Abstract | Another line of research that is closely related to our work is phrase table refinement and pruning. |
Abstract | The parallel sentences were forced to be aligned at the phrase level using the phrase table and other features as in a decoding process. |
Abstract | To prevent overf1tting, the statistics of phrase pairs from a particular sentence was excluded from the phrase table when aligning that sentence. |
Beyond lexical CLTE | In order to enrich the feature space beyond pure lexical match through phrase table entries, our model |
Beyond lexical CLTE | builds on two additional feature sets, derived from i) semantic phrase tables , and ii) dependency relations. |
Beyond lexical CLTE | Semantic Phrase Table (SPT) matching represents a novel way to leverage the integration of semantics and MT—derived techniques. |
CLTE-based content synchronization | CLTE has been previously modeled as a phrase matching problem that exploits dictionaries and phrase tables extracted from bilingual parallel corpora to determine the number of word sequences in H that can be mapped to word sequences in T. In this way a semantic judgement about entailment is made exclusively on the basis of lexical evidence. |
Experiments and results | To build the English-German phrase tables we combined the Europarl, News Commentary and “de-news”3 parallel corpora. |
Introduction | The CLTE methods proposed so far adopt either a “pivoting approach” based on the translation of the two input texts into the same language (Mehdad et al., 2010), or an “integrated solution” that exploits bilingual phrase tables to capture lexical relations and contextual information (Mehdad et al., 2011). |
Experiments | We validated our simple implementation using a phrase table of 38,488,777 lines created with the Moses toolkit3(Koehn et al., 2007) phrase-based SMT system, corresponding to 15,764,069 entries |
Experiments | Figure 4 displays the time required to complete retrieval for subsets of increasing size of the 2,000 sentence test set, and for phrase tables uniformly sampled at 25%, 50%, 75% and 100%. |
Experiments | 217,019 distinct digests are generated for all possible phrase of length up to 6 from the full test set, resulting in the retrieval of 47,072 entries (596,560 lines) from the full phrase table . |
Implementation | This mirrors the standard practice of filtering the phrase table for a given source file to translate before starting the actual decoding. |
Introduction | In this method, the owner of the TM generates a Phrase Table (PT) from it, and makes it accessible to the user following a special procedure. |
Introduction | 0 The user acquires all and only the phrase table entries required to perform the decoding of a specific file, thus avoiding complete transfer of the TM to the user; |
Introduction | While the exposition will focus on phrase tables , there is nothing in the method precluding its use with other resources, provided that they can be represented as lookup tables, a very mild constraint. |
Related work | private access to a phrase table or other resources for the purpose of performing statistical machine translation. |
Baselines | where m ranges over IN and OUT, pm(é| f) is an estimate from a component phrase table , and each Am is a weight in the top-level log-linear model, set so as to maximize dev-set BLEU using minimum error rate training (Och, 2003). |
Baselines | Whenever a phrase pair does not appear in a component phrase table , we set the corresponding pm(é| f) to a small epsilon value. |
Baselines | Whenever a phrase pair does not appear in a component phrase table , we set the corresponding pm(é|f) to 0; pairs in 15(6, that do not appear in at least one component table are discarded. |
Ensemble Decoding | The cells of the CKY chart are populated with appropriate rules from all the phrase tables of different components. |
Experiments & Results 4.1 Experimental Setup | The corpus was word-aligned using both HMM and IBM2 models, and the phrase table was the union of phrases extracted from these separate alignments, with a length limit of 7. |
Related Work 5.1 Domain Adaptation | In intersection, for each span only the hypotheses would be used that are present in all phrase tables . |
Related Work 5.1 Domain Adaptation | Union, on the other hand, uses hypotheses from all the phrase tables . |
Abstract | The model does not require bitext or phrase table annotations and can be easily implemented as a feature in many phrase-based decoders. |
Conclusion and Outlook | Our class-based agreement model improves translation quality by promoting local agreement, but with a minimal increase in decoding time and no additional storage requirements for the phrase table . |
Discussion of Translation Results | Phrase Table Coverage In a standard phrase-based system, effective translation into a highly inflected target language requires that the phrase table contain the inflected word forms necessary to construct an output with correct agreement. |
Discussion of Translation Results | During development, we observed that the phrase table of our large-scale English-Arabic system did often contain the inflected forms that we desired the system to select. |
Introduction | Unlike previous models for scoring syntactic relations, our model does not require bitext annotations, phrase table features, or decoder modifications. |
Experimental Evaluation | We use identical phrase tables and scaling factors for Moses and our decoder. |
Experimental Evaluation | The phrase table is pruned to a maximum of 400 target candidates per source phrase before decoding. |
Experimental Evaluation | The phrase table and LM are loaded into memory before translating and loading time is eliminated for speed measurements. |