Filters








828 Hits in 8.4 sec

Semantically-Informed Syntactic Machine Translation: A Tree-Grafting Approach [article]

Kathryn Baker, Michael Bloodgood, Chris Callison-Burch, Bonnie J. Dorr, Nathaniel W. Filardo, Lori Levin, Scott Miller, Christine Piatko
2014 arXiv   pre-print
We describe a unified and coherent syntactic framework for supporting a semantically-informed syntactic approach to statistical machine translation.  ...  This finding supports the hypothesis (posed by many researchers in the MT community, e.g., in DARPA GALE) that both syntactic and semantic information are critical for improving translation quality---and  ...  This work is supported, in part, by the Johns Hopkins Human Language Technology Center of Excellence, by the National Science Foundation under grant IIS-0713448, and by BBN Technologies under GALE DARPA  ... 
arXiv:1409.7085v1 fatcat:i63rydjyhbgilg6o5tvglfm2te

Building Korean Sign Language Augmentation (KoSLA) Corpus with Data Augmentation Technique [article]

Changnam An, Eunkyung Han, Dongmyeong Noh, Ohkyoon Kwon, Sumi Lee, Hyunshim Han
2022 arXiv   pre-print
For the experimental support, we verify the effectiveness of data augmentation technique and usefulness of our corpus by performing a translation task between normal sentences and sign language annotations  ...  To overcome data scarcity, we resorted to data augmentation techniques such as synonym replacement to boost the efficiency of our translation model and available data, while maintaining grammatical and  ...  Acknowledgments We would like to thank Professor Hong-Goo Kang of the Department of Electrical and Electronic Engineering at Yonsei University, for providing insightful feedback during research planning  ... 
arXiv:2207.05261v1 fatcat:roum2eejhjhxndiz5imwzp46ge

Empirical Study of Utilizing Morph-Syntactic Information in SMT [chapter]

Young-Sook Hwang, Taro Watanabe, Yutaka Sasaki
2005 Lecture Notes in Computer Science  
, and the relative positional information of a word in a statistical machine translation framework.  ...  We learn not only translation models but also word-based/class-based language models by manipulating morphological and relative positional information.  ...  Acknowledgments The research reported here was supported in part by a contract with the National Institute of Information and Communications Technology entitled "A study of speech dialogue translation  ... 
doi:10.1007/11562214_42 fatcat:tkcbvagphfehpcrz5t2ymguooi

Multimodal machine translation through visuals and speech

Umut Sulubacak, Ozan Caglayan, Stig-Arne Grönroos, Aku Rouhe, Desmond Elliott, Lucia Specia, Jörg Tiedemann
2020 Machine Translation  
Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data.  ...  These tasks are distinguished from their monolingual counterparts of speech recognition, image captioning, and video captioning by the requirement of models to generate outputs in a different language.  ...  We would also like to thank Maarit Koponen for her valuable feedback and her help in establishing our discussions of machine translation evaluation.  ... 
doi:10.1007/s10590-020-09250-0 fatcat:jod3ghcsnnbipotcqp6sme4lna

Multimodal Machine Translation through Visuals and Speech

Umut Sulubacak, Ozan Caglayan, Stig-Arne Grönroos, Aku Rouhe, Desmond Elliott, Lucia Specia, Jörg Tiedemann
2019 Zenodo  
Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data.  ...  These tasks are distinguished from their monolingual counterparts of speech recognition, image captioning, and video captioning by the requirement of models to generate outputs in a different language.  ...  We would also like to thank Maarit Koponen for her valuable feedback and her help in establishing our discussions of machine translation evaluation.  ... 
doi:10.5281/zenodo.3690791 fatcat:otdy5i33fzfsnnbb3xgb6zph6q

D4.1 Report on Multimodal Machine Translation

Stig-Arne Grönroos, Umut Sulubacak, Jörg Tiedemann
2018 Zenodo  
In this deliverable, we present a survey of the state of the art in machine translation with an emphasis on multimodal tasks and systems.  ...  Both of these tasks are championed by evaluation campaigns, acting as competitions to stimulate research and to serve as a regulated platform investigating evaluation methodologies.  ...  Acknowledgments This work has been supported by the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No 780069, and by the Academy of Finland in the project 313988.  ... 
doi:10.5281/zenodo.3690761 fatcat:n3b34ooubfayxphgyf6bli6bya

Getting Past the Language Gap: Innovations in Machine Translation [chapter]

Rodolfo Delmonte
2012 Mobile Speech and Advanced Natural Language Solutions  
Learning Improves Performance Learning has been applied to the final decoding phase by introducing weights associated with translations and a final phase in which automatic evaluation is applied to the  ...  An example of appending statistical techniques to rule-based MT is the experiment (by a number of researchers in Spain, Japan, and Canada) of 'statistical post-editing'.  ...  ., so it is important to follow Chiang's (2007) observation to use SRL labels to augment the extraction of SCFG rules.  ... 
doi:10.1007/978-1-4614-6018-3_6 fatcat:2njkc6meabhaxosl4wircumfjm

Asian language processing: current state-of-the-art

Chu-Ren Huang, Takenobu Tokunaga, Sophia Yat Mei Lee
2007 Language Resources and Evaluation  
The challenge is made more formidable by the fact that as a whole, Asian languages range from the language with most speakers in the world (Mandarin Chinese, close to 900 million native speakers) to the  ...  One of the first and most obvious challenges is the multitude and diversity of languages: more than 2,000 languages are listed as languages in Asia by Ethnologue (Gordon, 2005) , representing four major  ...  In addition, without the diligent work of both Estella La Jappon and Jenna Cataluna at Springer, we would never have been able to negotiate all the steps of publication.  ... 
doi:10.1007/s10579-007-9041-9 fatcat:ryrtqspk5nggdgzp7o75knch3m

Neural Natural Language Generation: A Survey on Multilinguality, Multimodality, Controllability and Learning

Erkut Erdem, Menekse Kuyu, Semih Yagcioglu, Anette Frank, Letitia Parcalabescu, Barbara Plank, Andrii Babii, Oleksii Turuta, Aykut Erdem, Iacer Calixto, Elena Lloret, Elena-Simona Apostol (+6 others)
2022 The Journal of Artificial Intelligence Research  
Especially, the advances in deep learning over the past couple of years have led to neural approaches to natural language generation (NLG).  ...  This report also focuses on the seminal applications of these NNLG models such as machine translation, description generation, automatic speech recognition, abstractive summarization, text simplification  ...  AE was supported by BAGEP 2021 Award of the Science Academy. EE was supported in part by TUBA GEBIP 2018 Award. BP is in in part funded by Independent Research Fund Denmark (DFF) grant 9063-00077B.  ... 
doi:10.1613/jair.1.12918 fatcat:xfnul3j5azchfe6pvgvwy3z6em

Conversational agents for learning foreign languages – a survey [article]

Jasna Petrovic, Mladjan Jovanovic
2020 arXiv   pre-print
In this paper, we provide an overview of the chatbots for learning languages, critically analyze existing approaches, and discuss the major challenges for future work.  ...  Conversational practice, while crucial for all language learners, can be challenging to get enough of and very expensive.  ...  One of the benefits of using this chatbot is that, in addition to conversing in Korean, the chatbot also uses English to answer and ask questions and clarify things.  ... 
arXiv:2011.07901v1 fatcat:pt6sykcgzfew3prrvimrqjvzxe

CLiFF Notes: Research in the Language, Information and Computation Laboratory of the University of Pennsylvania [article]

Editors: Matthew Stone, Libby Levison
1995 arXiv   pre-print
Short abstracts by computational linguistics researchers at the University of Pennsylvania describing ongoing individual and joint projects.  ...  Acknowledgements Thanks to all the contributors.  ...  translate such structures between Korean and English; work on lexical selection in translating from Korean to English; and recovering dropped NPs in Korean in preparation for translating to English.  ... 
arXiv:cmp-lg/9506008v1 fatcat:aidgv3pdzvfatc7yjygdvthcjq

Natural Language Processing: A Human-Computer Interaction Perspective [chapter]

Bill Manaris
1998 Advances in Computers  
This chapter examines the field of natural language processing as it relates to humancomputer interaction by focusing on its history, interactive application areas, theoretical approaches to linguistic  ...  During this time, it has significantly contributed to the field of human-computer interaction in terms of theoretical results and practical applications.  ...  Slator is acknowledged for his contribution to an early outline -especially on the phases of NLP evolution; István Berkeley for discussions on philosophical and connectionist issues; and Eleni Efthimiou  ... 
doi:10.1016/s0065-2458(08)60665-8 fatcat:qkvovunv6bdqrn4wwuutmtwd6m

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
To inject knowledge, we use a state-of-the-art system which cross-links (or "grounds") expressions in free text to Wikipedia.  ...  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.  ...  for colloquial Arabic to English machine translation.  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria

Artificial Intelligence Technologies for Sign Language

Ilias Papastratis, Christos Chatzikonstantinou, Dimitrios Konstantinidis, Kosmas Dimitropoulos, Petros Daras
2021 Sensors  
To this end, this survey aims to provide a comprehensive review of state-of-the-art methods in sign language capturing, recognition, translation and representation, pinpointing their advantages and limitations  ...  In addition, the survey presents a number of applications, while it discusses the main challenges in the field of sign language technologies.  ...  The input was translated to English and then to the corresponding Indian sign language using Natural Language Processing (NLP) rules and techniques.  ... 
doi:10.3390/s21175843 pmid:34502733 fatcat:ylhimzy6brd2zpbaz274vl7x3u

Machine Translation from Signed to Spoken Languages: State of the Art and Challenges [article]

Mathieu De Coster, Dimitar Shterionov, Mieke Van Herreweghe, Joni Dambre
2022 arXiv   pre-print
We give a high-level introduction to sign language linguistics and machine translation to illustrate the requirements of automatic sign language translation.  ...  Nevertheless, research in this domain is performed mostly by computer scientists in isolation.  ...  De Coster's research is funded by the Research Foundation Flanders (FWO Vlaanderen): file number 77410. This work has been conducted within the SignON project.  ... 
arXiv:2202.03086v3 fatcat:g2t2vovwjjgxlevtzv26nbf7z4
« Previous Showing results 1 — 15 out of 828 results