Improve performance of machine translation service using memcached

Author(s):  
Priyank Gupta ◽  
Rashid Ahmad ◽  
Manish Shrivastava ◽  
Pawan Kumar ◽  
Mukul K Sinha
2013 ◽  
Vol 1 ◽  
pp. 165-178
Author(s):  
Adam Lopez ◽  
Matt Post ◽  
Chris Callison-Burch ◽  
Jonathan Weese ◽  
Juri Ganitkevitch ◽  
...  

Machine translation (MT) draws from several different disciplines, making it a complex subject to teach. There are excellent pedagogical texts, but problems in MT and current algorithms for solving them are best learned by doing. As a centerpiece of our MT course, we devised a series of open-ended challenges for students in which the goal was to improve performance on carefully constrained instances of four key MT tasks: alignment, decoding, evaluation, and reranking. Students brought a diverse set of techniques to the problems, including some novel solutions which performed remarkably well. A surprising and exciting outcome was that student solutions or their combinations fared competitively on some tasks, demonstrating that even newcomers to the field can help improve the state-of-the-art on hard NLP problems while simultaneously learning a great deal. The problems, baseline code, and results are freely available.


2019 ◽  
Vol 5 (1) ◽  
pp. 55
Author(s):  
Muhammad Muharrom Al Haromainy ◽  
Dimas Ari Setyawan ◽  
Onny Kartika Waluya ◽  
Agus Zainal Arifin

Sistem Information Retrieval (IR) maupun chatbot semakin banyak dikembangkan. Salah satu bagian yang banyak diteliti adalah cross language. Masalah pada pengembangan cross language yaitu terjadinya kesalahan pada hasil terjemahan mesin translasi yang memberikan arti tidak sesuai dengan bahasa natural, sehingga pengguna tidak mendapatkan jawaban yang semestinya, bahkan tidak jarang pula pengguna tidak menemukan jawaban. Penelitian ini mengusulkan skema baru mesin translasi yang bertujuan meningkatkan performa dalam masalah ambiguitas. Mesin translasi bekerja dengan cek kebenaran kata kunci, kemudian melakukan Part-of-Speech (POS) Tagging pada kata benda (noun). Kemudian, setiap kata benda yang terdeteksi akan dicari sinonimnya. Lalu, sinonim yang didapatkan akan ditambahkan dan menjadi alternatif kueri baru. Kueri yang mempunyai nilai confident tertinggi diasumsikan sebagai kueri yang paling sesuai. Pada hasil yang didapatkan setelah dilakukan uji coba, melalui penambahan metode yang kami usulkan pada machine translation, dapat meningkatkan akurasi chatbot dibandingkan tanpa menggunakan skema yang diusulkan. Hasil akurasi bertambah 5%, dari yang semula 73% menjadi 77%.  Information retrieval and chatbot systems are increasingly being developed with its language part mostly studied. However, the problem associated with its development is the occurrence of errors in the translation machine resulting in inaccurate answers not in accordance with the natural language, thereby providing users with wrong answers. This study proposes a new translation machine scheme that aims to improve performance while translating ambiguous terms. Translation machines functions by checking the correctness of keywords, and carrying out Part-of-Speech (POS) Tagging on nouns (noun). The synonyms of any detected noun are searched for and obtained added to become alternative new queries. Those with the highest confident value are assumed to be the most appropriate. The results obtained after testing, through the addition of the method proposed in machine translation, can improve the accuracy of the chatbot compared to not using the proposed scheme. The results of the accuracy increased from the original 73% to 77%.


Author(s):  
Mārcis Pinnis ◽  
Stephan Busemann ◽  
Artūrs Vasiļevskis ◽  
Josef van Genabith

AbstractThis contribution describes the German EU Council Presidency Translator (EUC PT), a machine translation service created for the German EU Council Presidency in the second half of 2020, which is open to the general public. Following a series of earlier presidency translators, the German version exhibits important extensions and improvements. The German EUC PT is the first to integrate systems from commercial vendors, public services, and a research center, using a mix of custom and generic translation engines, and to introduce a new webpage translation widget. A further important feature is the close collaboration with human translators from the German ministries, who were provided with computer-assisted translation tool plugins integrating machine translation services into their daily work environments. Uptake by the public reflects a huge interest in the service, showing the need for breaking language barriers.


Author(s):  
Ryu Iida ◽  
Canasai Kruengkrai ◽  
Ryo Ishida ◽  
Kentaro Torisawa ◽  
Jong-Hoon Oh ◽  
...  

This paper proposes a novel method for generating compact answers to open-domain why-questions, such as the following answer, “Because deep learning technologies were introduced,” to the question, “Why did Google’s machine translation service improve so drastically?” Although many works have dealt with why-question answering, most have focused on retrieving as answers relatively long text passages that consist of several sentences. Because of their length, such passages are not appropriate to be read aloud by spoken dialog systems and smart speakers; hence, we need to create a method that generates compact answers. We developed a novel neural summarizer for this compact answer generation task. It combines a recurrent neural network-based encoderdecoder model with stacked convolutional neural networks and was designed to effectively exploit background knowledge, in this case a set of causal relations (e.g., “[Microsoft’s machine translation has made great progress over the last few years]effect since [it started to use deep learning.]cause”) that was extracted from a large web data archive (4 billion web pages). Our experimental results show that our method achieved significantly better ROUGE F-scores than existing encoder-decoder models and their variations that were augmented with query-attention and memory networks, which are used to exploit the background knowledge.


Author(s):  
Milam Aiken

Communicating in a non-native language during a traditional, oral meeting is difficult, but a Group Support System (GSS) along with online machine translation (MT) can increase the efficiency and effectiveness of the discussion. An experimental study shows that a group facilitator can use a Web-based translation service to support a multilingual meeting, but completely automated language support is likely to be more efficient for large groups.


2020 ◽  
Vol 46 (2) ◽  
pp. 387-424 ◽  
Author(s):  
Raúl Vázquez ◽  
Alessandro Raganato ◽  
Mathias Creutz ◽  
Jörg Tiedemann

Neural machine translation has considerably improved the quality of automatic translations by learning good representations of input sentences. In this article, we explore a multilingual translation model capable of producing fixed-size sentence representations by incorporating an intermediate crosslingual shared layer, which we refer to as attention bridge. This layer exploits the semantics from each language and develops into a language-agnostic meaning representation that can be efficiently used for transfer learning. We systematically study the impact of the size of the attention bridge and the effect of including additional languages in the model. In contrast to related previous work, we demonstrate that there is no conflict between translation performance and the use of sentence representations in downstream tasks. In particular, we show that larger intermediate layers not only improve translation quality, especially for long sentences, but also push the accuracy of trainable classification tasks. Nevertheless, shorter representations lead to increased compression that is beneficial in non-trainable similarity tasks. Similarly, we show that trainable downstream tasks benefit from multilingual models, whereas additional language signals do not improve performance in non-trainable benchmarks. This is an important insight that helps to properly design models for specific applications. Finally, we also include an in-depth analysis of the proposed attention bridge and its ability to encode linguistic properties. We carefully analyze the information that is captured by individual attention heads and identify interesting patterns that explain the performance of specific settings in linguistic probing tasks.


2015 ◽  
Vol 54 ◽  
pp. 159-192
Author(s):  
Lluís Formiga ◽  
Alberto Barrón-Cedeño ◽  
Lluís Màrquez ◽  
Carlos A. Henríquez ◽  
José B. Mariño

In this article we present a three-step methodology for dynamically improving a statistical machine translation (SMT) system by incorporating human feedback in the form of free edits on the system translations. We target at feedback provided by casual users, which is typically error-prone. Thus, we first propose a filtering step to automatically identify the better user-edited translations and discard the useless ones. A second step produces a pivot-based alignment between source and user-edited sentences, focusing on the errors made by the system. Finally, a third step produces a new translation model and combines it linearly with the one from the original system. We perform a thorough evaluation on a real-world dataset collected from the Reverso.net translation service and show that every step in our methodology contributes significantly to improve a general purpose SMT system. Interestingly, the quality improvement is not only due to the increase of lexical coverage, but to a better lexical selection, reordering, and morphology. Finally, we show the robustness of the methodology by applying it to a different scenario, in which the new examples come from an automatically Web-crawled parallel corpus. Using exactly the same architecture and models provides again a significant improvement of the translation quality of a general purpose baseline SMT system.


2017 ◽  
Vol 109 (1) ◽  
pp. 5-14
Author(s):  
Sander Tars ◽  
Kaspar Papli ◽  
Dmytro Chasovskyi ◽  
Mark Fishel

Abstract We introduce an open-source implementation of a machine translation API server. The aim of this software package is to enable anyone to run their own multi-engine translation server with neural machine translation engines, supporting an open API for client applications. Besides the hub with the implementation of the client API and the translation service providers running in the background we also describe an open-source demo web application that uses our software package and implements an online translation tool that supports collecting translation quality comparisons from users.


2014 ◽  
Vol 45 (3) ◽  
pp. 239-245 ◽  
Author(s):  
Robert J. Calin-Jageman ◽  
Tracy L. Caldwell

A recent series of experiments suggests that fostering superstitions can substantially improve performance on a variety of motor and cognitive tasks ( Damisch, Stoberock, & Mussweiler, 2010 ). We conducted two high-powered and precise replications of one of these experiments, examining if telling participants they had a lucky golf ball could improve their performance on a 10-shot golf task relative to controls. We found that the effect of superstition on performance is elusive: Participants told they had a lucky ball performed almost identically to controls. Our failure to replicate the target study was not due to lack of impact, lack of statistical power, differences in task difficulty, nor differences in participant belief in luck. A meta-analysis indicates significant heterogeneity in the effect of superstition on performance. This could be due to an unknown moderator, but no effect was observed among the studies with the strongest research designs (e.g., high power, a priori sampling plan).


Sign in / Sign up

Export Citation Format

Share Document