Articles

AbstractThe typical training of a hierarchical phrase-based machine translation involves a pipeline of multiple steps where mistakes in early steps of the pipeline are propagated without any scope for rectifying them. Additionally the alignments are trained independent of and without being informed of the end goal and hence are not …...

AbstractLeft-to-right (LR) decoding Watanabe et al. (2006) is a promising decoding algorithm for hierarchical phrase-based translation (Hiero) that visits input spans in arbitrary order producing the output translation in left to right order. This leads to far fewer language model calls. But the constrained SCFG grammar used in LR-Hiero (GNF) …...

AbstractThe training data for statistical machine translation are gathered from various sources representing a mixture of domains. In this work, we argue that when translating dialects representing varieties of the same language, a manually assigned data source is not a reliable indicator of the dialect. We resort to automatic dialect …...

AbstractIn this paper, we address the problem of extracting and integrating bilingual terminology into a Statistical Machine Translation (SMT) system for a Computer Aided Translation (CAT) tool scenario. We develop a framework that, taking as input a small amount of parallel in-domain data, gathers domain-specific bilingual terms and injects them …...

AbstractIn spoken language translation, it is crucial that an automatic speech recognition (ASR) system produces outputs that can be adequately translated by a statistical machine translation (SMT) system. While word error rate (WER) is the standard metric of ASR quality, the assumption that each ASR error type is weighted equally …...

Aspect-based opinion mining has attracted lots of attention today. In this paper, we address the problem of product aspect rat- ing prediction, where we would like to ex- tract the product aspects, and predict as- pect ratings simultaneously. Topic mod- els have been widely adapted to jointly model aspects and …...

ive Summarization of Product Reviews Using Discourse Structure Shima Gerani‡† ∗ Yashar Mehdad‡ ∗ Giuseppe Carenini‡ Raymond T. Ng‡ Bita Nejat‡ †University of Lugano ‡University of British Columbia Switzerland Vancouver, BC, Canada {gerani,mehdad,carenini,rng,nejatb}@cs.ubc.ca Abstract We propose a novel abstractive summa- rization system for product reviews by tak- ing advantage of …...

This paper presents how a novel evalua- tion framework was used to collect trans- lation ratings thanks to users of an on- line German-speaking support community in the IT domain. Using an innovative data collection approach and mechanism, this paper shows that segment-level ratings can be collected in an effective …...

This paper describes the Kanjingo post- editing application for smartphones. The application was developed using an agile methodology at the Centre for Global Intelligent Content (CNGL) at DCU and a first stage of user testing was conducted using content from Translators Without Borders.1 Initial feedback on this app was quite …...

Translation between varieties of the same language is a widespread reality in the lo- calisation industry. However, monolin- gual statistical machine translation (SMT) is still a solution that has not yet been ade- quately explored; to the best of our knowl- edge, previous work in this area has never directly …...

A method is presented to assist users with no background in linguistics in adding the unknown words in a text to monolingual dictionaries such as those used in rule- based machine translation systems. Adding a word to these dictionaries requires identi- fying its stem and the inflection paradigm to be …...

This paper evaluates the impact of ma- chine translation on the software localiza- tion process and the daily work of profes- sional translators when SMT is applied to low-resourced languages with rich mor- phology. Translation from English into six low-resourced languages (Czech, Es- tonian, Hungarian, Latvian, Lithuanian and Polish) from …...

The exchange between Translation Studies (TS) and Machine Translation (MT) has been relatively rare. However, given recent developments in both fields like increased importance of post-editing and reintegra- tion of linguistic and translational knowl- edge into hybrid systems, it seems desir- able to intensify the exchange. This paper aims to …...

Despite the growing interest in and use of machine translation post-edited out- puts, there is little research work explor- ing different types of post-editing opera- tions, i.e. types of translation errors cor- rected by post-editing. This work in- vestigates five types of post-edit oper- ations and their relation with cognitive …...

It is often assumed that raw MT output requires post-editing if it is to be used for more than gisting purposes. However, we know little about how end users engage with raw machine translated text or post- edited text, or how usable this text is, in particular if users have …...

When machine translation researchers par- ticipate in evaluation tasks, they typically design their primary submissions using ideas that are not genre-specific. In fact, their systems look much the same from one evaluation campaign to another. In this pa- per, we analyze two popular genres: spo- ken language and written news, …...

We present an extrinsic evaluation of crawlers of parallel corpora from multi- lingual web sites in machine translation (MT). Our case study is on Croatian to English translation in the tourism domain. Given two crawlers, we build phrase-based statistical MT systems on the datasets pro- duced by each crawler using …...

This work presents the new flexible Mul- tidimensional Quality Metrics (MQM) framework and uses it to analyze the per- formance of state-of-the-art machine trans- lation systems, focusing on “nearly accept- able” translated sentences. A selection of WMT news data and “customer” data provided by language service providers (LSPs) in four …...

We present a method to generate feature- rich multilingual parallel datasets for ma- chine translation systems, including e.g. type of widget, user’s locale, or geoloca- tion. To support this argument, we have developed a bookmarklet that instruments arbitrary websites so that casual end users can modify their texts on demand. …...

We present a formal account of the mean- ing of vague scalar adjectives such as ‘tall’ formulated in Type Theory with Records. Our approach makes precise how percep- tual information can be integrated into the meaning representation of these pred- icates; how an agent evaluates whether an entity counts as …...