-
Ergun Biçici.
Consensus Ontologies in Socially Interacting MultiAgent Systems.
Multiagent and Grid Systems - An International Journal of Cloud Computing,
4(3):297-314,
2008.
[WWW]
[PDF]
Keyword(s): Consensus Ontology.
Abstract: |
This paper presents approaches for building, managing, and evaluating consensus ontologies from the individual ontologies of a network of socially interacting agents. Each agent has its own conceptualization of the world within the multiagent system framework. The interactions between agents are modeled by sending queries and receiving responses and later assessing each other's performance based on the results. This model enables us to measure the \emph{quality} of the societal beliefs in the resources which we represent as the \emph{expertise} in each domain. The dynamic nature of our system allows us to model the emergence of consensus that mimics the evolution of language. We present an algorithm for generating the consensus ontologies which makes use of the authoritative agent's conceptualization in a given domain. As the expertise of agents changes after a number of interactions, the consensus ontology that we build based on the agents' individual views evolves. The resulting approach is concordant with the principles of emergent semantics. We provide formal definitions for the problem of finding a consensus ontology in a step by step manner. We evaluate the consensus ontologies by using different heuristic measures of similarity based on the component ontologies. Conceptual processing methods for generating, manipulating, and evaluating consensus ontologies are given and experimental results are presented. The presented approach looks promising and opens new directions for further research. |
@article{Bicici:JMAGS07,
author = {Ergun Bi\c{c}ici},
title = {Consensus Ontologies in Socially Interacting MultiAgent Systems},
journal = {Multiagent and Grid Systems - An International Journal of Cloud Computing},
pages = {297-314},
volume = {4},
number = {3},
year = {2008},
keywords = {Consensus Ontology},
url = {content.iospress.com/articles/multiagent-and-grid-systems/mgs00106},
pdf = {http://bicici.github.io/publications/2007/JMAGS.pdf},
abstract = {This paper presents approaches for building, managing, and evaluating consensus ontologies from the individual ontologies of a network of socially interacting agents. Each agent has its own conceptualization of the world within the multiagent system framework. The interactions between agents are modeled by sending queries and receiving responses and later assessing each other's performance based on the results. This model enables us to measure the \emph{quality} of the societal beliefs in the resources which we represent as the \emph{expertise} in each domain. The dynamic nature of our system allows us to model the emergence of consensus that mimics the evolution of language. We present an algorithm for generating the consensus ontologies which makes use of the authoritative agent's conceptualization in a given domain. As the expertise of agents changes after a number of interactions, the consensus ontology that we build based on the agents' individual views evolves. The resulting approach is concordant with the principles of emergent semantics. We provide formal definitions for the problem of finding a consensus ontology in a step by step manner. We evaluate the consensus ontologies by using different heuristic measures of similarity based on the component ontologies. Conceptual processing methods for generating, manipulating, and evaluating consensus ontologies are given and experimental results are presented. The presented approach looks promising and opens new directions for further research.},
}
-
Ergun Biçici.
Context-Based Sentence Alignment in Parallel Corpora.
Lecture Notes in Computer Science,
4919:434-444,
2008.
Note: 9th International Conf. on Intelligent Text Processing and Computational Linguistics (CICLing 2008).
ISBN: 978-3-540-78135-6.
[WWW]
[PDF]
[doi:10.1007/978-3-540-78135-6_37]
Keyword(s): Artificial Intelligence,
Machine Translation.
Abstract: |
This paper presents a language-independent context-based sentence alignment technique given parallel corpora. We can view the problem of aligning sentences as finding translations of sentences chosen from different sources. Unlike current approaches which rely on pre-defined features and models, our algorithm employs features derived from the distributional properties of words and does not use any language dependent knowledge. We make use of the context of sentences and the notion of Zipfian word vectors which effectively models the distributional properties of words in a given sentence. We accept the context to be the frame in which the reasoning about sentence alignment is done. We evaluate the performance of our system based on two different measures: sentence alignment accuracy and sentence alignment coverage. We compare the performance of our system with commonly used sentence alignment systems and show that our system performs 1.2149 to 1.6022 times better in reducing the error rate in alignment accuracy and coverage for moderately sized corpora. |
@article{Bicici:CICLing08,
title = {Context-Based Sentence Alignment in Parallel Corpora},
author = {Ergun Bi\c{c}ici},
booktitle = {9th International Conf. on Intelligent Text Processing and Computational Linguistics (CICLing 2008), LNCS},
year = {2008},
journal = {Lecture Notes in Computer Science},
volume = {4919},
pages = {434--444},
isbn = {978-3-540-78135-6},
doi = {10.1007/978-3-540-78135-6_37},
url = {http://dx.doi.org/10.1007/978-3-540-78135-6_37},
note = {9th International Conf. on Intelligent Text Processing and Computational Linguistics (CICLing 2008)},
address = {Haifa, Israel},
keywords = {Artificial Intelligence, Machine Translation},
pdf = {bicici.github.io/publications/2008/ContextBasedSAPC.pdf},
abstract = {This paper presents a language-independent context-based sentence alignment technique given parallel corpora. We can view the problem of aligning sentences as finding translations of sentences chosen from different sources. Unlike current approaches which rely on pre-defined features and models, our algorithm employs features derived from the distributional properties of words and does not use any language dependent knowledge. We make use of the context of sentences and the notion of Zipfian word vectors which effectively models the distributional properties of words in a given sentence. We accept the context to be the frame in which the reasoning about sentence alignment is done. We evaluate the performance of our system based on two different measures: sentence alignment accuracy and sentence alignment coverage. We compare the performance of our system with commonly used sentence alignment systems and show that our system performs 1.2149 to 1.6022 times better in reducing the error rate in alignment accuracy and coverage for moderately sized corpora.},
}
-
Ergun Biçici and Marc Dymetman.
Dynamic Translation Memory: Using Statistical Machine Translation to improve Translation Memory Fuzzy Matches.
Lecture Notes in Computer Science,
4919:454-465,
2008.
Note: 9th International Conf. on Intelligent Text Processing and Computational Linguistics (CICLing 2008).
ISBN: 978-3-540-78135-6.
[WWW]
[PDF]
[doi:10.1007/978-3-540-78135-6_39]
Keyword(s): Artificial Intelligence,
Machine Translation,
Natural Language Processing.
Abstract: |
Professional translators of technical documents often use Translation Memory (TM) systems in order to capitalize on the repetitions frequently observed in these documents. TM systems typically exploit not only complete matches between the source sentence to be translated and some previously translated sentence, but also so-called \emph{fuzzy matches}, where the source sentence has some substantial commonality with a previously translated sentence. These fuzzy matches can be very worthwhile as a starting point for the human translator, but the translator then needs to manually edit the associated TM-based translation to accommodate the differences with the source sentence to be translated. If part of this process could be automated, the cost of human translation could be significantly reduced. The paper proposes to perform this automation in the following way: a phrase-based Statistical Machine Translation (SMT) system (trained on a bilingual corpus in the same domain as the TM) is combined with the TM fuzzy match, by extracting from the fuzzy-match a large (possibly gapped) bi-phrase that is dynamically added to the usual set of ''static'' bi-phrases used for decoding the source. We report experiments that show significant improvements in terms of BLEU and NIST scores over both the translations produced by the stand-alone SMT system and the fuzzy-match translations proposed by the stand-alone TM system. |
@article{BiciciDymetman:CICLing08,
title = {Dynamic Translation Memory: Using Statistical Machine Translation to improve Translation Memory Fuzzy Matches},
author = {Ergun Bi\c{c}ici and Marc Dymetman},
booktitle = {9th International Conf. on Intelligent Text Processing and Computational Linguistics (CICLing 2008), LNCS},
year = {2008},
journal = {Lecture Notes in Computer Science},
volume = {4919},
pages = {454--465},
isbn = {978-3-540-78135-6},
doi = {10.1007/978-3-540-78135-6_39},
url = {http://dx.doi.org/10.1007/978-3-540-78135-6_39},
note = {9th International Conf. on Intelligent Text Processing and Computational Linguistics (CICLing 2008)},
address = {Haifa, Israel},
keywords = {Artificial Intelligence, Machine Translation, Natural Language Processing},
pdf = {http://bicici.github.io/publications/2008/DTM.pdf},
abstract = {Professional translators of technical documents often use Translation Memory (TM) systems in order to capitalize on the repetitions frequently observed in these documents. TM systems typically exploit not only complete matches between the source sentence to be translated and some previously translated sentence, but also so-called \emph{fuzzy matches}, where the source sentence has some substantial commonality with a previously translated sentence. These fuzzy matches can be very worthwhile as a starting point for the human translator, but the translator then needs to manually edit the associated TM-based translation to accommodate the differences with the source sentence to be translated. If part of this process could be automated, the cost of human translation could be significantly reduced. The paper proposes to perform this automation in the following way: a phrase-based Statistical Machine Translation (SMT) system (trained on a bilingual corpus in the same domain as the TM) is combined with the TM fuzzy match, by extracting from the fuzzy-match a large (possibly gapped) bi-phrase that is dynamically added to the usual set of ''static'' bi-phrases used for decoding the source. We report experiments that show significant improvements in terms of BLEU and NIST scores over both the translations produced by the stand-alone SMT system and the fuzzy-match translations proposed by the stand-alone TM system.},
}