Search results for "computer.software_genre"

Data Augmentation for Pipeline-Based Speech Translation

2020

International audience; Pipeline-based speech translation methods may suffer from errors found in speech recognition system output. Therefore, it is crucial that machine translation systems are trained to be robust against such noise. In this paper, we propose two methods for parallel data augmentation for pipeline-based speech translation system development. The first method utilises a speech processing workflow to introduce errors and the second method generates commonly found suffix errors using a rule-based method. We show that the methods in combination allow significantly improving speech translation quality by 1.87 BLEU points over a baseline system.

Semantic Word Error Rate for Sentence Similarity

2016

Sentence similarity measures have applications in several tasks, including: Machine Translation, Paraphrase Iden- tification, Speech Recognition, Question-answering and Text Summarization. However, measures designed for these tasks are aimed at assessing equivalence rather than resemblance, partly departing from human cognition of similarity. While this is reasonable for these activities, it hinders the applicability of sentence similarity measures to other tasks. We therefore propose a new sentence similarity measure specifically designed for resemblance evaluation, in order to cover these fields better. Experimental results are discussed.

Robust Neural Machine Translation: Modeling Orthographic and Interpunctual Variation

2020

Neural machine translation systems typically are trained on curated corpora and break when faced with non-standard orthography or punctuation. Resilience to spelling mistakes and typos, however, is crucial as machine translation systems are used to translate texts of informal origins, such as chat conversations, social media posts and web pages. We propose a simple generative noise model to generate adversarial examples of ten different types. We use these to augment machine translation systems’ training data and show that, when tested on noisy data, systems trained using adversarial examples perform almost as well as when translating clean data, while baseline systems’ performance drops by…

Source-Target Mapping Model of Streaming Data Flow for Machine Translation

2017

Streaming information flow allows identification of linguistic similarities between language pairs in real time as it relies on pattern recognition of grammar rules, semantics and pronunciation especially when analyzing so called international terms, syntax of the language family as well as tenses transitivity between the languages. Overall, it provides a backbone translation knowledge for building automatic translation system that facilitates processing any of various abstract entities which combine to specify underlying phonological, morphological, semantic and syntactic properties of linguistic forms and that act as the targets of linguistic rules and operations in a source language foll…

Translingual text mining for identification of language pair phenomena

2016

Translingual Text Mining (TTM) is an innovative technology of natural language processing for building multilingual parallel corpora, processing machine translation, contextual knowledge acquisition, information extraction, query profiling, language modeling, contextual word sensing, creating feature test sets and for variety of other purposes. The Keynote Lecture will discuss opportunities and challenges of this computational technology. In particular, the focus will be made on identification of language pair phenomena and their applications to building holistic language model which is a novel tool for processing machine translation, supporting professional translations, evaluation of tran…

Outline for a Relevance Theoretical Model of Machine Translation Post-editing

2018

Translation process research (TPR) has advanced in the recent years to a state which allows us to study “in great detail what source and target text units are being processed, at a given point in time, to investigate what steps are involved in this process, what segments are read and aligned and how this whole process is monitored” (Alves 2015, p. 32). We have sophisticated statistical methods and with the powerful tools to produce a better and more detailed understanding of the underlying cognitive processes that are involved in translation. Following Jakobsen (2011), who suspects that we may soon be in a situation which allows us to develop a computational model of human translation, Alve…

Monolingual and cross-lingual intent detection without training data in target languages

2021

Due to recent DNN advancements, many NLP problems can be effectively solved using transformer-based models and supervised data. Unfortunately, such data is not available in some languages. This research is based on assumptions that (1) training data can be obtained by the machine translating it from another language

2014

Large data sets classification is widely used in many industrial applications. It is a challenging task to classify large data sets efficiently, accurately, and robustly, as large data sets always contain numerous instances with high dimensional feature space. In order to deal with this problem, in this paper we present an online Logdet divergence based metric learning (LDML) model by making use of the powerfulness of metric learning. We firstly generate a Mahalanobis matrix via learning the training data with LDML model. Meanwhile, we propose a compressed representation for high dimensional Mahalanobis matrix to reduce the computation complexity in each iteration. The final Mahalanobis mat…

Decision Committee Learning with Dynamic Integration of Classifiers

2000

Decision committee learning has demonstrated spectacular success in reducing classification error from learned classifiers. These techniques develop a classifier in the form of a committee of subsidiary classifiers. The combination of outputs is usually performed by majority vote. Voting, however, has a shortcoming. It is unable to take into account local expertise. When a new instance is difficult to classify, then the average classifier will give a wrong prediction, and the majority vote will more probably result in a wrong prediction. Instead of voting, dynamic integration of classifiers can be used, which is based on the assumption that each committee member is best inside certain subar…

Dynamic Integration of Decision Committees

2000

Decision committee learning has demonstrated outstanding success in reducing classification error with an ensemble of classifiers. In a way a decision committee is a classifier formed upon an ensemble of subsidiary classifiers. Voting, which is commonly used to produce the final decision of committees has, however, a shortcoming. It is unable to take into account local expertise. When a new instance is difficult to classify, then it easily happens that only the minority of the classifiers will succeed, and the majority voting will quite probably result in a wrong classification. We suggest that dynamic integration of classifiers is used instead of majority voting in decision committees. Our…