Сөйлем Жұптары
Related Papers
Augmenting a statistical translation system with a translation memory
. In this paper, we present a translation memory (TM) based system to augment a statistical translation (SMT) system. It is used for translating sentences which have close matches in …...
Improved Statistical Machine Translation Using Paraphrases
Parallel corpora are crucial for training SMT systems. However, for many lan- guage pairs they are available only in very limited quantities. For these lan- guage pairs a huge portion …...
MISTRAL: a lattice translation system for IWSLT 2007
AbstractThis paper describes MISTRAL, the lattice translation system that we developed for the Italian-English track of the International Workshop on Spoken Language Translation 2007. MISTRAL is a discriminative phrase-based system …...
Building A Case-based Semantic English-Chinese Parallel Treebank
AbstractWe construct a case-based English-to-Chinese semantic constituent parallel Treebank for a Statistical Machine Translation (SMT) task by labelling each node of the Deep Syntactic Tree (DST) with our refined semantic …...
Modelling Sentence Pairs with Tree-structured Attentive Encoder
AbstractWe describe an attentive encoder that combines tree-structured recursive neural networks and sequential recurrent neural networks for modelling sentence pairs. Since existing attentive models exert attention on the sequential structure, …...
Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach
AbstractIn the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce. Many DA approaches aim …...
Constructing A Dataset of Support and Attack Relations in Legal Arguments in Court Judgements using Linguistic Rules
AbstractArgumentation mining is a growing area of research and has several interesting practical applications of mining legal arguments. Support and Attack relations are the backbone of any legal argument. However, …...
French CrowS-Pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than English
AbstractWarning: This paper contains explicit statements of offensive stereotypes which may be upsetting. Much work on biases in natural language processing has addressed biases linked to the social and cultural …...
Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages
AbstractWe present Samanantar, the largest publicly available parallel corpora collection for Indic languages. The collection contains a total of 49.7 million sentence pairs between English and 11 Indic languages (from …...
SciPar: A Collection of Parallel Corpora from Scientific Abstracts
AbstractThis paper presents SciPar, a new collection of parallel corpora created from openly available metadata of bachelor theses, master theses and doctoral dissertations hosted in institutional repositories, digital libraries of …...