Matches in SemOpenAlex for { <https://semopenalex.org/work/W2781780309> ?p ?o ?g. }
- W2781780309 abstract "We investigate methods to adapt translation models in SMT to a specific target domain. We discuss two major problems, unknown words because of data sparseness in the (in-domain) training data, and ambiguities arising from out-of-domain parallel texts with different domain-specific translations. We propose novel solutions to both problems.The main contributions of this thesis are as follows:* We present a novel translation model architecture that supports domain adaptation at decoding time from a vector of component models. The combination is implemented through instance weighting, and all statistics necessary for the computation of translation probabilities are stored in the models.* We present an architecture to combine multiple MT systems, using techniques and ideas from domain adaptation. The hypotheses by external MT systems are treated as out-of-domain knowledge, and combined with in-domain data through instance weighting.* We introduce a sentence alignment algorithm that is able to robustly align even noisy parallel texts. We found that higher-quality sentence alignment of the in-domain parallel text has a significant effect on translation quality in our target domain.* We propose new translation model features that express how flexible, or general, translation units are, in order to prevent translations that only occur in the context of multiword expressions from being overgeneralised." @default.
- W2781780309 created "2018-01-12" @default.
- W2781780309 creator A5005771535 @default.
- W2781780309 date "2013-01-01" @default.
- W2781780309 modified "2023-09-25" @default.
- W2781780309 title "Domain adaptation for translation models in statistical machine translation" @default.
- W2781780309 cites W107230253 @default.
- W2781780309 cites W1205016396 @default.
- W2781780309 cites W14574270 @default.
- W2781780309 cites W145987047 @default.
- W2781780309 cites W1480519300 @default.
- W2781780309 cites W1489525520 @default.
- W2781780309 cites W1491049622 @default.
- W2781780309 cites W1494910745 @default.
- W2781780309 cites W1498763386 @default.
- W2781780309 cites W1517947178 @default.
- W2781780309 cites W1533246198 @default.
- W2781780309 cites W1574901103 @default.
- W2781780309 cites W1596675947 @default.
- W2781780309 cites W1625582487 @default.
- W2781780309 cites W1631260214 @default.
- W2781780309 cites W171331851 @default.
- W2781780309 cites W1716250762 @default.
- W2781780309 cites W1724972948 @default.
- W2781780309 cites W1819903106 @default.
- W2781780309 cites W1848260265 @default.
- W2781780309 cites W1905522558 @default.
- W2781780309 cites W1906341845 @default.
- W2781780309 cites W1916559533 @default.
- W2781780309 cites W1934041838 @default.
- W2781780309 cites W1940278502 @default.
- W2781780309 cites W1970689298 @default.
- W2781780309 cites W1981116971 @default.
- W2781780309 cites W1989658336 @default.
- W2781780309 cites W1994581546 @default.
- W2781780309 cites W1995875735 @default.
- W2781780309 cites W2000359198 @default.
- W2781780309 cites W2006969979 @default.
- W2781780309 cites W2010856309 @default.
- W2781780309 cites W2041232209 @default.
- W2781780309 cites W2054549124 @default.
- W2781780309 cites W2079145130 @default.
- W2781780309 cites W2080373976 @default.
- W2781780309 cites W2087735403 @default.
- W2781780309 cites W2100281225 @default.
- W2781780309 cites W2101105183 @default.
- W2781780309 cites W2109664771 @default.
- W2781780309 cites W2115081467 @default.
- W2781780309 cites W2115410424 @default.
- W2781780309 cites W2116652448 @default.
- W2781780309 cites W2117278770 @default.
- W2781780309 cites W2117652747 @default.
- W2781780309 cites W2122270629 @default.
- W2781780309 cites W2123301721 @default.
- W2781780309 cites W2124807415 @default.
- W2781780309 cites W2132001515 @default.
- W2781780309 cites W2133622676 @default.
- W2781780309 cites W2134800885 @default.
- W2781780309 cites W2136925175 @default.
- W2781780309 cites W2137181778 @default.
- W2781780309 cites W2137698233 @default.
- W2781780309 cites W2142112143 @default.
- W2781780309 cites W2144600658 @default.
- W2781780309 cites W2144642230 @default.
- W2781780309 cites W2144879357 @default.
- W2781780309 cites W2146574666 @default.
- W2781780309 cites W2148334774 @default.
- W2781780309 cites W2152263452 @default.
- W2781780309 cites W2152382718 @default.
- W2781780309 cites W2154124206 @default.
- W2781780309 cites W2155501171 @default.
- W2781780309 cites W2156985047 @default.
- W2781780309 cites W2158195707 @default.
- W2781780309 cites W2161694750 @default.
- W2781780309 cites W2169755259 @default.
- W2781780309 cites W2170204377 @default.
- W2781780309 cites W2171421863 @default.
- W2781780309 cites W2180952760 @default.
- W2781780309 cites W2182115895 @default.
- W2781780309 cites W22168010 @default.
- W2781780309 cites W2250238837 @default.
- W2781780309 cites W2250695194 @default.
- W2781780309 cites W2251098065 @default.
- W2781780309 cites W2251202280 @default.
- W2781780309 cites W2251222643 @default.
- W2781780309 cites W2252110609 @default.
- W2781780309 cites W2280403519 @default.
- W2781780309 cites W23077562 @default.
- W2781780309 cites W2401082558 @default.
- W2781780309 cites W2408503330 @default.
- W2781780309 cites W2408655637 @default.
- W2781780309 cites W2496235729 @default.
- W2781780309 cites W2503849903 @default.
- W2781780309 cites W2588710172 @default.
- W2781780309 cites W2614322402 @default.
- W2781780309 cites W2758884106 @default.
- W2781780309 cites W2787646045 @default.
- W2781780309 cites W2796578018 @default.
- W2781780309 cites W2886079201 @default.
- W2781780309 cites W2892587090 @default.