A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Filters
Using a support-vector machine for Japanese-to-English translation of tense, aspect, and modality
2001
Proceedings of the workshop on Data-driven methods in machine translation -
unpublished
Preserved Fulltext
This paper describes experiments carried out using a variety of machine-learning methods, including the k-nearest neighborhood method that was used in a previous study, for the translation of tense, aspect ...
It was found that the support-vector machine method was the most precise of all the methods tested. ...
Introduction Tense, aspect, and modality are known to cause problems in machine translation. ...
doi:10.3115/1118037.1118052
fatcat:g4m3xuqvtfhr3ku4e5ddghixxe
On the Integration of LinguisticFeatures into Statistical and Neural Machine Translation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Aside from the fact that many of these papers craft their own definition of human parity, these sensational claims are often not supported by a complete analysis of all aspects involved in translation. ...
The problems range from simple number and gender agreement errors to more complex phenomena such as the correct translation of aspectual values and tenses. ...
Neural Machine Translation No other studies have been done on 'tense' and 'aspect' for NMT. ...
arXiv:2003.14324v1
fatcat:hjmii6oob5cx3oxxmwlkzuqlgu
A Japanese sentence analyzer
1988
IBM Journal of Research and Development
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2005; you can also visit the original URL.
The file type is application/pdf.
The dependency structures have semantically important information such as tense, aspect, and modality, as well as preference scores reflecting relative ranking of parse acceptability. ...
This paper presents the design of a broadcoverage Japanese sentence analyzer which can be part of various Japanese processing systems. ...
Acknowledgments The authors would like to thank George Heidorn, Norman Haas, and Martin Mikelsons for Kanjification; and Karen Jensen, Chie Yamanouchi, Hiroshi Kitamura, and Hiroshi Maruyama for their ...
doi:10.1147/rd.322.0238
fatcat:u2gmxouv4jh3dlffxq36zntpeq
Asian language processing: current state-of-the-art
2007
Language Resources and Evaluation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
As a result, there are vast differences in the level of language processing capability and the number of sharable resources available for individual languages. ...
A comprehensive overview of the current state of Asian language processing must necessarily address the range of issues that arise due to the diversity of Asian languages and must reflect the vastly different ...
We would like to thank AFNLP for its support of the initiative to promote Asian language processing. Various colleagues helped us processing all the papers, including Dr. ...
doi:10.1007/s10579-007-9041-9
fatcat:ryrtqspk5nggdgzp7o75knch3m
Genre Effects of Compound Verbs in Hindi-Urdu: A Comparative Study of Jana with Japanese Verb Shimau in Translations
2004
Translation Today
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The second phase of the study involves the analysis of illustrative examples of compatibility between jānā 'go' and the Japanese verb shimau 'put away', as used in their Japanese translations * ...
I use two short stories by Premchand and the screenplay for the famous film In Custody. ...
Although there have not been enough translated Japanese versions for each story in Hindi-Urdu, which would enable comparison between English and Japanese translations using parallel corpora, I have used ...
doi:10.46623/tt/2019.13.1.ar3
fatcat:dw6knl5ryzdehcyvyrteqe763u
Simple or Complex? Assessing the readability of Basque Texts
2014
International Conference on Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this paper we present a readability assessment system for Basque, ErreXail, which is going to be the preprocessing module of a Text Simplification system. ...
To that end we compile two corpora, one of simple texts and another one of complex texts. ...
This research was supported by the the Basque Government (IT344-10), and the Spanish Ministry of Science and Innovation, Hibrido Sint project (MICINN, TIN2010-202181). ...
dblp:conf/coling/Gonzalez-DiosASS14
fatcat:dnyxrlk5zncg3hmv7e6s4ee3ne
Cross-Linguistic Sentiment Analysis: From English to Spanish
2009
Recent Advances in Natural Language Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We explore the adaptation of English resources and techniques for text sentiment analysis to a new language, Spanish. ...
Support Vector Machine classification. ...
Acknowledgments This work was supported by a NSERC Discovery Grant (261104-2008) to Maite Taboada. ...
dblp:conf/ranlp/BrookeTT09
fatcat:4q5f354cfnahnfcumzlp3zh3zm
I Wish I Would Have Loved This One, But I Didn't – A Multilingual Dataset for Counterfactual Detection in Product Reviews
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
For this purpose, we annotate a multilingual CFD dataset from Amazon product reviews covering counterfactual statements written in English, German, and Japanese languages. ...
Applying machine translation on English counterfactual examples to create multilingual data performs poorly, demonstrating the language-specificity of this problem, which has been ignored so far. ...
it on test sentences in a target language of interest, which are translated into English using a machine translation (MT) system. ...
arXiv:2104.06893v2
fatcat:pjudi346rbcmxpimz5cytijo2e
Use of Modality and Negation in Semantically-Informed Syntactic MT
[article]
2015
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We apply our MN annotation scheme to statistical machine translation using a syntactic framework that supports the inclusion of semantic annotations. ...
We describe a new modality/negation (MN) annotation scheme, the creation of a (publicly available) MN lexicon, and two automated MN taggers that we built using the annotation scheme and lexicon. ...
For their helpful ideas and suggestions during the development of the modality framework, we are indebted to Mona Diab, Eduard Hovy, Marge McShane, Teruko Mitamura, Sergei Nirenburg, Boyan Onyshkevych, ...
arXiv:1502.01682v1
fatcat:qliff2qekrhijflqscwle5mssi
Rule-Based Pronominal Anaphora Treatment for Machine Translation
2015
Proceedings of the Second Workshop on Discourse in Machine Translation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
These two linguistic phenomena have the particularity that either a pronoun and its antecedent (the token which gives meaning to it), or a verbal tense and its referent, are potentially placed in di erent ...
However, most Machine Translation (MT) systems process texts one sentence at the time. ...
Acknowledgements
Predicting the boundedness of English SP verbs We chose to work with the bounded/unbounded distinction for two main reasons: availability of resources and the need for a disambiguation ...
doi:10.18653/v1/w15-2512
dblp:conf/discomt/LoaicigaW15
fatcat:nqb7ci7tc5gajbonpbwi4ku4k4
Modality and Negation in SIMT Use of Modality and Negation in Semantically-Informed Syntactic MT
2012
Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
We apply our MN annotation scheme to statistical machine translation using a syntactic framework that supports the inclusion of semantic annotations. ...
We describe a new modality/negation (MN) annotation scheme, the creation of a (publicly available) MN lexicon, and two automated MN taggers that we built using the annotation scheme and lexicon. ...
For their helpful ideas and suggestions during the development of the modality framework, we are indebted to Mona Diab, Eduard Hovy, Marge McShane, Teruko Mitamura, Sergei Nirenburg, Boyan Onyshkevych ...
doi:10.1162/coli_a_00099
fatcat:22t5zht6bzhqbluutawiztjjvm
XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
to translation-based transfer. ...
Advances in machine reasoning and cross-lingual transfer depend on the availability of challenging evaluation benchmarks. ...
Heartfelt thanks to Fangyu Liu, Ulla Meeri Petti, and Yi Zhu for their invaluable help. ...
arXiv:2005.00333v2
fatcat:23pink4pifhjnlo4oiapyhbivy
Towards Automatic Subtitling: Assessing the Quality of Old and New Resources
2020
Italian Journal of Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this work, we compare the previously studied corpora with MuST-Cinema, a corpus enabling end-to-end speech to subtitles translation, in terms of the conformity to the constraints of: 1) length and reading ...
Growing needs in localising multimedia content for global audiences have resulted in Neural Machine Translation (NMT) gradually becoming an established practice in the field of subtitling in order to reduce ...
Álvarez, Arzelus, and Etchegoyhen (2014) trained Support Vector Machine and Logistic Regression classifiers on correctly/incorrectly segmented subtitles to predict line breaks. ...
doi:10.4000/ijcol.649
fatcat:ozasm3svvfhk7d2hv4igk4mibu
Past, Present, Future: A Computational Investigation of the Typology of Tense in 1000 Languages
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We show that SuperPivot performs well for the crosslingual analysis of the linguistic phenomenon of tense. ...
in use. ...
Mofrad, Yadollah Yaghoobzadeh, and Benjamin Roth. We are indebted to Michael Cysouw for the Parallel Bible Corpus. ...
arXiv:1704.08914v2
fatcat:qrxhejelbzhttpn7d7dkr3yvbu
A Statistical Machine Translation Primer
[chapter]
2008
Learning Machine Translation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2012; you can also visit the original URL.
The file type is application/pdf.
of the volume: This first chapter is a short introduction to the main aspects of Statistical Machine Translation. ...
We wish to thank the MIT Press who gave us the opportunity to publish this volume, and in particular Susan Buckley and Robert Prior for their support in preparing the manuscript. ...
the "translation model" part of a noisy-channel model (hence the model is indeed eventually used for translating from Japanese to English, and not the reverse.) ...
doi:10.7551/mitpress/9780262072977.003.0001
fatcat:lxpjkowiufaobddnf6xbuoc23m
« Previous
Showing results 1 — 15 out of 580 results