I just completed my first guest blogging post over at mind x the + gap where I talked about the mutual history of language and commerce, as well as some thoughts on how that will continue into the future. Since the focus of Mil Joshi‘s blog is more towards psychology and economics, the following is [...]
Posts Tagged ‘machine translation’
Language, Commerce and Google Translate
Posted: 10 February 2009 in UncategorizedTags: commerce, creoles, economics, google translate, guest blogging, history, language, language change, linguistic homogenization, linguistics, machine translation, pidgins, trade
3
MT Eval with Binary Comparisons
Posted: 12 May 2008 in UncategorizedTags: computational linguistics, machine translation, mt, machine learning, recommender systems, collaborative filtering, machine translation evaluation, mt eval, rankings
The standard way of doing human evaluations of machine translation (MT) quality for the past few years has been to have human judges grade each sentence of MT output against a reference translation on measures of adequacy and fluency. Adequacy is the level at which the translation conveys the information contained in the original (source [...]
Seven Grand Tech Challenges
Posted: 16 April 2008 in UncategorizedTags: futurism, gartner, information technology, it, machine translation, management, predictions, technology
According to Gartner, these will keep us busy for the next 25 years. Eliminate need to recharge batteries on wireless devices Improved parallel processing (at the PL and OS levels) Gesture detection Speech-to-speech machine translation Long term persistent storage 100-fold increase in programmer productivity Identifying the financial consequences of IT investment I think numbers 1-3, [...]
Is Systran going statistical?
Posted: 27 February 2008 in UncategorizedTags: computational linguistics, jobs, linguist list, machine translation, statistical machine translation, systran
Systran is one of the oldest companies around that provide machine translation software. They power some language-pairs of Microsoft’s translation service, Altavista’s Babelfish, and quite a few others (including, until recently, Google). In the past, their software has been rule-based, so translation is done with a bilingual dictionary and a set of rules of how [...]
Syntactic Features for MT Eval
Posted: 24 February 2008 in UncategorizedTags: computational linguistics, kernel trick, machine translation, machine translation evaluation, mt eval, syntax, tree kernels
Stepping back in time in MT Eval from my last post, Liu and Gildea (2005) were among the first to really bring syntactic information to evaluating machine translation output. They proposed three metrics for evaluating machine hypotheses: the subtree metric (STM), the tree kernel metric (TKM), and the headword chain metric (HWCM). STM and TKM [...]
Labeled Dependencies in MT Evaluation
Posted: 20 February 2008 in UncategorizedTags: computational linguistics, dependency grammar, lexical functional grammar, machine translation, machine translation evaluation, mt eval
Since Papineni et al. (2002) introduced the BLEU metric for machine translation evaluation, string matching functions have dominated the field. These metrics work well enough, but there are cases where they break down and more and more research is revealing their biases. Also, BLEU does not correlate especially well with human judgments, so the quality [...]
MT Evaluation Shared Task
Posted: 13 February 2008 in UncategorizedTags: acl, computational linguistics, machine translation, machine translation evaluation, mt eval, workshops
At ACL this year, the Third Workshop on Stastical Machine Translation will be held and they are featuring a shared task on MT evaluation. The shared task will involve evaluating output from the shared translation task, which will be released on March 24th, with short papers and rankings due on April 4th. I created an [...]
What’s new in MT Evaluation?
Posted: 6 February 2008 in UncategorizedTags: ai complete, computational linguistics, context, evaluation, machine translation, machine translation evaluation, mt eval, word sense disambiguation
This is the question I will have to answer over the next few weeks. One of my classes this semester is the Advanced Machine Translation Seminar (and I hope that link works outside of CMU). Each of us who has registered for the class will present a certain topic in MT and then do a [...]
Cognate Identification: Orthographic Methods
Posted: 26 January 2008 in UncategorizedTags: algorithms, cognate identification, cognates, computational linguistics, historical linguistics, language change, linguistics, machine translation, natural language processing, orthography, string matching
In previous posts on cognate identification, I discussed the difference between strict and loose cognates. Loose cognates are words in two languages that have the same or similar written forms. I also described how approaches to cognate identification tend to differ based on whether the data being used is plain text or phonetic transcriptions. The [...]
Old English Translator
Posted: 8 November 2007 in UncategorizedTags: computational morphology, dictionaries, historical linguistics, languages, machine translation, morphology, old english, open source
Phil Barthram recently announced on the ENGLISC mailing list a new Old English translator. For those unfamiliar with Old English, this is not the really cheap malt liquor. This is the grandmother of Modern English (by way of its mother, Middle English and a few others, chiefly Norman French). Whereas an Olde English (the malt [...]
