LOGIN TO YOUR ACCOUNT

Username
Password
Remember Me
Or use your Academic/Social account:

CREATE AN ACCOUNT

Or use your Academic/Social account:

Congratulations!

You have just completed your registration at OpenAire.

Before you can login to the site, you will need to activate your account. An e-mail will be sent to you with the proper instructions.

Important!

Please note that this site is currently undergoing Beta testing.
Any new content you create is not guaranteed to be present to the final version of the site upon release.

Thank you for your patience,
OpenAire Dev Team.

Close This Message

CREATE AN ACCOUNT

Name:
Username:
Password:
Verify Password:
E-mail:
Verify E-mail:
*All Fields Are Required.
Please Verify You Are Human:
fbtwitterlinkedinvimeoflicker grey 14rssslideshare1
Languages: English
Types: Other
Subjects:
Quality estimation models are used to predict the quality of the output from a spoken language translation (SLT) system. When these scores are used to rerank a k-best list, the rank of the scores is more important than their absolute values. This paper proposes groupwise learning to model this rank. Groupwise features were constructed by grouping pairs, triplets or M-plets among the ASR k-best outputs of the same sentence. Regression and classification models were learnt and a score combination strategy was used to predict the rank among the k-best list. Regression models with pairwise features give a bigger gain over other model and feature constructions. Groupwise learning is robust to sentences with different ASR-confidence. This technique is also complementary to linear discriminant analysis feature projection. An overall BLEU score improvement of 0.80 was achieved on an in-domain English-to-French SLT task.
  • The results below are discovered through our pilot algorithms. Let us know how we are doing!

    • [1] Natalia Segal, Hlne Bonneau-Maynard, Quoc Khanh Do, Alexandre Allauzen, Jean-Luc Gauvain, Lori Lamel, and Franois Yvon, “LIMSI English-French Speech Translation System,” in Proceedings of the eleventh International Workshop on Spoken Language Translation (IWSLT), 2014.
    • [2] Nicholas Ruiz, Qin Gao, William Lewis, and Marcello Federico, “Adapting machine translation models toward misrecognized speech with text-to-speech pronunciation rules and acoustic confusability,” in Proc. Interspeech, 2015, pp. 2247- 2251.
    • [3] Hermann Ney, “Speech translation: coupling of recognition and translation,” in Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on, 1999, vol. 1, pp. 517-520 vol.1.
    • [4] Alicia Pe´rez, M. In/'es Torres, and Francisco Casascuberta, “Potential scope of a fully-integrated architecture for speech translation,” in Proc. EAMT, 2010.
    • [5] Evgeny Matusov, Stephan Kanthak, and Hermann Ney, “On the integration of speech recognition and statistical machine translation,” in Proc. Interspeech, 2005, pp. 3177-3180.
    • [6] Nicola Bertoldi, Richard Zens, Marcello Federico, and Wade Shen, “Efficient speech translation through confusion network decoding,” Audio, Speech, and Language Processing, IEEE Transactions on, vol. 16, no. 8, pp. 1696-1705, 2008.
    • [7] Evgeny Matusov and Hermann Ney, “Lattice-based asr-mt interface for speech translation,” Audio, Speech, and Language Processing, IEEE Transactions on, vol. 19, no. 4, pp. 721-732, 2011.
    • [8] George A. Saon and Michael A. Picheny, “Lattice-based Viterbi decoding techniques for speech translation,” in Proc. ASRU, 2007, pp. 386-389.
    • [9] V. H. Quan, M. Federico, and M. Cettolo, “Integrated Nbest re-ranking for spoken language translation,” in Proc. Eurospeech, 2005.
    • [10] Chi-Ho Li, Nan Duan, Yinggong Zhao, Shujie Liu, and Lei Cui, “The MSRA machine translation system for IWSLT 2010,” in Proc. IWSLT, 2010, pp. 135-138.
    • [11] Ruiqiang Zhang, Genichio Kikui, Hirofumi Yamamoto, Taro Watanabe, Frank Soong, and Wai Kit Lo, “A unified approach in speech-to-speech translation: Integrating features of speech recognition and machine translation,” in Proc. COLING, 2004.
    • [12] Raymond W. M. Ng, Kashif Shah, Lucia Specia, and Thomas Hain, “A study on the stability and effectiveness of features in quality estimation for spoken langauge translation,” in Proc. Interspeech, 2015.
    • [13] Lucia Specia, Kashif Shah, Jose´ G. C. de Souza, and Trevor Cohn, “QuEst - A translation quality estimation framework,” in Proceedings of 51st Annual Meeting of the Association for Computational Linguistics: Demo Session, 2013, p. 794.
    • [14] K. Shah, E. Avramidis, E Bic¸ici, and L Specia, “Quest - design, implementation and extensions of a framework for machine translation quality estimation,” Prague Bull. Math. Linguistics, vol. 100, pp. 19-30, 2013.
    • [15] Michael Denkowski and Alon Lavie, “Meteor universal: Language specific translation evaluation for any target language,” in Proceedings of WMT14, 2014.
    • [16] Alex J. Smola and Bernhard Scho¨lkopf, “A tutorial on support vector regression,” 1998.
    • [17] Faqiang Wang, Wangmeng Zuo, Lei Zhang, Deyu Meng, and David Zhang, “A kernel classification framework for metric learning,” IEEE Transactions on Neural Networks and Learning Systems, vol. 26, no. 9, pp. 1950-1962, 2015.
    • [18] Carl Brunner, Andreas Fischer, Klaus Luig, and Thorsten Thies, “Pairwise support vector machines and their application to large scale problems,” Journal of Machine Learning Research, vol. 13, pp. 2279-2292.
    • [19] Li Liao and William Stafford Noble, “Combining pairwise sequence similarity and support vector machines for detecting remote protein evolutionary and structural relationships,” Journal of Computational Biology, vol. 10, no. 6, pp. 857-868, 2003.
    • [20] Wei Chu and S. Sathiya Keerthi, “Support vector ordinal regression,” Neural Computation, vol. 19, no. 3, pp. 792-815, March 2007.
    • [21] Eyke Hllermeier, Johannes Frnkranz, Weiwei Cheng, and Klaus Brinker, “Label ranking by learning pairwise preferences,” Artificial Intelligence, vol. 172, no. 167, pp. 1897 - 1916, 2008.
    • [22] Thorsten Joachims, “Training linear svms in linear time,” in Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA, 2006, KDD '06, pp. 217-226, ACM.
    • [23] LLC, “Liberated learning //liberatedlearning.com.
    • [24] ECRN, “Stanford university's entrepreneurship corner,” http://ecorner.stanford.edu.
    • [25] Ondrˇej Bojar, Christian Buck, Christian Federmann, Barry Haddow, Philipp Koehn, Johannes Leveling, Christof Monz, Pavel Pecina, Matt Post, Herve Saint-Amand, Radu Soricut, Lucia Specia, and Alesˇ Tamchyna, “Findings of the 2014 workshop on statistical machine translation,” in Proceedings of WMT14, 2014, pp. 12-58.
    • [26] Mauro Cettolo, Christian Girardi, and Marcello Federico, “Wit3: Web inventory of transcribed and translated talks,” in Proceedings of the 16th Conference of the European Association for Machine Translation (EAMT), Trento, Italy, May 2012, pp. 261-268.
    • [27] TED, “Technology entertainment design,” http://www. ted.com, 2006.
    • [28] Philipp Koehn, Hieu Hoang, Alexandra Birch, Chris CallisonBurch, Marcello Federico, Nicola Bertoldi, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens, Chris Dyer, Ondrˇej Bojar, Alexandra Constantin, and Evan Herbst, “Moses: open source toolkit for statistical machine translation,” in ACL '07: Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions, 2007, pp. 177-180.
    • [29] Raymond W. M. Ng, Kashif Shah, Wilker Aziz, Lucia Specia, and Thomas Hain, “Quality estimation for ASR K-best list rescoring in spoken language translation,” in Proc. of ICASSP, 2015.
    • [30] Olivier Chapelle, “Training a support vector machine in the primal,” Neural Computation, vol. 19, no. 5, pp. 1155-1178, 2007.
  • No related research data.
  • Discovered through pilot similarity algorithms. Send us your feedback.

Share - Bookmark

Cite this article