Articles

This paper describes T ¨UB˙ITAK-B˙ILGEM statistical machine translation (SMT) sys- tems submitted to the Eighth Work- shop on Statistical Machine Transla- tion (WMT) shared translation task for German-English language pair in both di- rections. We implement phrase-based SMT systems with standard parameters. We present the results of using a big …...

We describe the Stanford University NLP Group submission to the 2013 Workshop on Statistical Machine Translation Shared Task. We demonstrate the effectiveness of a new adaptive, online tuning algorithm that scales to large feature and tuning sets. For both English-French and English-German, the algorithm produces feature-rich mod- els that improve …...

This paper describes the phrase-based SMT systems developed for our partici- pation in the WMT13 Shared Translation Task. Translations for English↔German and English↔French were generated us- ing a phrase-based translation system which is extended by additional models such as bilingual, fine-grained part-of- speech (POS) and automatic cluster lan- guage models …...

This paper describes the English-Russian and Russian-English statistical machine translation (SMT) systems developed at Yandex School of Data Analysis for the shared translation task of the ACL 2013 Eighth Workshop on Statistical Machine Translation. We adopted phrase-based SMT approach and evaluated a number of different techniques, including data fil- tering, …...

This paper describes our WMT submis- sions CU-BOJAR and CU-DEPFIX, the lat- ter dubbed “CHIMERA” because it com- bines on three diverse approaches: Tec- toMT, a system with transfer at the deep syntactic level of representation, factored phrase-based translation using Moses, and finally automatic rule-based correction of frequent grammatical and …...

We describe our experiments with phrase-based machine translation for the WMT 2013 Shared Task. We trained one system for 18 translation directions between English or Czech on one side and English, Czech, Ger- man, Spanish, French or Russian on the other side. We describe a set of re- sults with …...

We describe the CMU systems submit- ted to the 2013 WMT shared task in ma- chine translation. We participated in three language pairs, French–English, Russian– English, and English–Russian. Our particular innovations include: a label- coarsening scheme for syntactic tree-to- tree translation and the use of specialized modules to create “synthetic …...

We use feature decay algorithms (FDA) for fast deployment of accurate statistical machine translation systems taking only about half a day for each translation direc- tion. We develop parallel FDA for solving computational scalability problems caused by the abundance of training data for SMT models and LM models and still …...

This paper describes LIMSI’s submis- sions to the shared WMT’13 translation task. We report results for French-English, German-English and Spanish-English in both directions. Our submissions use n-code, an open source system based on bilingual n-grams, and continuous space models in a post-processing step. The main novelties of this year’s participation …...

There has been a recent surge of interest in semantic machine translation, which stan- dard automatic metrics struggle to evalu- ate. A family of measures called MEANT has been proposed which uses semantic role labels (SRL) to overcome this prob- lem. The human variant, HMEANT, has largely been evaluated using …...

This paper presents the results of the WMT13 Metrics Shared Task. We asked participants of this task to score the outputs of the MT systems involved in WMT13 Shared Translation Task. We collected scores of 16 metrics from 8 re- search groups. In addition to that we com- puted scores …...

We present the results of the WMT13 shared tasks, which included a translation task, a task for run-time estimation of ma- chine translation quality, and an unoffi- cial metrics task. This year, 143 machine translation systems were submitted to the ten translation tasks from 23 institutions. An additional 6 anonymized …...

The 2013 ALTA Shared Task was utilised as a class project for a subject taught at The Uni- versity of Melbourne in the second semester of 2013. This paper reviews the experience of us- ing an on-line, Kaggle in Class-based shared task for class work. Adoption of the shared task …...

This paper describes the winning entry to the ALTA Shared Task 2013. The theme of the shared task was recovery of cas- ing and punctuation information from de- graded English text. We tackle the task as a sequential labeling problem, jointly learning the casing and punctuation labels. We implement our …...

This study investigates idiosyncrasy manifest- ed in language use in spoken Japanese. For this purpose, we use speaker classification techniques as analytical tools. More precisely, focusing on Japanese case particles and fillers, of which the linguistic functions differ signifi- cantly, we aim to investigate 1) the extent of speaker idiosyncrasy …...

The 2013 ALTA shared task was the fourth in the ALTA series of shared tasks, where all participants attempt to solve the same problem using the same data. This year’s shared task was based on the problem of restoring casing and punctuation. As with last year, we used Kaggle in …...

Climate type is one of the potentially most relevant pieces of metadata for identify- ing studies in evidence-based environmen- tal management. In this paper, we pro- pose a method for automatically predict- ing the climate type in environmental sci- ence literature using NLP techniques, rel- ative to a pre-existing set …...

We offer a supervised machine learn- ing approach for recognizing erroneous words in the output of a speech recognizer. We have investigated several sets of fea- tures combined with two word configura- tions, and compared the performance of two classifiers: Decision Trees and Naïve Bayes. Evaluation was performed on a …...

Since Ramus et al. (1999) a number of statisti- cal metrics have been routinely employed by researchers (Ramus 2003, Grabe & Low 2002 etc.) in an effort to rhythmically classify lan- guages. However, recent studies by Arvaniti (2009), Tilsen & Arvaniti (2013), Arvaniti & Rodriquez (2013) etc., have challenged both …...

The improvements to ad-hoc IR sys- tems over the last decades have been re- cently criticized as illusionary and based on incorrect baseline comparisons. In this paper several improvements to the LM approach to IR are combined and evaluated: Pitman-Yor Process smooth- ing, TF-IDF feature weighting and model- based feedback. …...