Báo cáo khoa học: "Rule Filtering by Pattern for Efficient Hierarchical Translation" pdf

... 380–388, Athens, Greece, 30 March – 3 April 2009. c 2009 Association for Computational Linguistics Rule Filtering by Pattern for Efficient Hierarchical Translation Gonzalo Iglesias ⋆ Adri ` a de Gispert ‡ ⋆ University ... 205801 Table 3: Hierarchical rule patterns classed by number of non-terminals, N nt , number of ele- ments N e , source and target patterns, and types in t...

Ngày tải lên: 24/03/2014, 03:20

Ngày tải lên: 20/02/2014, 04:20

... 16.5 Table 4: CAT results for the “XRCE” task for 1- best hypothesis and 5-best hypothesis. alternatives before choosing. It is still to be shown if this extra time is compensated by the fewer key strokes ... ad- equate framework for CAT since the MT mod- els used can be learnt automatically from a train- ing bilingual corpus and the search procedures developed for SMT can be adapte...

Ngày tải lên: 20/02/2014, 12:20

... phrase-based SMT to a hierarchical phrase-based SMT. We used a max-chart-span 15 for the hierarchical phrase-based SMT. We used distortion limits of 12 or 20 for PBMT and a max-chart-span 15 for HPBMT. The ... SMT (PO-HPBMT). We used Moses for these 5 systems. For PO-PBMT, a distortion limit 0 was used for the Japanese-to-HFE translation and a distortion limit 20 was used for...

Ngày tải lên: 30/03/2014, 17:20

... fveq(str) For more 0.13 7 200 For more information 0.33 3 168 For more information , 0.21 4 46 For more information , see 1.03 8 25 For more information , refer to 1.17 6 15 For more information ... " ;For more information on" and " ;For more information, refer to" act more cohesively than the grammatical string " ;For more information" in the corp...

Ngày tải lên: 31/03/2014, 21:20

... relevant to the target concerned. Therefore, we argue that existing information representation i.e. bag-of-word, cannot satisfy the information needs for opinion retrieval. In this paper, ... and Ounis, 2006). Therefore, in this paper we regard the information needs for opinion retrieval as relevant opinion. 2.2 Motivation of Our Approach In traditional information retrieval (IR...

Ngày tải lên: 20/02/2014, 04:20

... were resolved by looking at the word context, and by preferring the alternatives per- ceived as most frequent. 3 No morphological analy- sis was performed, so that different inflected forms of the ... remains the same for all lan- guage pairs. We will use Levenshtein distance as a baseline for our experiments. 3.2 Stochastic Transducers Trained with EM The algorithm presented by Rist...

Ngày tải lên: 20/02/2014, 12:20

... multiple arguments for assigning the crucial syllable boundary. In de-prive vs. dep-rivalion, for instance, the difference is revealed by the vowel argument above 5 and by the aspiration ... before the labial stop /p/, the cor9nal nasal/n/ before the coronal stop/t/, and the velar nasal/7// before the velar stop/k/. This constraint, like subject-verb agreement. poses a problem...

Ngày tải lên: 21/02/2014, 20:20

... transducer using the forward- backward algorithm on the current training set. 3. Calculate the forward score for all word pairs under consideration. 4. If the forward score for a pair of words ... rule-based classifier for word sense disam- biguation by starting with a small set of seed ex- amples for which the sense is known. The trained classifier is then used to label examples for...

Ngày tải lên: 08/03/2014, 02:21

... been heavily investigated in the formal language com- munity (G ´ ecseg and Steinby, 1984; G ´ ecseg and Steinby, 1997), but as argued by Shieber (2004) they are still too weak for syntax-based machine translation. ... about trees, tree languages, and tree transformations. For a more in-depth discussion we refer to G ´ ecseg and Steinby (1984) and G ´ ecseg and Steinby (1997). A finite s...

Ngày tải lên: 17/03/2014, 00:20