Toward Practical Spoken Language Translation

Zong, Chengqing; Seligman, Mark

doi:10.1007/s10590-006-9000-z

Cited by 9 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The repository of prepared translations thus serves as translation memory, an element of many MT systems, whether rule-based, statistical, or neural. This approach was employed, for instance, in the Converser for Healthcare prototype speech translation system (Seligman and Dillinger, 2006a, 2006b, 2012, 2014Dillinger and Seligman, 2004;Zong and Seligman, 2005) under the proprietary name of Translation Shortcuts™. Section 2.3.3.7 will demonstrate its use in context.…”

Section: Offline Preparation Of Outputmentioning

confidence: 99%

Speech and Translation Technologies

Seligman

2023

Translation Technology in Accessible Health Communication

Self Cite

View full text Add to dashboard Cite

mark seligman IntroductionCross-language communication in healthcare is urgently needed. Daily and nightly throughout the world, thousands of conversations are required between caregiversdoctors, nurses, administrators, volunteers, and othersand patients or family members with differing native languages.Chapter 1 describes and illustrates the exploding development of the relevant linguistic technologiesmachine translation (MT) of text, automatic speech recognition (ASR), and text-to-speech (TTS). The related infrastructurewireless communication, cloud computing, and mobile deviceshas also been developing apace. This chapter will shift focus to the combination and application of these technologies in the healthcare context, with special interest in speech translation.Given this impressive and accelerating progress, we'd expect various automatic translation and speech-enabled systems to be in widespread use by now; in fact, however, adoption remains slow. We'll examine the obstacles to adoption and directions for overcoming them in Section 2.2. In Section 2.3, we'll examine two major types of speech translation systems, concentrating on their respective approaches to the same obstacles. Section 2.4 will survey some healthcare-oriented communication systems, past and future. We'll conclude with an optimistic forecast for speech and translation applications in healthcare, tempered by due cautions. Obstacles to Adoption and Potential SolutionsOne key factor in the lagging adoption of linguistic technology in healthcare is the sheer difficulty of understanding the relevant technologies, and thus the natural hesitation to trust them. Accordingly, Chapter 1 aimed to bridge the 47

show abstract

Section: Offline Preparation Of Outputmentioning

confidence: 99%

Speech and Translation Technologies

Seligman

2023

Translation Technology in Accessible Health Communication

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast, research on automatic NE semantic translation is less common. Zhang et al (2005) proposed a phrase-based context-dependent joint probability model for semantic translation, which is similar to phrase-level translation models in statistical MT (Zong and Seligman 2005;Hu, Zong, and Xu 2006). Chen, Yang, and Lin (2003) and Chen et al (2006) studied formulation and transformation rules for English-Chinese NEs.…”

Section: Related Workmentioning

confidence: 99%

A Joint Model to Identify and Align Bilingual Named Entities

Chen

Zong

Su³

2013

Computational Linguistics

Self Cite

View full text Add to dashboard Cite

In this article, an integrated model is derived that jointly identifies and aligns bilingual named entities (NEs) between Chinese and English. The model is motivated by the following observations: (1) whether an NE is translated semantically or phonetically depends greatly on its entity type, (2) entities within an aligned pair should share the same type, and (3) the initially detected NEs can act as anchors and provide further information while selecting NE candidates. Based on these observations, this article proposes a translation mode ratio feature (defined as the proportion of NE internal tokens that are semantically translated), enforces an entity type consistency constraint, and utilizes additional new NE likelihoods (based on the initially detected NE anchors).Experiments show that this novel method significantly outperforms the baseline. The typeinsensitive F-score of identified NE pairs increases from 78.4% to 88.0% (12.2% relative improvement) in our Chinese-English NE alignment task, and the type-sensitive F-score increases from 68.4% to 83.0% (21.3% relative improvement). Furthermore, the proposed model demonstrates its robustness when it is tested across different domains. Finally, when semi-supervised learning is conducted to train the adopted English NE recognition model, the proposed model also significantly boosts the English NE recognition type-sensitive F-score.

show abstract

“…As for SMT, there have been many effective translation models for sentence translation [Zong and Seligman 2005]. But these models are not suitable for NE translation.…”

Section: Introductionmentioning

confidence: 99%

A Structure-Based Model for Chinese Organization Name Translation

Chen

Zong

2008

ACM Transactions on Asian Language Information Processing

Self Cite

View full text Add to dashboard Cite

Named entity (NE) translation is a fundamental task in multilingual natural language processing. The performance of a machine translation system depends heavily on precise translation of the inclusive NEs. Furthermore, organization name (ON) is the most complex NE for translation among all the NEs. In this article, the structure formulation of ONs is investigated and a hierarchical structure-based ON translation model for Chinese-to-English translation system is presented. First, the model performs ON chunking; then both the translation of words within chunks and the process of chunk-reordering are achieved by synchronous context-free grammar (CFG). The CFG rules are extracted from bilingual ON pairs in a training program.The main contributions of this article are: (1) defining appropriate chunk-units for analyzing the internal structure of Chinese ONs; (2) making the chunk-based ON translation feasible and flexible via a hierarchical CFG derivation; and (3) proposing a training architecture to automatically learn the synchronous CFG for constructing ONs with chunk-units from aligned bilingual ON pairs. The experiments show that the proposed approach translates the Chinese ONs into English with an accuracy of 93.75% and significantly improves the performance of a baseline statistical machine translation (SMT) system.

show abstract

Toward Practical Spoken Language Translation

Cited by 9 publications

References 34 publications

Speech and Translation Technologies

Speech and Translation Technologies

A Joint Model to Identify and Align Bilingual Named Entities

A Structure-Based Model for Chinese Organization Name Translation

Contact Info

Product

Resources

About