Related papers: Automatic Discovery of Non-Compositional Compounds…
Neural machine translation (NMT) has arguably achieved human level parity when trained and evaluated at the sentence-level. Document-level neural machine translation has received less attention and lags behind its sentence-level…
Despite the recent developments in the field of cross-modal retrieval, there has been less research focusing on low-resource languages due to the lack of manually annotated datasets. In this paper, we propose a noise-robust cross-lingual…
In Machine Translation, considering the document as a whole can help to resolve ambiguities and inconsistencies. In this paper, we propose a simple yet promising approach to add contextual information in Neural Machine Translation. We…
In this paper, we describe methods for handling multilingual non-compositional constructions in the framework of GF. We specifically look at methods to detect and extract non-compositional phrases from parallel texts and propose methods to…
We show that the state of the art Transformer Machine Translation (MT) model is not biased towards monotonic reordering (unlike previous recurrent neural network models), but that nevertheless, long-distance dependencies remain a challenge…
Phrase-based statistical machine translation (SMT) systems have previously been used for the task of grammatical error correction (GEC) to achieve state-of-the-art accuracy. The superiority of SMT systems comes from their ability to learn…
Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition,…
The most common tools for word-alignment rely on a large amount of parallel sentences, which are then usually processed according to one of the IBM model algorithms. The training data is, however, the same as for machine translation (MT)…
Set constraints provide a highly general way to formulate program analyses. However, solving arbitrary boolean combinations of set constraints is NEXPTIME-hard. Moreover, while theoretical algorithms to solve arbitrary set constraints…
Language segmentation consists in finding the boundaries where one language ends and another language begins in a text written in more than one language. This is important for all natural language processing tasks. The problem can be solved…
We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of…
Dropped Pronouns (DP) in which pronouns are frequently dropped in the source language but should be retained in the target language are challenge in machine translation. In response to this problem, we propose a semi-supervised approach to…
The Transformer model has revolutionized Natural Language Processing tasks such as Neural Machine Translation, and many efforts have been made to study the Transformer architecture, which increased its efficiency and accuracy. One potential…
Low-resource languages pose a challenge for machine translation with large language models (LLMs), which require large amounts of training data. One potential way to circumvent this data dependence is to rely on LLMs' ability to use…
Neural Machine Translation (MT) has radically changed the way systems are developed. A major difference with the previous generation (Phrase-Based MT) is the way monolingual target data, which often abounds, is used in these two paradigms.…
Despite the known limitations, most machine translation systems today still operate on the sentence-level. One reason for this is, that most parallel training data is only sentence-level aligned, without document-level meta information…
Parallel data are an important part of a reliable Statistical Machine Translation (SMT) system. The more of these data are available, the better the quality of the SMT system. However, for some language pairs such as Persian-English,…
With little to no parallel data available for programming languages, unsupervised methods are well-suited to source code translation. However, the majority of unsupervised machine translation approaches rely on back-translation, a method…
Translation models based on hierarchical phrase-based statistical machine translation (HSMT) have shown better performances than the non-hierarchical phrase-based counterparts for some language pairs. The standard approach to HSMT learns…
Building conversational speech recognition systems for new languages is constrained by the availability of utterances that capture user-device interactions. Data collection is both expensive and limited by the speed of manual transcription.…