Toward a unified approach to statistical language modeling for Chinese

Gao, Jianfeng; Goodman, Joshua; Li, Mingjing; Lee, Kai-Fu

doi:10.1145/595576.595578

Cited by 97 publications

(68 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basic architecture of ASR is inspired by the human auditory system. [7] Speech utterances of word sequence W is decided by speaker mind and delivered through his / her text generator [6]. Speaker vocal apparatus contain the signal processing component and produce the speech waveform which passes through the many noise channels.…”

Section: Motivationmentioning

confidence: 99%

Implementation and Performance Evaluation of Speaker Adaptive Continuous Hindi ASR using Tri-phone based Acoustic Modelling

2015

March 29-30, 2015 Singapore

View full text Add to dashboard Cite

Section: Motivationmentioning

confidence: 99%

Implementation and Performance Evaluation of Speaker Adaptive Continuous Hindi ASR using Tri-phone based Acoustic Modelling

2015

March 29-30, 2015 Singapore

View full text Add to dashboard Cite

“…Many methods (Lin et al, 1997;Gao et al, 2002;Klakow, 2000;Moore and Lewis, 2010;Axelrod et al, 2011) rank sentences in the generaldomain data according to their similarity to the in-domain data and select only those with score higher than some threshold. Such methods are effective and widely used.…”

Section: Related Workmentioning

confidence: 99%

Kneser-Ney Smoothing on Expected Counts

Zhang¹,

Chiang²

2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Widely used in speech and language processing, Kneser-Ney (KN) smoothing has consistently been shown to be one of the best-performing smoothing methods. However, KN smoothing assumes integer counts, limiting its potential uses-for example, inside Expectation-Maximization. In this paper, we propose a generalization of KN smoothing that operates on fractional counts, or, more precisely, on distributions over counts. We rederive all the steps of KN smoothing to operate on count distributions instead of integral counts, and apply it to two tasks where KN smoothing was not applicable before: one in language model adaptation, and the other in word alignment. In both cases, our method improves performance significantly.

show abstract

“…Language modeling research has explored methods for subselecting newdomain data from a large monolingual target language corpus for use as language model training data (Lin et al, 1997;Klakow, 2000;Gao et al, 2002;Mansour et al, 2011). Translation modeling research has typically assumed that either (1) two parallel datasets are available, one in the old domain and one in the new, or (2) a large, mixed-domain parallel training corpus is available.…”

Section: Related Workmentioning

confidence: 99%

Proceedings of the Ninth Workshop on Statistical Machine Translation

Bojar

Buck

Federmann

et al. 2014

View full text Add to dashboard Cite

The focus of our workshop was to use parallel corpora for machine translation. Recent experimentation has shown that the performance of SMT systems varies greatly with the source language. In this workshop we encouraged researchers to investigate ways to improve the performance of SMT systems for diverse languages, including morphologically more complex languages, languages with partial free word order, and low-resource languages.Prior to the workshop, in addition to soliciting relevant papers for review and possible presentation, we conducted four shared tasks: a general translation task, a medical translation task, a quality estimation task, and a task to test automatic evaluation metrics. The medical translation task was introduced this year to address the important issue of domain adaptation within SMT. The results of the shared tasks were announced at the workshop, and these proceedings also include an overview paper for the shared tasks that summarizes the results, as well as provides information about the data used and any procedures that were followed in conducting or scoring the task. In addition, there are short papers from each participating team that describe their underlying system in greater detail.Like in previous years, we have received a far larger number of submission than we could accept for presentation. This year we have received 27 full paper submissions and 49 shared task submissions. In total WMT 2014 featured 12 full paper oral presentations and 49 shared task poster presentations.The invited talk was given by Alon Lavie (Carnegie Mellon University and Safaba Translation Solutions, Inc.) entitled "Machine Translation in Academia and in the Commercial World -a Contrastive Perspective".We would like to thank the members of the Program Committee for their timely reviews. We also would like to thank the participants of the shared task and all the other volunteers who helped with the evaluations. is a ranking of the systems that participated in its shared translation tasks, produced by aggregating pairwise sentencelevel comparisons collected from human judges. Over the past few years, there have been a number of tweaks to the aggregation formula in attempts to address issues arising from the inherent ambiguity and subjectivity of the task, as well as weaknesses in the proposed models and the manner of model selection.We continue this line of work by adapting the TrueSkill TM algorithm -an online approach for modeling the relative skills of players in ongoing competitions, such as Microsoft's Xbox Live -to the human evaluation of machine translation output. Our experimental results show that TrueSkill outperforms other recently proposed models on accuracy, and also can significantly reduce the number of pairwise annotations that need to be collected by sampling non-uniformly from the space of system competitions. IntroductionThe Workshop on Statistical Machine Translation (WMT) has long been a central event in the machine translation (MT) community for the evaluation of MT output. It hosts...

show abstract

Toward a unified approach to statistical language modeling for Chinese

Cited by 97 publications

References 14 publications

Implementation and Performance Evaluation of Speaker Adaptive Continuous Hindi ASR using Tri-phone based Acoustic Modelling

Implementation and Performance Evaluation of Speaker Adaptive Continuous Hindi ASR using Tri-phone based Acoustic Modelling

Kneser-Ney Smoothing on Expected Counts

Proceedings of the Ninth Workshop on Statistical Machine Translation

Contact Info

Product

Resources

About