To Cache or Not To Cache? Experiments with Adaptive Models in Statistical Machine Translation

نویسنده

  • Jörg Tiedemann
چکیده

We report results of our submissions to the WMT 2010 shared translation task in which we applied a system that includes adaptive language and translation models. Adaptation is implemented using exponentially decaying caches storing previous translations as the history for new predictions. Evidence from the cache is then mixed with the global background model. The main problem in this setup is error propagation and our submissions essentially failed to improve over the competitive baseline. There are slight improvements in lexical choice but the global performance decreases in terms of BLEU scores.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Context Adaptation in Statistical Machine Translation Using Models with Exponentially Decaying Cache

We report results from a domain adaptation task for statistical machine translation (SMT) using cache-based adaptive language and translation models. We apply an exponential decay factor and integrate the cache models in a standard phrasebased SMT decoder. Without the need for any domain-specific resources we obtain a 2.6% relative improvement on average in BLEU scores using our dynamic adaptat...

متن کامل

Adaptive Language and Translation Models for Interactive Machine Translation

We describe experiments carried out with adaptive language and translation models in the context of an interactive computer-assisted translation program. We developed cache-based language models which were then extended to the bilingual case for a cachebased translation model. We present the improvements we obtained in two contexts: in a theoretical setting, we achieved a drop in perplexity for...

متن کامل

Learning to Remember Translation History with a Continuous Cache

Existing neural machine translation (NMT) models generally translate sentences in isolation, missing the opportunity to take advantage of document-level information. In this work, we propose to augment NMT models with a very light-weight cache-like memory network, which stores recent hidden representations as translation history. The probability distribution over generated words is updated onli...

متن کامل

Cache-based Document-level Statistical Machine Translation

Statistical machine translation systems are usually trained on a large amount of bilingual sentence pairs and translate one sentence at a time, ignoring document-level information. In this paper, we propose a cache-based approach to document-level translation. Since caches mainly depend on relevant data to supervise subsequent decisions, it is critical to fill the caches with highly-relevant da...

متن کامل

Reduction in Cache Memory Power Consumption based on Replacement Quantity

Today power consumption is considered to be one of the important issues. Therefore, its reduction plays a considerable role in developing systems. Previous studies have shown that approximately 50% of total power consumption is used in cache memories. There is a direct relationship between power consumption and replacement quantity made in cache. The less the number of replacements is, the less...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2010