Duygu Ataman

Duygu Ataman

Auto-generated profile, based on publicly available information

Duygu Ataman

Google AI University of Trento Fondazione Bruno Kessler University of Trento Fondazione Bruno Kessler University of Edinburgh

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2017 in The Prague Bulletin of Mathematical Linguistics
Verified
Journal Article
Open access
PDF file
DADuygu Ataman
Duygu Ataman
MNMatteo Negri
Matteo Negri
MTMarco Turchi
Marco Turchi
MFMarcello Federico
Marcello Federico
The necessity of using a fixed-size word vocabulary in order to control the model complexity in state-of-the-art neural machine translation (NMT) systems is an important bottleneck on performance, especially for morphologically rich languages. Conventional methods that aim to overcome this problem by using sub-word or character-level representations solely rely on statistics and disregard the linguistic properties of words, which leads to interruptions in the word structure and causes semantic and syntactic losses. 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. Our method is based on unsupervised morphology learning and can be, in principle, used for pre-processing any language pair. We also present an alternative word segmentation method based on supervised morphological analysis, which aids us in measuring the accuracy of our model. We evaluate our method in Turkish-to-English NMT task where the input language is morphologically rich and agglutinative. We analyze different representation methods in terms of translation accuracy as well as the semantic and syntactic properties of the generated output. Our method obtains a significant improvement of 2.3 BLEU points over the conventional vocabulary reduction technique, showing that it can provide better accuracy in open vocabulary translation of morphologically rich languages.

1 January 2019
Verified
Conference Paper
Open access
PDF file
DADuygu Ataman
Duygu Ataman
OFOrhan Firat
Orhan Firat
MGMattia A. Di Gangi
Mattia A. Di Gangi
MFMarcello Federico
Marcello Federico
ABAlexandra Birch
Alexandra Birch
Duygu Ataman, Orhan Firat, Mattia A. Di Gangi, Marcello Federico, Alexandra Birch. Proceedings of the 3rd Workshop on Neural Generation and Translation. 2019.

14 May 2018 in arXiv
Verified
Preprint
Open access
PDF file
DADuygu Ataman
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. In this paper, we describe the collection process of the corpus and its statistical properties. We validate the benefit of using the Bianet corpus by evaluating bilingual and multilingual neural machine translation models in English-Turkish and English-Kurdish directions.

5 May 2018 in arXiv
Verified
Preprint
Open access
PDF file
DADuygu Ataman
Duygu Ataman
MFMarcello Federico
Marcello Federico
Neural machine translation (NMT) models are typically trained with fixed-size input and output vocabularies, which creates an important bottleneck on their accuracy and generalization capability. As a solution, various studies proposed segmenting words into sub-word units and performing translation at the sub-lexical level. However, statistical word segmentation methods have recently shown to be prone to morphological errors, which can lead to inaccurate translations. In this paper, we propose to overcome this problem by replacing the source-language embedding layer of NMT with a bi-directional recurrent neural network that generates compositional representations of the input at any desired level of granularity. We test our approach in a low-resource setting with five languages from different morphological typologies, and under different composition assumptions. 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.