The RWTH Aachen System for NTCIR-10 PatentMT
نویسندگان
چکیده
This paper describes the statistical machine translation (SMT) systems developed by RWTH Aachen University for the Patent Translation task of the 10th NTCIR Workshop. Both phrase-based and hierarchical SMT systems were trained for the Japanese-English and Chinese-English tasks. Experiments were conducted to compare standard and inverse direction decoding, the performance of several additional models and the addition of monolingual training data. Moreover, for the Chinese-English subtask we applied a system combination technique to create a consensus hypothesis from several different systems.
منابع مشابه
The System Combination RWTH Aachen: SYSTRAN for the NTCIR-10 PatentMT Evaluation
This paper describes the joint submission by RWTH Aachen University and SYSTRAN in the Chinese-English Patent Machine Translation Task at the 10th NTCIR Workshop. We specify the statistical systems developed by RWTH Aachen University and the hybrid machine translation systems developed by SYSTRAN. We apply RWTH Aachen’s combination techniques to create consensus hypotheses from very different s...
متن کاملThe RWTH Aachen System for NTCIR-9 PatentMT
This paper describes the statistical machine translation (SMT) systems developed by RWTH Aachen University for the Patent Translation task of the 9th NTCIR Workshop. Both phrase-based and hierarchical SMT systems were trained for the constrained JapaneseEnglish and Chinese-English tasks. Experiments were conducted to compare different training data sets, training methods and optimization criter...
متن کاملt-Pancyclic Arcs in Tournaments
Let $T$ be a non-trivial tournament. An arc is emph{$t$-pancyclic} in $T$, if it is contained in a cycle of length $ell$ for every $tleq ell leq |V(T)|$. Let $p^t(T)$ denote the number of $t$-pancyclic arcs in $T$ and $h^t(T)$ the maximum number of $t$-pancyclic arcs contained in the same Hamiltonian cycle of $T$. Moon ({em J. Combin. Inform. System Sci.}, {bf 19} (1994), 207-214) showed that $...
متن کاملThe NiuTrans Machine Translation System for NTCIR-9 PatentMT
This paper describes the NiuTrans system developed by the Natural Language Processing Lab at Northeastern University for the NTCIR-9 Patent Machine Translation task (NTCIR-9 PatentMT). We present our submissions to the two tracks of NTCIR-9 PatentMT, and show several improvements to our phrase-based Statistical MT engine, including: a hybrid reordering model, large-scale language modeling, and ...
متن کاملA Six-step Approach to Gain Higher Quality Results From Organotypic Hippocampal Brain Slices in a Traumatic Brain Injury Model
Background: Organotypic Hippocampal Brain Slices (OHBS) provide a better alternative to in vivo models to scrutinize Traumatic Brain Injury (TBI). We followed a well-established TBI protocol but noticed that several factors might influence the results in such a set-up. Here, we describe a structured approach to generate more comparable results and discuss why specific eligibility criteria shoul...
متن کامل