Filters








343 Hits in 4.4 sec

Multilingual Extractive Reading Comprehension by Runtime Machine Translation [article]

Akari Asai, Akiko Eriguchi, Kazuma Hashimoto, Yoshimasa Tsuruoka
2018 arXiv   pre-print
English), our method leverages existing RC resources in the pivot language by combining a competitive RC model in the pivot language with an attentive Neural Machine Translation (NMT) model.  ...  Despite recent work in Reading Comprehension (RC), progress has been mostly limited to English due to the lack of large-scale datasets in other languages.  ...  This project is partially financially supported by Microsoft Japan. This work is also partially supported by JST CREST Grant Number JP-MJCR1513, Japan.  ... 
arXiv:1809.03275v2 fatcat:dtkec7kfwnhz7npap4w6aop4fu

BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels [article]

Yimin Jing, Deyi Xiong, Yan Zhen
2019 arXiv   pre-print
This paper presents BiPaR, a bilingual parallel novel-style machine reading comprehension (MRC) dataset, developed to support multilingual and cross-lingual reading comprehension.  ...  The biggest difference between BiPaR and existing reading comprehension datasets is that each triple (Passage, Question, Answer) in BiPaR is written parallelly in two languages.  ...  Acknowledgments The present research was supported by the National Natural Science Foundation of China (Grant No. 61622209).  ... 
arXiv:1910.05040v1 fatcat:owk5qfc67ne73mjx5quy5que5y

BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels

Yimin Jing, Deyi Xiong, Zhen Yan
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)  
This paper presents BiPaR, a bilingual parallel novel-style machine reading comprehension (MRC) dataset, developed to support multilingual and cross-lingual reading comprehension.  ...  The biggest difference between BiPaR and existing reading comprehension datasets is that each triple (Passage, Question, Answer) in BiPaR is written parallelly in two languages.  ...  Acknowledgments The present research was supported by the National Natural Science Foundation of China (Grant No. 61622209).  ... 
doi:10.18653/v1/d19-1249 dblp:conf/emnlp/JingXZ19 fatcat:t5hllpche5epbek6uttmxvra6y

Cross-Lingual Machine Reading Comprehension

Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang, Guoping Hu
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)  
We conduct experiments on two Chinese machine reading comprehension datasets CMRC 2018 and DRCD.  ...  In this paper, we propose Cross-Lingual Machine Reading Comprehension (CLMRC) task for the languages other than English.  ...  The first author was partially supported by the Google TensorFlow Research Cloud (TFRC) program for Cloud TPU access.  ... 
doi:10.18653/v1/d19-1169 dblp:conf/emnlp/CuiCLQWH19 fatcat:3gtck5uhcvey7gjbvq6um6cqyi

Beyond English-Only Reading Comprehension: Experiments in Zero-Shot Multilingual Transfer for Bulgarian [article]

Momchil Hardalov, Ivan Koychev, Preslav Nakov
2019 arXiv   pre-print
Here, we study the effectiveness of multilingual BERT fine-tuned on large-scale English datasets for reading comprehension (e.g., for RACE), and we apply it to Bulgarian multiple-choice reading comprehension  ...  Recently, reading comprehension models achieved near-human performance on large-scale datasets such as SQuAD, CoQA, MS Macro, RACE, etc.  ...  This research is partially supported by Project UNITe BG05M2OP001-1.001-0004 funded by the OP "Science and Education for Smart Growth" and co-funded by the EU through the ESI Funds.  ... 
arXiv:1908.01519v2 fatcat:gvaxbyxdg5hp3oin4a4c5c3eqy

Semantic Web Standards and Ontologies for Legislative Drafting Support [chapter]

Tommaso Agnoloni, Daniela Tiscornia
2010 Lecture Notes in Computer Science  
Machine readable open public data and the issue of multilingual web are open challenges promising to transform the relationship between citizens and European institutions.  ...  Lexical and conceptual multilingual alignment has been accomplished exploiting terms position in parallel documents.  ...  The application prototype (the integrated environment composed by the drafting tool and the knowledge resource) has been tested and evaluated within the project by legislative offices of the Italian Parliament  ... 
doi:10.1007/978-3-642-15158-3_16 fatcat:xe472mgyh5cehfxjyftbuurmvq

Flexible Speech Translation Systems

T. Schultz, A.W. Black, S. Vogel, M. Woszczyna
2006 IEEE Transactions on Audio, Speech, and Language Processing  
In the second part, we show how flexibility and reconfigurability is implemented by more radically relying on learning approaches and use our English-Thai two-way speech translation system as a concrete  ...  Speech translation research has made significant progress over the years with many high-visibility efforts showing that translation of spontaneously spoken speech from and to diverse languages is possible  ...  Second, the time from speaking into the system to achieving the translated synthesized output is critical for multilingual conversations mediated by machines.  ... 
doi:10.1109/tsa.2005.860768 fatcat:mhg2q67jprfufarbietqm363iy

Architecture for a multilingual Wikipedia [article]

Denny Vrandečić
2020 arXiv   pre-print
Both parts are fully owned and maintained by the community, as is the integration of the results in the existing Wikipedia editions.  ...  We argue that we need a new approach to tackle this problem more effectively, a multilingual Wikipedia where content can be shared between language editions.  ...  In short, relying on Machine Translation may delay the achievement of the Wikipedia mission by a rather unpredictable time frame.  ... 
arXiv:2004.04733v1 fatcat:fbtqmuzyivedbixbioh6u6uxzm

Using B-trees to Implement Water: a Portable,High Performance, High-Level Language [chapter]

A. Jaffer, M. Plusch, R. Nilsson
2009 Innovations and Advances in Computer Sciences and Engineering  
MULTILINGUAL PROGRAMMING WB is written in a subset of the Algorithmic Language Scheme which can be translated to C by the Schlep compiler [6] which is included in the WB distribution.  ...  Another mechanical translation is done by a simple bespoke Scheme program processing the data-representation design document, extracting the version, byte opcode, and (numerical) type assignments and producing  ... 
doi:10.1007/978-90-481-3658-2_17 dblp:conf/cisse/JafferPN08 fatcat:lk6gj5366vcgrjygvikvyfliqe

Data Mining in Clinical Trial Text: Transformers for Classification and Question Answering Tasks [article]

Lena Schmidt, Julie Weeds, Julian P. T. Higgins
2020 arXiv   pre-print
Recent neural network architectures based on transformers show capacities for transfer learning and increased performance on downstream natural language processing tasks such as universal reading comprehension  ...  Additionally, it demonstrates how the problem of insufficient amounts of training annotations for PICO entity extraction is tackled by augmentation.  ...  We thank Vincent Cheng for the Chinese translation. Furthermore, we thank the BERT team at Google Re-search and Allenai for making their pre-trained model weights available.  ... 
arXiv:2001.11268v1 fatcat:okwhlyamjvdmpouhdwmsposhny

Meta-Analysis of Cross-Language Plagiarism and Self-Plagiarism Detection Methods for Russian-English Language Pair

Alina Tlitova, Alexander Toschev, Max Talanov, Vitaliy Kurnosov
2020 Frontiers in Computer Science  
We analyzed solutions by studying the works on various language pairs and paid the great attention to the Russian-English language pair.  ...  Identification of translated plagiarism is a complex task, and there are almost no such tools for this purpose on the Russian market now.  ...  The authors did a comprehensive comparative analysis of CL-CnG, CL-ESA, and CL-ASA with usual CL-KGA and its various models using the largest multilingual semantic network that combines lexicographic information  ... 
doi:10.3389/fcomp.2020.523053 fatcat:2eqhh655mbb3jedkai74igfk7q

Orchestrating NLP Services for the Legal Domain [article]

Julián Moreno-Schneider and Georg Rehm and Elena Montiel-Ponsoda and Víctor Rodriguez-Doncel and Artem Revenko and Sotirios Karampatakis and Maria Khvalchik and Christian Sageder and Jorge Gracia and Filippo Maganza
2020 arXiv   pre-print
key contribution of this paper is a workflow manager that enables the flexible orchestration of workflows based on a portfolio of Natural Language Processing and Content Curation services as well as a Multilingual  ...  Acknowledgments This work has been partially funded by the project LYNX, which has received funding from the EU's Horizon 2020 research and innovation programme under grant agreement no. 780602, see http  ...  Thanks to machine translation, the prototype is able to deal with multiple languages -the documents presented to the user are not necessarily in the same language as the uploaded document.  ... 
arXiv:2003.12900v1 fatcat:vlejc7mkqfh6fnh4bt6huspiym

Gender Aware Spoken Language Translation Applied to English-Arabic [article]

Mostafa Elaraby, Ahmed Y. Tawfik, Mahmoud Khaled, Hany Hassan, Aly Osama
2018 arXiv   pre-print
In this paper, we introduce an approach to tackle such limitation by enabling a Neural Machine Translation system to produce gender-aware translation.  ...  The proposed approach can achieve significant improvement of the translation quality by 2 BLEU points.  ...  The triggering sequences extracted 300 sentences that would be affected by gender.  ... 
arXiv:1802.09287v1 fatcat:ri3tiolowvezhaxgfxppec5nqm

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
Our end system outperforms the state-of-the-art baseline by 2 B 3 F1 points on non-transcript portion of the ACE 2004 dataset.  ...  At runtime,the model is used to extracting translation candidates for a given term.  ...  for lexicon extraction that extracts translation pairs from comparable corpora by using graph-based label propagation.  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria

Big Data Semantics

Paolo Ceravolo, Antonia Azzini, Marco Angelini, Tiziana Catarci, Philippe Cudré-Mauroux, Ernesto Damiani, Alexandra Mazak, Maurice Van Keulen, Mustafa Jarrar, Giuseppe Santucci, Kai-Uwe Sattler, Monica Scannapieco (+3 others)
2018 Journal on Data Semantics  
Based on our literature review, we argue that methods, principles, and perspectives developed by the Data Semantics community can significantly contribute to address Big Data challenges.  ...  In this paper, the third of its kind co-authored by members of IFIP WG 2.6 on Data Semantics, we propose a review of the literature addressing these topics and discuss relevant challenges for future research  ...  Similar to under-resourced and morphologically rich languages, such documents require preprocessing and expert knowledge for information extraction and machine translation tasks.  ... 
doi:10.1007/s13740-018-0086-2 fatcat:bhbeyntbtzdkvf5t3dcko42jpy
« Previous Showing results 1 — 15 out of 343 results