Filters








53,077 Hits in 9.9 sec

How to Answer in English to Questions Asked in French: by Exploiting Results from Several Sources of Information

Guillaume Bourdil, Faza Elkateb, Brigitte Grau, Gabriel Illouz, Laura Monceaux, Isabelle Robba, Anne Vilnat
2004 Conference and Labs of the Evaluation Forum  
fs ut o 2 er @ t je h o if {p rg i g d Pt y ³ ¤ 0p ys t 6t o 2 ee ¿ s © t p w Pf yo fe h e i w yo 6y f ew p t r r t jr Xp y t u e¬ ft o ®p ry fy fg i e i t j S³ ¥ ¬ it p ro r g § xt Wt q p yp e i w yo by  ...  3 # ( 2¢ S Q # 0A ) S Q B CËD by fy h³ 2× § | 2 P× Õ n ¤p rf Po fe h o ie St 0p rg ³ i× r P P× r Ø ¦v W³ yn {p rf yo ie h o fe Pn `³ P vt jf y ee Pu 1³ P t j² yt et xp yo i Ẍ³ ¥ p yo ft ² a 2× y y 2× h  ... 
dblp:conf/clef/BourdilEGIMRV04 fatcat:irj7n76b6fesnflzmfqqjtt6su

Mind the Cultural Gap: Bridging Language-Specific DBpedia Chapters for Question Answering [chapter]

Elena Cabrio, Julien Cojan, Fabien Gandon
2014 Towards the Multilingual Semantic Web  
An alignment between properties is also carried out by DBpedia contributors as a mapping from the terms in Wikipedia to a common ontology, enabling the exploitation of information coming from language  ...  In the current version of QAKiS, English, French and German DBpedia chapters are queried using a natural language interface.  ...  In the context of Natural Language (NL) Question Answering (QA) over Linked Data, a system which is able to exploit information coming from the multilingual and parallel versions of DBpedia would increase  ... 
doi:10.1007/978-3-662-43585-4_9 fatcat:ettfisn7hre5rfxqa5untxa6ei

Reconciling Information in DBpedia through a Question Answering System

Elena Cabrio, Alessio Palmero Aprosio, Serena Villata
2014 International Semantic Web Conference  
Results obtained querying language-specific DBpedia chapters SPARQL endpoints for the same query can be related by several heterogenous relations, or contain an inconsistent set of information about the  ...  To overcome this issue in question answering systems over language-specific DBpedia chapters, we propose the RADAR framework for information reconciliation.  ...  Introduction In the Web of Data, it is possible to retrieve heterogeneous information items concerning a single real-world object coming from different data sources, e.g., the results of a single SPARQL  ... 
dblp:conf/semweb/CabrioAV14 fatcat:nlvr42yskzbevdwryzccx2e224

Multilingual Question Answering from Formatted Text applied to Conversational Agents [article]

Wissam Siblini, Charlotte Pasqual, Axel Lavielle, Mohamed Challal, Cyril Cauchois
2021 arXiv   pre-print
In this paper, we show that multilingual BERT is naturally capable of zero-shot transfer for an extractive Question Answering task (eQA) from English to other languages.  ...  We finally present a practical application: a multilingual conversational agent called Kate which answers to HR-related questions in several languages directly from the content of intranet pages.  ...  Applied in a real-world situation in chatbots, first results indicate that it allows the conversational process to handle new user questions from web information sources.  ... 
arXiv:1910.04659v2 fatcat:zv5we4ktvjgejmjpne2dof7vmu

Filling the gaps among DBpedia multilingual chapters for question answering

Julien Cojan, Elena Cabrio, Fabien Gandon
2013 Proceedings of the 5th Annual ACM Web Science Conference on - WebSci '13  
An alignment between properties is also carried out by DBpedia contributors as a mapping from the terms used in Wikipedia to a common ontology, enabling the exploitation of information coming from the  ...  We report on experiments carried out applying the QAKiS (Question Answering wiKiframework-based) system on the English and French DBpedia chapters, and we show that the use of such approach broadens its  ...  Moreover, in the context of Natural Language (NL) question answering over linked data, a system able to exploit information coming from the multilingual and parallel versions of DBpedia would increase  ... 
doi:10.1145/2464464.2464500 dblp:conf/websci/CojanCG13 fatcat:vne4zc4os5dw5mrhuy3zb52bwe

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)  
The results show consistent and significant improvements over various state-of-the-art systems by a large margin, which demonstrate the potentials in CLMRC task.  ...  In this context, we propose a novel model called Dual BERT, which takes advantage of the large-scale training data provided by rich-resource language (such as English) and learn the semantic relations  ...  This work was supported by the National Natural Science Foundation of China (NSFC) via grant 61976072, 61632011, and 61772153.  ... 
doi:10.18653/v1/d19-1169 dblp:conf/emnlp/CuiCLQWH19 fatcat:3gtck5uhcvey7gjbvq6um6cqyi

Argumentation-based Inconsistencies Detection for Question-Answering over DBpedia

Elena Cabrio, Julien Cojan, Serena Villata, Fabien Gandon
2013 International Semantic Web Conference  
In the Web of Data, the pieces of information obtained by querying distributed SPARQL endpoints may provide different results for the same query.  ...  In particular, the problem of reconciling information obtained by distributed SPARQL endpoints is encountered in question-answering systems over linked data, where different SPARQL endpoints are queried  ...  In this paper, we answer the following research question: How to reconcile information provided by the multilingual chapters of DBpedia to obtain a consistent results set?  ... 
dblp:conf/semweb/CabrioCVG13a fatcat:gc3vxtzljbaznhk2mxhk6dwapq

Cross-lingual Question Answering with QED

Kisuh Ahn, Beatrix Alex, Johan Bos, Tiphaine Dalmas, Jochen L. Leidner, Matthew Smillie
2004 Conference and Labs of the Evaluation Forum  
) Question Answering Track 2004 for the source languages French and German and the target language English.  ...  For answering factoid questions, we report an accuracy of 16% (German to English) and 20% (French to English), respectively.  ...  Dalmas is supported by the School of Informatics, University of Edinburgh.  ... 
dblp:conf/clef/AhnABDLS04 fatcat:gnfqa7hvx5hx3p5kh5xe64o25i

Unsupervised Induction of Cross-Lingual Semantic Relations

Mike Lewis, Mark Steedman
2013 Conference on Empirical Methods in Natural Language Processing  
We also show how to use the semantics to improve the accuracy of machine translation, by using it in a simple reranker.  ...  We introduce the first unsupervised approach to this problem, learning clusters of semantically equivalent English and French relations between referring expressions, based on their named-entity arguments  ...  This work was funded by ERC Advanced Fellow-ship 249520 GRAMPLUS and IP EC-FP7-270273 Xperience.  ... 
dblp:conf/emnlp/LewisS13 fatcat:m3rbbswp35cn7jg3ubwtrnws4m

Project PIAF: Building a Native French Question-Answering Dataset [article]

Rachel Keraron, Guillaume Lancrenon, Mathilde Bras, Frédéric Allary, Gilles Moyse, Thomas Scialom, Edmundo-Pavel Soriano-Morales, Jacopo Staiano
2020 arXiv   pre-print
Motivated by the lack of data for non-English languages, in particular for the evaluation of downstream tasks such as Question Answering, we present a participatory effort to collect a native French Question  ...  Answering Dataset.  ...  We deemed such information as not directly exploitable, given the presence of several ambiguities and inconsistencies.  ... 
arXiv:2007.00968v1 fatcat:ksqezgkdpbcxxmj4jhlp5bgswq

Overview of the CLEF 2004 Multilingual Question Answering Track [chapter]

Bernardo Magnini, Alessandro Vallin, Christelle Ayache, Gregor Erbach, Anselmo Peñas, Maarten de Rijke, Paulo Rocha, Kiril Simov, Richard Sutcliffe
2005 Lecture Notes in Computer Science  
Nine target languages and ten source languages were exploited to enact 8 monolingual and 73 cross-language tasks. Twenty-four groups participated in the exercise.  ...  The best performing monolingual system irrespective of target language answered 64.5% of the questions correctly (in the monolingual Portuguese task), while the average of the best performances for each  ...  questions were formulated in five source languages -Dutch, French, German, Italian-and answer were searched in an English corpus collection.  ... 
doi:10.1007/11519645_38 fatcat:odzpsiwi2vhcdfmksgdi2lh6dq

Overview of the CLEF 2005 Multilingual Question Answering Track [chapter]

Alessandro Vallin, Bernardo Magnini, Danilo Giampiccolo, Lili Aunimo, Christelle Ayache, Petya Osenova, Anselmo Peñas, Maarten de Rijke, Bogdan Sacaleanu, Diana Santos, Richard Sutcliffe
2006 Lecture Notes in Computer Science  
Nine target languages and ten source languages were exploited to enact 8 monolingual and 73 cross-language tasks. Twenty-four groups participated in the exercise.  ...  The best performing monolingual system irrespective of target language answered 64.5% of the questions correctly (in the monolingual Portuguese task), while the average of the best performances for each  ...  questions were formulated in five source languages -Dutch, French, German, Italian-and answer were searched in an English corpus collection.  ... 
doi:10.1007/11878773_36 fatcat:xmet2ayrajbllfv2w5azaq4wyu

Overview of the CLEF 2006 Multilingual Question Answering Track [chapter]

Bernardo Magnini, Danilo Giampiccolo, Pamela Forner, Christelle Ayache, Valentin Jijkoun, Petya Osenova, Anselmo Peñas, Paulo Rocha, Bogdan Sacaleanu, Richard Sutcliffe
2007 Lecture Notes in Computer Science  
Nine target languages and ten source languages were exploited to enact 8 monolingual and 73 cross-language tasks. Twenty-four groups participated in the exercise.  ...  The best performing monolingual system irrespective of target language answered 64.5% of the questions correctly (in the monolingual Portuguese task), while the average of the best performances for each  ...  questions were formulated in five source languages -Dutch, French, German, Italian-and answer were searched in an English corpus collection.  ... 
doi:10.1007/978-3-540-74999-8_31 fatcat:lilwqiqyqzbhfn6bal4jggdaoe

Cross-lingual Approaches for Task-specific Dialogue Act Recognition [article]

Jiří Martínek, Christophe Cerisara, Pavel Král, Ladislav Lenc
2021 arXiv   pre-print
We compute dialogue turn embeddings with both a CNN and multi-head self-attention model and show that the best results are obtained by combining all sources of transferred information.  ...  In this paper we exploit cross-lingual models to enable dialogue act recognition for specific tasks with a small number of annotations.  ...  We investigate in this work two sources of information from which we transfer knowledge: pre-trained English BERT sentence embeddings and an English corpus annotated with dialogue acts.  ... 
arXiv:2005.09260v2 fatcat:dh2nm2xta5ddlmenvwnsgcw3sm

A Multi-Layer Network for Aspect-based Cross-lingual Sentiment Classification

Kalim Sattar, Qasim Umer, Dinara G. Vasbieva, Sungwook Chung, Zohaib Latif, Choonhwa Lee
2021 IEEE Access  
To answer the research question RQ4, the performance results of the proposed approach are compared by excluding the POS tagging information to check its influence on the proposed approach. B.  ...  To answer the research question RQ3, the performance results of the proposed approach are compared by excluding the divided attention to check its influence on the proposed approach.  ... 
doi:10.1109/access.2021.3116053 fatcat:p6noysvmubfvpfqm4htk2vernq
« Previous Showing results 1 — 15 out of 53,077 results