Abstract | We achieve significant improvement over both Hiero and phrase-based baselines for Arabic-English, Chinese-English and German-English translation. |
Experiment Results | We will report the impact of integrating phrase-based features into Hiero systems for three language pairs: Arabic-English, Chinese-English and German-English. |
Experiment Results | 4.3 Chinese-English Results |
Experiment Results | The Chinese-English system was trained on FBIS corpora of 384K sentence pairs, the English corpus is lower case. |
Introduction | In our Chinese-English experiment, the Hiero system still outperforms the discontinuous phrase-based system. |
Introduction | (2008) added structure distortion features into their decoder and showed improvements in their Chinese-English experiment. |
Phrasal-Hiero Model | In the experiment section, we will discuss the impact of removing rules with nonaligned sub-phrases in our German-English and Chinese-English experiments. |
Abstract | We evaluate our optimizer on Chinese-English and Arabic-English translation tasks, each with small and large feature sets, and show that our learner is able to achieve significant improvements of 1.2-2 BLEU and 1.7-4.3 TER on average over state-of-the-art optimizers with the large feature set. |
Additional Experiments | In both Arabic-English feature sets, MIRA seems to take the second place, while RAMPION lags behind, unlike in Chinese-English (§4).6 |
Discussion | Spread analysis: For RM, the average spread of the projected data in the Chinese-English small feature set was 0.9i3.6 for all tuning iterations, and 0.7j:2.9 for the iteration with the highest decoder performance. |
Experiments | To evaluate the advantage of explicitly accounting for the spread of the data, we conducted several experiments on two Chinese-English translation test sets, using two different feature sets in each. |
Experiments | As can be seen from the results in Table 3, our RM method was the best performer in all Chinese-English tests according to all measures — up to 1.9 BLEU and 6.6 TER over MIRA — even though we only optimized for BLEU.5 Surprisingly, it seems that MIRA did not benefit as much from the sparse features as RM. |
Experiments | In preliminary experiments with a smaller trigram LM, our RM method consistently yielded the highest scores in all Chinese-English tests — up to 1.6 BLEU and 6.4 TER from MIRA, the second best performer. |
Introduction | Chinese-English translation experiments show that our algorithm, RM, significantly outperforms strong state-of-the-art optimizers, in both a basic feature setting and high-dimensional (sparse) feature space (§4). |
Abstract | Experiments on Chinese-English translation demonstrated the effectiveness of our approach on enhancing the quality of overall translation, name translation and word alignment over a high-quality MT baselinel. |
Baseline MT | As our baseline, we apply a high-performing Chinese-English MT system (Zheng, 2008; Zheng et al., 2009) based on hierarchical phrase-based translation framework (Chiang, 2005). |
Conclusions and Future Work | Experiments on Chinese-English translation demonstrated the effectiveness of our approach over a high-quality MT baseline in both overall translation and name translation, especially for formal genres. |
Experiments | We used a large Chinese-English MT training corpus from various sources and genres (including newswire, web text, broadcast news and broadcast conversations) for our experiments. |
Experiments | get side of Chinese-English and Egyptian Arabic-English parallel text, English monolingual discussion forums data Rl-R4 released in BOLT Phase 1 (LDC2012E04, LDC2012E16, LDC2012E21, LDC2012E54), and English Gigaword Fifth Edition (LDC2011T07). |
Experiments | We conducted the experiment on the Chinese-English Parallel Treebank (Li et a1., 2010) with ground-truth word alignment. |
Abstract | We have been able to extract over 1M Chinese-English parallel segments from Sina Weibo (the Chinese counterpart of Twitter) using only their public APIs. |
Experiments | For the news test, we created a new test set from a crawl of the Chinese-English documents on the Project Syndicate website2, which contains news commentary articles. |
Experiments | Second, we use the full 2012 NIST Chinese-English dataset (approximately 8M sentence pairs, including FBIS). |
Introduction | Section 5 describes the data we gathered from both Sina Weibo (Chinese-English) and Twitter ( Chinese-English and Arabic-English). |
Parallel Data Extraction | The target domains in this work are Twitter and Sina Weibo, and the main language pair is Chinese-English . |
Parallel Data Extraction | This means that for the Chinese-English language pair, we only keep tweets with more than 3 Mandarin characters and 3 latin words. |
Experiments | The first experiments are on the IWSLT data set for Chinese-English translation. |
Experiments | Table 3: Machine translation performance in BLE U % on the IWSLT 2005 Chinese-English test set. |
Experiments | To test whether our improvements carry over to larger datasets, we assess the performance of our model on the FBIS Chinese-English data set. |
Introduction | We demonstrate our model on Chinese-English and Arabic-English translation datasets. |
Abstract | As our approach combines the merits of phrase-based and string-to-dependency models, it achieves significant improvements over the two baselines on the NIST Chinese-English datasets. |
Introduction | We evaluate our method on the NIST Chinese-English translation datasets. |
Introduction | 1Empirically, we find that the average number of stacks for J words is about 1.5 X J on the Chinese-English data. |
Introduction | We evaluated our phrase-based string-to-dependency translation system on Chinese-English translation. |
Abstract | In our experiments, our model improved 2.9 BLEU points for J apanese-English and 2.6 BLEU points for Chinese-English translation compared to the lexical reordering models. |
Experiment | Japanese-English Chinese-English HIER 30.47 32.66 |
Introduction | Experiments confirmed the effectiveness of our method for J apanese-English and Chinese-English translation, using NTCIR-9 Patent Machine Translation Task data sets (Goto et al., 2011). |
Abstract | Large-scale experiments on Arabic-English and Chinese-English show that our method produces significant translation quality gains by exploiting sparse features. |
Experiments | We built Arabic-English and Chinese-English MT systems with Phrasal (Cer et al., 2010), a phrase-based system based on alignment templates (Och and Ney, 2004). |
Introduction | We conduct large-scale translation quality experiments on Arabic-English and Chinese-English . |
Experiments | The system is trained on 10 million parallel sentences that are available to the Phase 1 of the DARPA BOLT Chinese-English MT task. |
Training | For our Chinese-English experiments, we use a simple heuristic that equates as anchors, single-word chunks whose corresponding word class belongs to closed-word classes, bearing a close resemblance to (Setiawan et al., 2007). |
Two-Neighbor Orientation Model | Figure 1: An aligned Chinese-English sentence pair. |
Conclusion and Future Work | Chinese-English experimental results on four typical attributes showed that WikiCiKE significantly outperforms both the current translation based methods and the monolingual extraction methods. |
Experiments | In this section, we present our experiments to evaluate the effectiveness of WikiCiKE, where we focus on the Chinese-English case; in other words, the target language is Chinese and the source language is English. |
Introduction | Chinese-English experiments for four typical attributes demonstrate that WikiCiKE outperforms both the monolingual extraction method and current translation-based method. |