Interactive Pattern Recognition applied to Natural Language Processing

This paper is concerned with combining models for decoding an optimum translation for a dictation based machine aided human translation (MAHT) task. Statistical language model (SLM) probabilities in automatic speech recognition (ASR) are updated using statistical machine translation (SMT) model probabilities. The effect of this procedure is evaluated for utterances from human translators dictating translations of source language documents. It is shown that computational complexity is significantly reduced while at the same time word error rate is reduced by 30%.

show abstract

“…The estimation of the sentence level translation confidence and its role in updating the weights in Eq. (9) is discussed in [7].…”

Section: Updating N-gram Lm Probabilitiesmentioning

confidence: 98%

Efficient integration of translation and speech models in dictation based machine aided human translation

Rodríguez

Reddy

Rose

2012

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

Application of bioinspired algorithms for solving transcomputational tasks

Kureichik

Kursitys

Kuliev

et al. 2020

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The paper investigates the pattern recognition task as one of the most important transcomputational problems. Pattern recognition is applied for statistical data analysis, signal processing, image analysis, bioinformatics, machine learning, and many other fields. The area of application is related to automated pattern detection in the data using computer algorithms and data classification in terms of different categories. The development of new ideas in the processing of large volumes of information creates a new trend in the pattern recognition area. A specific field is formed by the bioinspired algorithms as mathematical reorganization, that transform the initial information into the results based on simulating the evolution methods, natural analogies, and statistic approach. In terms of computer modelling based on the bioinspired algorithms, we can create and develop difficult concepts, for which we have no analytical description. The authors present the optimal bioinspired algorithms based on the ant, monkey, and bat behavior in nature and develop software based on the principle of pattern recognition using the uploaded photo and downloading the results into the file. The experiments demonstrate the effectiveness of the proposed approach.

show abstract

Building task-oriented machine translation systems

Trilles¹

View full text Add to dashboard Cite

The main goal of this thesis is to develop computer assisted translation and machine translation systems which present a more robust synergy with their potential users. Hence, the main purpose is to make current state-of-the-art systems more ergonomic, intuitive and efficient, so that the human expert feels more comfortable when using them. For doing this, different techniques are presented, focusing on improving the adaptability and response time of the underlying statistical machine translation systems, as well as a strategy aiming at enhancing human-machine interaction within an interactive machine translation setup. All of this with the ultimate purpose of filling in the existing gap between the state of the art in machine translation and the final tools that are usually available for the final human translators.Concerning the response time of the machine translation systems, a parameter pruning technique is presented, whose intuition stems from the concept of bilingual segmentation, but which evolves towards a full parameter re-estimation strategy. By using such strategy, experimental results presented here prove that it is possible to achieve reductions of up to 97% in the number of parameters required without a significant loss in translation quality. Being robust across different language pairs, these results evidence that the pruning technique presented is effective in a traditional machine translation scenario, and could be used for instance in a post-editing setup. Nevertheless, experiments carried out within a simulated interactive machine translation environment are slightly less convincing, since a trade-off between response time and translation quality is needed.Two orthogonally different approaches are presented with the purpose of increasing the adaptability of the statistical machine translation systems. On the one hand, we investigate how to increase the adaptability of the language model, by subdividing it into several smaller language models which are then interpolated in translation time according to the source sentence to be translated. The specific sub-models are built either by taking advantage of supervised information present in certain bilingual corpora, or by performing unsupervised clustering on the training set, with the aim of uncovering specific sub-topics or language vii styles present. On the other hand, Bayesian predictive adaptation is elucidated as an efficient strategy for adapting the translation models present in state-of-the-art machine translation systems. Although adaptation experiments are only performed within the traditional machine translation framework, the results obtained are compelling enough for implementing them within an interactive setup, and such work will be done in the near future. Nevertheless, it should be noted that the techniques developed may be readily implemented within a computer assisted translation scenario, in which a statistical machine translation system is providing the translations that the user needs to modify and validate.Finally...

show abstract

Interactive Pattern Recognition applied to Natural Language Processing

Cited by 3 publications

References 36 publications

Efficient integration of translation and speech models in dictation based machine aided human translation

Efficient integration of translation and speech models in dictation based machine aided human translation

Application of bioinspired algorithms for solving transcomputational tasks

Building task-oriented machine translation systems

Contact Info

Product

Resources

About