Báo cáo khoa học: "Reducing SMT Rule Table with Monolingual Key Phrase" potx

... pages 121–124, Suntec, Singapore, 4 August 2009. c 2009 ACL and AFNLP Reducing SMT Rule Table with Monolingual Key Phrase Zhongjun He † Yao Meng † Yajuan L ‡ Hao Yu † Qun Liu ‡ † Fujitsu R&D ... for the rule table reduction on Chinese-English test sets. The rule table is re- duced to the same size (22% of original table) using the two metrics, separately. However, a...

Ngày tải lên: 31/03/2014, 00:20

... translation rules used by the best derivation d*. The forced decoding based TSA generation on the example sentence pair in Figure 1 can be shown in Table 2. 3 Better Rule Extraction with TSAs ... [了]<=>[have] Table 2. Forced decoding based TSA generation on the example sentence pair in Fig. 1. where r i indicates a phrase rule used to form d*. ⊕is a composition ope...

Ngày tải lên: 23/03/2014, 14:20

... Machine Translation (SMT) output with Transla- tion Memory (TM) systems. The frame- work recommends SMT outputs to a TM user when it predicts that SMT outputs are more suitable for post-editing ... = { +1 if T ER (SMT) + b < T ER(TM) −1 if T ER (SMT) + b  T ER(TM) (8) We experiment with b in [0, 0.25] using MT sys- tem features and TM features. Results are reported in Table 2....

Ngày tải lên: 23/03/2014, 16:20

... in Fig- ure 1(c), Rule (1) and Rule (2) are two different SCFG rules extracted from Figure 1(a) and Figure 1(b) respectively, where their source-side rules are the same. As Rule (1) cannot be ... target-side rule provides one of the candi- date translations of the source-side rule. Improper rule selections may result in poor translations. There is some related work about the hierar...

Ngày tải lên: 23/03/2014, 16:20

... propose to use monolingual collocations to improve SMT. We first identify potentially collocated words and estimate collo- cation probabilities from monolingual corpora using a Monolingual Word ... two aspects, namely improving word alignment for various kinds of SMT sys- tems and improving phrase table for phrase-based SMT. The experimental re- sults show that our method im...

Ngày tải lên: 20/02/2014, 04:20

... then associate each event mention with only one cluster from each set. The first set uses the transitive closure of the WordNet SYNONYMOUS relation to form clusters with all the words from WordNet ... associated with an event z, φ a notation for all model parameters, and X a notation for all ran- dom variables that represent observable features. 2 Given a document collection annotated w...

Ngày tải lên: 07/03/2014, 22:20

... performs well with a wide range of parameter values. 7 5.1 Method Comparison We first compare the proposed joint model (Joint) with the baselines in Table 2. As seen from the table, the proposed ... training data. (Examples with conflicting labels within the pair are not included.) 5 Results and Analysis In our experiments, the methods are tested in the two data settings wit...

Ngày tải lên: 17/03/2014, 00:20

... and feature set. Table 2 shows the results of Chunking and NER obtained with this parameter initialization setting. When we compare Tables 1 and 2, we find that the initialization with the MAP parameter ... MCE-F with the MAP parameter initialization achieved an F-score of 94.03, which surpasses the above result without manual parameter tuning. With NER, we cannot make a direct compa...

Ngày tải lên: 17/03/2014, 04:20

... (NANC). Since there were very few NPs with more than 5 modifiers, we kept those with 2-5 modifiers and with tags NN or NNS for the head noun. We also kept NPs with only 1 modifier to be used for generating ... Count table where bigrams are not actually seen in the training data but their counts can be inferred from other entries in the table, and they use a clustering method to group...

Ngày tải lên: 30/03/2014, 21:20

... codes with respect to X, i.e., those with higher salience with respect to X, dis(X, s) will be smaller due to the fact that the contribution of a semantic code to the distance increases with ... irrelevant with the 22,028 univocal words. Tab. 2 and 3 list the distribution of the entries with respect to the number of their sense tags, and the distribution of the senses...

Ngày tải lên: 31/03/2014, 04:20