Articles

We propose an interactive-predictive neu- ral machine translation framework for eas- ier model personalization using reinforce- ment and imitation learning. During the interactive translation process, the user is asked for feedback on uncertain locations identified by the system. Responses are weak feedback in the form of “keep” and “delete” edits, …...

Although automatic classification of ma- chine translation errors still cannot provide the same detailed granularity as manual er- ror classification, it is an important task which enables estimation of translation er- rors and better understanding of the ana- lyzed MT system, in a short time and on a large scale. …...

This paper presents MAGMATic (Multi- domain Academic Gold Standard with Manual Annotation of Terminology), a novel Italian–English benchmark which al- lows MT evaluation focused on terminol- ogy translation. The data set comprises 2,056 parallel sentences extracted from in- stitutional academic texts, namely course unit and degree program descriptions. This text …...

This paper presents preliminary results of a study of Japanese native speakers working with the Microsoft Word application in two modalities: the released Japanese version and a machine translated (MT) version (the raw MT strings incorporated into the MS Word interface). To explore the effect of translation modality on task …...

Translation quality could degrade non- gracefully outside the desired domain for MT. Meanwhile, translation requests are often unknown and potentially out-of- domain in practice. This paper shows that having an ecosystem with a range of pre- trained domain-specific MT systems can reduce the effect: a translation task can be out …...

The combination of machines and humans for translation is effective, with many stud- ies showing productivity gains when hu- mans post-edit machine-translated output instead of translating from scratch. To take full advantage of this combination, we need a fine-grained understanding of how human translators work, and which post-editing styles are …...

Due to the scarcity of parallel training data for many language pairs, quasi-parallel or comparable training data provides an important alternative resource for train- ing machine translation systems for such language pairs. Since comparable cor- pora are not of as high quality as man- ually annotated parallel data, using them …...

In recent years, pretrained word embed- dings have proved useful for multimodal neural machine translation (NMT) mod- els to address the shortage of available datasets. However, the integration of pretrained word embeddings has not yet been explored extensively. Further, pre- trained word embeddings in high dimen- sional spaces have been …...

Neural end-to-end architectures have been recently proposed for spoken language translation (SLT), following the state-of- the-art results obtained in machine transla- tion (MT) and speech recognition (ASR). Motivated by this contiguity, we propose an SLT adaptation of Transformer (the state-of-the-art architecture in MT), which exploits the integration of ASR solutions …...

The goal of cross-lingual information re- trieval (CLIR) is to find relevant docu- ments written in languages different from that of the query. Robustness to transla- tion errors is one of the main challenges for CLIR, especially in low-resource settings where there is limited training data for building machine translation …...

This paper is devoted to developing a re- current neural network (RNN) solution for segmenting the unpunctuated transcripts generated by automatic speech recognition for simultaneous interpretation. RNNs are effective in capturing long-distance depen- dencies and straightforward for online de- coding. Thus, they are ideal for the task compared to the …...

AbstractThis paper contributes to the on-going discussion of how best to analyze and handle complex predicate formations, commenting in particular on the properties of Hindi N-V complex predicates as set out by Vaidya et al. (2019). I highlight features of existing LFG analyses and focus in particular on the modular …...

AbstractVaidya et al. (2019) discuss argument alternations in Hindi complex predicates, and propose an analysis within an LTAG framework, comparing this with an LFG analysis of complex predicates. In this paper I clarify the inadequacies in existing LFG analyses of complex predicates, and show how the LFG+glue approach proposed by …...

AbstractPrevious work on light verb constructions (e.g. chorii kar ‘theft do; steal’) in Hindi describes their syntactic formation via co-predication (Ahmed et al., 2012, Butt, 2014). This implies that both noun and light verb contribute their arguments, and these overlapping argument structures must be composed in the syntax. In this …...

AbstractThis paper compares a recent TAG-based analysis of complex predicates in Hindi/Urdu with its HPSG analog. It points out that TAG combines actual structure while HPSG (and Categorial Grammar and other valence-based frameworks) specify valence of lexical items and hence potential structure. This makes it possible to have light verbs …...

AbstractParallel sentences provide semantically similar information which can vary on a given dimension, such as language or register. Parallel sentences with register variation (like expert and non-expert documents) can be exploited for the automatic text simplification. The aim of automatic text simplification is to better access and understand a given …...

AbstractImages and text represent types of content which are used together for conveying user emotions in online social networks. These contents are usually associated with a sentiment category. In this paper, we investigate an approach for mapping images to text for three types of sentiment categories: positive, neutral and negative. …...

AbstractWe present an open-source, wide-coverage context-free grammar (CFG) for Icelandic, and an accompanying parsing system. The grammar has over 5,600 nonterminals, 4,600 terminals and 19,000 productions in fully expanded form, with feature agreement constraints for case, gender, number and person. The parsing system consists of an enhanced Earley-based parser and …...

AbstractDynamic topic models (DTMs) capture the evolution of topics and trends in time series data. Current DTMs are applicable only to monolingual datasets. In this paper we present the multilingual dynamic topic model (ML-DTM), a novel topic model that combines DTM with an existing multilingual topic modeling method to capture …...

AbstractShort-text classification is a challenging task, due to the sparsity and high dimensionality of the feature space. In this study, we aim to analyze and classify Turkish tweets based on their topics. Social media jargon and the agglutinative structure of the Turkish language makes this classification task even harder. As …...