Browsing Department of International Language Studies and Computational Linguistics (ISV) by Author "Elming, Jakob"
Now showing items 1-2 of 2
-
Hardt, Daniel; Elming, Jakob (Frederiksberg, 2010)[More information][Less information]
Abstract: A method is presented for incremental retraining of an SMT system, in which a local phrase table is created and incrementally updated as a file is translated and post-edited. It is shown that translation data from within the same file has higher value than other domain-specific data. In two technical domains, within-file data increases BLEU score by several full points. Furthermore, a strong recency effect is documented; nearby data within the file has greater value than more distant data. It is also shown that the value of translation data is strongly correlated with a metric defined over new occurrences of ngrams. Finally, it is argued that the incremental re-training prototype could serve as the basis for a practical system which could be interactively updated in real time in a post-editing setting. Based on the results here, such an interactive system has the potential to dramatically improve translation quality. URI: http://hdl.handle.net/10398/8272 Files in this item: 1
Hardt_Elming.pdf (201.1Kb) -
Elming, Jakob (Frederiksberg, 2008)[More information][Less information]
Abstract: Reordering has been an important topic in statistical machine translation (SMT) as long as SMT has been around. State-of-the-art SMT systems such as Pharaoh (Koehn, 2004a) still employ a simplistic model of the reordering process to do non-local reordering. This model penalizes any reordering no matter the words. The reordering is only selected if it leads to a translation that looks like a much better sentence than the alternative. Recent developments have, however, seen improvements in translation quality following from syntax-based reordering. One such development is the pre-translation approach that adjusts the source sentence to resemble target language word order prior to translation. This is done based on rules that are either manually created or automatically learned from word aligned parallel corpora. We introduce a novel approach to syntactic reordering. This approach provides better exploitation of the information in the reordering rules and eliminates problematic biases of previous approaches. Although the approach is examined within a pre-translation reordering framework, it easily extends to other frameworks. Our approach significantly outperforms a state-of-the-art phrase-based SMT system and previous approaches to pretranslation reordering, including (Li et al., 2007; Zhang et al., 2007b; Crego & Mari˜ no, 2007). This is consistent both for a very close language pair, English-Danish, and a very distant language pair, English-Arabic. We also propose automatic reordering rule learning based on a rich set of linguistic information. As opposed to most previous approaches that extract a large set of rules, our approach produces a small set of predominantly general rules. These provide a good reflection of the main reordering issues of a given language pair. We examine the influence of several parameters that may have influence on the quality of the rules learned. Finally, we provide a new approach for improving automatic word alignment. This word alignment is used in the above task of automatically learning reordering rules. Our approach learns from hand aligned data how to combine several automatic word alignments to one superior word alignment. The automatic word alignments are created from the same data that has been preprocessed with different tokenization schemes. Thus utilizing the different strengths that different tokenization schemes exhibit in word alignment. We achieve a 38% error reduction for the automatic word alignment URI: http://hdl.handle.net/10398/7922 Files in this item: 1
jakob_elming.pdf (1.033Mb)
Now showing items 1-2 of 2