Search Results for author: Duygu Ataman

Found 13 papers, 4 papers with code

Evaluating Multiway Multilingual NMT in the Turkic Languages

no code implementations13 Sep 2021 Jamshidbek Mirzakhalov, Anoop Babu, Aigiz Kunafin, Ahsan Wahab, Behzod Moydinboyev, Sardana Ivanova, Mokhiyakhon Uzokova, Shaxnoza Pulatova, Duygu Ataman, Julia Kreutzer, Francis Tyers, Orhan Firat, John Licato, Sriram Chellappan

Then, we train 26 bilingual baselines as well as a multi-way neural MT (MNMT) model using the corpus and perform an extensive analysis using automatic metrics as well as human evaluations.

Machine Translation

Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models

1 code implementation EMNLP 2021 Jiaoda Li, Duygu Ataman, Rico Sennrich

Multimodal machine translation (MMT) systems have been shown to outperform their text-only neural machine translation (NMT) counterparts when visual context is available.

Image Captioning Multimodal Machine Translation +1

A Latent Morphology Model for Open-Vocabulary Neural Machine Translation

1 code implementation ICLR 2020 Duygu Ataman, Wilker Aziz, Alexandra Birch

Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic.

Machine Translation Morphological Inflection +1

On the Importance of Word Boundaries in Character-level Neural Machine Translation

1 code implementation WS 2019 Duygu Ataman, Orhan Firat, Mattia A. Di Gangi, Marcello Federico, Alexandra Birch

Neural Machine Translation (NMT) models generally perform translation using a fixed-size lexical vocabulary, which is an important bottleneck on their generalization capability and overall translation quality.

Machine Translation Translation

Bianet: A Parallel News Corpus in Turkish, Kurdish and English

no code implementations14 May 2018 Duygu Ataman

We present a new open-source parallel corpus consisting of news articles collected from the Bianet magazine, an online newspaper that publishes Turkish news, often along with their translations in English and Kurdish.

Machine Translation Translation

Compositional Representation of Morphologically-Rich Input for Neural Machine Translation

no code implementations ACL 2018 Duygu Ataman, Marcello Federico

By training NMT to compose word representations from character n-grams, our approach consistently outperforms (from 1. 71 to 2. 48 BLEU points) NMT learning embeddings of statistically generated sub-word units.

Machine Translation Translation

Linguistically Motivated Vocabulary Reduction for Neural Machine Translation from Turkish to English

no code implementations31 Jul 2017 Duygu Ataman, Matteo Negri, Marco Turchi, Marcello Federico

In this paper, we propose a new vocabulary reduction method for NMT, which can reduce the vocabulary of a given input corpus at any rate while also considering the morphological properties of the language.

Machine Translation Morphological Analysis +1

Cannot find the paper you are looking for? You can Submit a new open access paper.