-print
Moreover, we propose to further improve NCLS by incorporating two related tasks, monolingual summarization and machine translation, into the training process of CLS under multi-task learning.  ...  Cross-lingual summarization (CLS) is the task to produce a summary in one particular language for a source document in a different language.  ...  We thank Xina Fu, Jinliang Lu, and Sikai Liu for conducting human evaluation.  ... 
arXiv:1909.00156v1 fatcat:pcfkgq3p4jdyxftme5czmuozqq

KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi [article]

Rubungo Andre Niyongabo and Hong Qu and Julia Kreutzer and Li Huang
2020 arXiv   pre-print
In addition, the design of the created datasets allows for a wider use in NLP beyond text classification in future studies, such as representation learning, cross-lingual learning with more distant languages  ...  Along with the datasets, we provide statistics, guidelines for preprocessing, and monolingual and cross-lingual baseline models.  ...  Acknowledgements This work was partially supported by the National Key R&D Program of China under Grant 2018AAA0100202, and the National Science Foundation of China under Grants 61976043.  ... 
arXiv:2010.12174v1 fatcat:xnobddrzxraidjhfftg3z7yequ

Cross-lingual Candidate Search for Biomedical Concept Normalization [article]

Roland Roller, Madeleine Kittner, Dirk Weissenborn, Ulf Leser
2018 arXiv   pre-print
The evaluation of our model is carried out on the French Quaero corpus, showing that it outperforms most teams of CLEF eHealth 2015 and 2016.  ...  To overcome the limitations of non-English terminologies we propose a cross-lingual candidate search for concept normalization using a character-based neural translation model trained on a multilingual  ...  Acknowledgements This research was supported by the German Federal Ministry of Economics and Energy (BMWi) through the project MACSS (01MD16011F) and the German Federal Ministry of Education and Research  ... 
arXiv:1805.01646v1 fatcat:ohcpjeltpbgndgqnkz6bj2f6aa

Baselines and test data for cross-lingual inference [article]

Željko Agić, Natalie Schluter
2018 arXiv   pre-print
Our systems are based on cross-lingual word embeddings and machine translation.  ...  The recent years have seen a revival of interest in textual entailment, sparked by i) the emergence of powerful deep neural network learners for natural language processing and ii) the timely development  ...  There, paired snippets of text are evaluated for their degree of equivalence, and could thus be treated as a fine-grained proxy for SNLI-style evaluations.  ... 
arXiv:1704.05347v2 fatcat:pbzvb2x6sbaupairgfoavj6zg4

Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems [article]

Evgeniia Razumovskaia, Goran Glavaš, Olga Majewska, Edoardo M. Ponti, Anna Korhonen, Ivan Vulić
2021 arXiv   pre-print
Hence, state-of-the-art approaches to multilingual ToD mostly rely on (zero- or few-shot) cross-lingual transfer from resource-rich languages (almost exclusively English), either by means of machine translation  ...  To overcome this limitation, we draw parallels between components of the ToD pipeline and other NLP tasks, which can inspire solutions for learning in low-resource scenarios.  ...  Goran Glavaš is supported by the Multi2ConvAI Grant (Mehrsprachige und domänenübergreifende Conversational AI) of the Baden-Württemberg Ministry of Economy, Labor, and Housing.  ... 
arXiv:2104.08570v2 fatcat:bi5xizz4wzct5fpiuk3ikotjta

NewsReader: Using knowledge resources in a cross-lingual reading machine to generate more knowledge from massive streams of news

Piek Vossen, Rodrigo Agerri, Itziar Aldabe, Agata Cybulska, Marieke van Erp, Antske Fokkens, Egoitz Laparra, Anne-Lyse Minard, Alessio Palmero Aprosio, German Rigau, Marco Rospocher, Roxane Segers
2016 Knowledge-Based Systems  
The real content, however, is defined using multilingual and cross-lingual knowledge resources, both semantic and episodic.  ...  We explain how these knowledge resources are used for the processing of text and ultimately define the actual content of the episodic situational knowledge that is reported in the news.  ...  The creation of the larger datasets was carried out with the support of SURF Cooperative.  ... 
doi:10.1016/j.knosys.2016.07.013 fatcat:bifn3yjo7vdfbj5przsfmhvqxu
« Previous Showing results 1 — 15 out of 2,050 results