117 Hits in 3.7 sec

Regularized Interlingual Projections: Evaluation on Multilingual Transliteration

Jagadeesh Jagarlamudi, Hal Daumé III
2012 Conference on Empirical Methods in Natural Language Processing  
In this paper, we address the problem of building a multilingual transliteration system using an interlingual representation.  ...  We also propose a regularization framework for learning the interlingual representation, which accounts for language specific phonemic variability, and thus it can find better mappings between languages  ...  Acknowledgements This work is partially funded by NSF grant IIS-1153487 and the BOLT program of the Defense Advanced Research Projects Agency, Contract No. HR0011-12-C-0015.  ... 
dblp:conf/emnlp/JagarlamudiD12 fatcat:jwbhpcwupbfetnaa22ts2pfulq

Improving Bilingual Projections via Sparse Covariance Matrices

Jagadeesh Jagarlamudi, Raghavendra Udupa, Hal Daumé III, Abhijit Bhole
2011 Conference on Empirical Methods in Natural Language Processing  
Mapping documents into an interlingual representation can help bridge the language barrier of cross-lingual corpora.  ...  Our experimental results on the task of aligning comparable documents shows the efficacy of sparse covariance matrices on two data sets from two different language pairs.  ...  Such an interlingual representation is useful in many tasks like cross-lingual text categorization (Bel et al., 2003) multilingual web search (Gao et al., 2009) and so on.  ... 
dblp:conf/emnlp/JagarlamudiUDB11 fatcat:6uya6v5v6nffhjff5lqa6voava

Multilingual Multiword Expressions [article]

Lahari Poddar
2016 arXiv   pre-print
The project aims to provide a semi-supervised approach to identify Multiword Expressions in a multilingual context consisting of English and most of the major Indian languages.  ...  If they are literally translated from one language to another the expression will lose its inherent meaning.  ...  Future Work Future work of the project has been divided in three subsections depending on their complexity and importance to the project.  ... 
arXiv:1612.00246v1 fatcat:4rs33ntycnadvnn6e3atd3ixra

Mobile Speech-to-Speech Translation of Spontaneous Dialogs: An Overview of the Final Verbmobil System [chapter]

Wolfgang Wahlster
2000 Artificial Intelligence  
We discuss Verbmobil's multi-blackboard architecture that is based on packed representations at all processing stages.  ...  Distinguishing features like the multilingual prosody module and the generation of dialog summaries are highlighted.  ...  The sharable language resources collected and distributed during the Verbmobil project will be useful beyond the project lifespan, since these transliterated and richly annotated corpora of spontaneously  ... 
doi:10.1007/978-3-662-04230-4_1 fatcat:rwlz5um2frfahomh6wibs4bvom

Multilinguality in the digital library

Anne R. Diekema
2012 Electronic library  
One can translate the query into the language of the document, one can translate the documents into the language of the query, one can translate both query and document into a so-called interlingual representation  ...  Next, we discuss the aspect that differentiates the multilingual DL from the regular DL: crossing the language barrier and the resulting problems and challenges therein.  ... 
doi:10.1108/02640471211221313 fatcat:2i3fopnqwngadgytpve2tbqklq

Japanese/English Cross-Language Information Retrieval: Exploration of Query Translation and Transliteration [article]

Atsushi Fujii, Tetsuya Ishikawa
2002 arXiv   pre-print
We evaluate our system using a test collection for CLIR, and show that both the compound word translation and transliteration methods improve the system performance.  ...  For the second problem, we use a transliteration method, which corresponds words unlisted in the base word dictionary to their phonetic equivalents in the target language.  ...  Interlingual representation approach The basis of this approach is to project both queries and documents in a language-independent (conceptual) space.  ... 
arXiv:cs/0206015v1 fatcat:kikjr5x6yjcqpl6zvyo4shkc3i

A comprehensive survey on Indian regional language processing

B. S. Harish, R. Kasturi Rangan
2020 SN Applied Sciences  
In recent information explosion, contents in internet are multilingual and majority will be in the form of natural languages.  ...  They proposed modified joint source-channel model, which is based on regular and non-probabilistic expression. It uses linguistic knowledge to transliterate person names from Bengali-English.  ...  and evaluation.  ... 
doi:10.1007/s42452-020-2983-x fatcat:e3u5r5qo7ngapj5mbiwit7qlwi

Review on Machine Translation from English to Kannada

Pankaj Dwivedi
2022 International Journal for Research in Applied Science and Engineering Technology  
Abstract: Interlingual is a machine translation tool that uses anartificial language to convey the meaning of reallanguages.  ...  Parallel data is a set of sentences in two languages that are sentence- aligned, meaning that each sentence in one languageis matched with its translated counterpart in the other.  ...  'Kernel Method for English to Kannada Transliteration' Machine transliteration is the process of converting a character or word from one alphabetical system to another.  ... 
doi:10.22214/ijraset.2022.45888 fatcat:wul2t6lq4zbqhcanangitgturq

Symbolic-to-statistical hybridization: extending generation-heavy machine translation

Nizar Habash, Bonnie Dorr, Christof Monz
2009 Machine Translation  
Much of that work is focused on extending statistical MT systems with symbolic knowledge and components.  ...  We conduct an extensive evaluation of multiple system variants.  ...  , Office of Naval Research MURI Contract FCPO.810548265, DoD Contract MDA904-96-C-1250, ONR MURI Contract FCPO.810548265, Mitre Contract 010418-7712, the GALE program of the Defense Advanced Research Projects  ... 
doi:10.1007/s10590-009-9056-7 fatcat:l5kkyzljv5c2hopwkl3atbgqca

A Survey of Multilingual Neural Machine Translation

Raj Dabre, Chenhui Chu, Anoop Kunchukuttan
2020 ACM Computing Surveys  
We present a survey on multilingual neural machine translation (MNMT), which has gained a lot of traction in recent years.  ...  Many approaches have been proposed to exploit multilingual parallel corpora for improving translation quality.  ...  Most works focus on an extrinsic evaluation of multilingual models.  ... 
doi:10.1145/3406095 fatcat:5fha6uwpqjeubbwwoxcdd26bge

Transfer learning and subword sampling for asymmetric-resource one-to-many neural translation [article]

Stig-Arne Grönroos and Sami Virpioja and Mikko Kurimo
2020 arXiv   pre-print
pairs can be used via parameter sharing or transfer learning in multilingual models; Subword segmentation and regularization techniques can be applied to ensure high coverage of the vocabulary.  ...  -- and one real-world task, Norwegian to North S\'ami and Finnish.  ...  Acknowledgements This study has been supported by the MeMAD project, funded by the European Union's Horizon 2020 research and innovation programme (grant agreement No 780069), and the FoTran project, funded  ... 
arXiv:2004.04002v2 fatcat:2pw4f4bm4zheppjvm2bnehfcyi


1978 Journal of Documentation  
In the first stage Russian text is input on magnetic tapes via IBM MT/ST tape cartridges using SYSTRAN's own transliteration system.  ...  at the University of California, Berkeley, the POLA system (Project on Linguistic Analysis)  ... 
doi:10.1108/eb026657 fatcat:3qdsjriq5nfgzoxohhhou4lpda

A Comprehensive Survey of Multilingual Neural Machine Translation [article]

Raj Dabre, Chenhui Chu, Anoop Kunchukuttan
2020 arXiv   pre-print
We present a survey on multilingual neural machine translation (MNMT), which has gained a lot of traction in the recent years.  ...  Many approaches have been proposed in order to exploit multilingual parallel corpora for improving translation quality.  ...  It will be interesting to determine whether using non-linear projections is better than linear ones.  ... 
arXiv:2001.01115v2 fatcat:rkl6utbsufdbpjvawx6vrqspum

Semantic Drift in Multilingual Representations

Lisa Beinborn, Rochelle Choenni
2020 Computational Linguistics  
Multilingual representations have mostly been evaluated based on their performance on specific tasks.  ...  In addition, we propose a measure to identify semantic drift between language families.We perform experiments on word-based and sentence-based multilingual models and provide both quantitative results  ...  So far, multilingual representations have mostly been evaluated based on their performance on specific tasks.  ... 
doi:10.1162/coli_a_00382 fatcat:csl5xocz55ez3l2pncbfibqf2u

A Comprehensive Analysis of Bilingual Lexicon Induction

Ann Irvine, Chris Callison-Burch
2017 Computational Linguistics  
We analyze the behavior of bilingual lexicon induction on low frequency words, rather than testing solely on high frequency words, as previous research has done.  ...  We present experiments on a wide range of languages and data sizes. We examine translation into English from 25 foreign languages: Welsh.  ...  In Irvine, Callison-Burch, and Klementiev (2010) , we provide a detailed evaluation of our transliteration technique, and found it to be competitive with the best performing system in a transliteration  ... 
doi:10.1162/coli_a_00284 fatcat:nq4s25ujkrfz3auq2jfalbmxly
« Previous Showing results 1 — 15 out of 117 results