Spectral clustering for example based machine translation

Gangadharaiah, Rashmi; Brown, Ralf D.; Carbonell, Jaime G.

doi:10.3115/1614049.1614060

Cited by 14 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MWE-aware strategies in EBMT and RBMT. EBMT (Gangadharaiah, Brown, and Carbonell 2006) or RBMT strategies (Anastasiou 2008;Forcada et al 2011;Monti et al 2011) dynamically apply rules to handle MWE translations. Some rules are identified from the syntactic tree alignments (Segura and Prince 2011) and integrated into an EBMT system to handle discontiguous MWEs.…”

Section: Identificationmentioning

confidence: 99%

Multiword Expression Processing: A Survey

Constant

Eryiğit

Monti

et al. 2017

Computational Linguistics

196

126

View full text Add to dashboard Cite

Multiword expressions (MWEs) are a class of linguistic forms spanning conventional word boundaries that are both idiosyncratic and pervasive across different languages. The structure of linguistic processing that depends on the clear distinction between words and phrases has to be re-thought to accommodate MWEs. The issue of MWE handling is crucial for NLP applications, where it raises a number of challenges. The emergence of solutions in the absence of guiding principles motivates this survey, whose aim is not only to provide a focused review of MWE processing, but also to clarify the nature of interactions between MWE processing and downstream applications. We propose a conceptual framework within which challenges and research contributions can be positioned. It offers a shared understanding of what is meant by “MWE processing,” distinguishing the subtasks of MWE discovery and identification. It also elucidates the interactions between MWE processing and two use cases: Parsing and machine translation. Many of the approaches in the literature can be differentiated according to how MWE processing is timed with respect to underlying use cases. We discuss how such orchestration choices affect the scope of MWE-aware systems. For each of the two MWE processing subtasks and for each of the two use cases, we conclude on open issues and research perspectives.

show abstract

Section: Identificationmentioning

confidence: 99%

Multiword Expression Processing: A Survey

Constant

Eryiğit

Monti

et al. 2017

Computational Linguistics

196

126

View full text Add to dashboard Cite

show abstract

“…While combining different system types has proven beneficial (e.g. Simard et al (2007), where the PB-SMT system Portage corrects the output of the Systran RBMT system), there was no significant improvement in overall translation score when merging these two EBMT systems, although including the MaTrEx system's chunks did improve the CMU clustering method (Gangadharaiah et al 2006).…”

Section: Integration With Other Modelsmentioning

confidence: 97%

Panning for EBMT gold, or “Remembering not to forget”

Way

2010

Machine Translation

View full text Add to dashboard Cite

A very useful service to the example-based machine translation (EBMT) community was provided by Harold Somers in his summary article which appeared in 1999, and was extended in our 2003 book Recent advances in example-based machine translation. As well as providing a comprehensive review of the paradigm, Somers gives a categorisation of the different instantiations of the basic model. In this paper, we provide a complementary view to that of Somers. Today's EBMT systems learn by analogy. Perhaps even more so than statistical models of translation, one might view these systems as being incapable of forgetting. We researchers and system developers, on the other hand, often forget or are ignorant of techniques and models presented in prior research. The primary aim of this paper is to try to ensure that golden nuggets from past (now quite distantly so) EBMT research papers are gathered together and presented here for a new generation of researchers keen to operate in the paradigm, especially given the spate of recent open-source releases of EBMT systems. We revisit the findings of the previous main research papers, relate them to some of the major research efforts which have taken place since then, and examine especially the prophecies given in the older pieces of work to see the extent to which they have been borne out in the newer research. Given the strong convergence between the leading corpusbased approaches to MT, especially since the introduction of phrase-based statistical MT, a further hope is that these findings may also prove useful to researchers and developers in other areas of MT.123 178 A. Way Decoding · Postprocessing · String-based models · Tree-based models · Hybrid models · Word alignment · Phrase alignment · Subtree alignment · Generalized templates

show abstract

“…Random sampling is often surprisingly powerful (Kendall and Smith, 1938;Knuth, 1991;Sennrich et al, 2016a). There is extensive research to beat random sampling by methods based on entropy (Koneru et al, 2022), coverage and uncertainty (Peris and Casacuberta, 2018;Zhao et al, 2020), clustering Gangadharaiah et al, 2009), consensus , syntactic parsing (Miura et al, 2016), density and diversity (Koneru et al, 2022;Ambati et al, 2011), and learning to learn active learning strategies (Liu et al, 2018).…”

Section: Active Learning In Machine Translationmentioning

confidence: 99%

Train Global, Tailor Local: Minimalist Multilingual Translation into Endangered Languages

Zhou,

Niehues,

Waibel

2023

Proceedings of the the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)

View full text Add to dashboard Cite

In many humanitarian scenarios, translation into severely low resource languages often does not require a universal translation engine, but a dedicated text-specific translation engine. For example, healthcare records, hygienic procedures, government communication, emergency procedures and religious texts are all limited texts. While generic translation engines for all languages do not exist, translation of multilingually known limited texts into new, endangered languages may be possible and reduce human translation effort. We attempt to leverage translation resources from many rich resource languages to efficiently produce best possible translation quality for a well known text, which is available in multiple languages, in a new, severely low resource language. We examine two approaches: 1.) best selection of seed sentences to jump start translations in a new language in view of best generalization to the remainder of a larger targeted text(s), and 2.) we adapt large general multilingual translation engines from many other languages to focus on a specific text in a new, unknown language. We find that adapting large pretrained multilingual models to the domain/text first and then to the severely low resource language works best. If we also select a best set of seed sentences, we can improve average chrF performance on new test languages from a baseline of 21.9 to 50.7, while reducing the number of seed sentences to only ∼1,000 in the new, unknown language.

show abstract

Spectral clustering for example based machine translation

Cited by 14 publications

References 3 publications

Multiword Expression Processing: A Survey

Multiword Expression Processing: A Survey

Panning for EBMT gold, or “Remembering not to forget”

Train Global, Tailor Local: Minimalist Multilingual Translation into Endangered Languages

Contact Info

Product

Resources

About