Search Results for author: Shahram Khadivi

Found 25 papers, 4 papers with code

Can Data Diversity Enhance Learning Generalization?

no code implementations COLING 2022 Yu Yu, Shahram Khadivi, Jia Xu

This paper introduces our Diversity Advanced Actor-Critic reinforcement learning (A2C) framework (DAAC) to improve the generalization and accuracy of Natural Language Processing (NLP).

Domain Adaptation Language Modelling +5

Multi-armed bandits for online optimization of language model pre-training: the use case of dynamic masking

no code implementations24 Mar 2022 Iñigo Urteaga, Moulay-Zaïdane Draïdia, Tomer Lancewicki, Shahram Khadivi

In this work, we propose a multi-armed bandit-based online optimization framework for the sequential selection of pre-training hyperparameters to optimize language model performance.

Decision Making Language Modelling +2

A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings

no code implementations loresmt (COLING) 2022 Mohaddeseh Bastan, Shahram Khadivi

Neural Machine Translation (NMT) models are strong enough to convey semantic and syntactic information from the source language to the target language.

Machine Translation NMT +1

Back-translation for Large-Scale Multilingual Machine Translation

1 code implementation WMT (EMNLP) 2021 Baohao Liao, Shahram Khadivi, Sanjika Hewavitharana

Surprisingly, the smaller size of vocabularies perform better, and the extensive monolingual English data offers a modest improvement.

Machine Translation Translation

Diving Deep into Context-Aware Neural Machine Translation

no code implementations WMT (EMNLP) 2020 Jingjing Huo, Christian Herold, Yingbo Gao, Leonard Dahlmann, Shahram Khadivi, Hermann Ney

Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e. g., document-level translation, or having meta-information.

Machine Translation NMT +1

Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages

no code implementations IJCNLP 2019 Yunsu Kim, Petre Petrov, Pavel Petrushkov, Shahram Khadivi, Hermann Ney

We present effective pre-training strategies for neural machine translation (NMT) using parallel corpora involving a pivot language, i. e., source-pivot and pivot-target, leading to a significant improvement in source-target translation.

Machine Translation NMT +2

Generalizing Back-Translation in Neural Machine Translation

no code implementations WS 2019 Miguel Graça, Yunsu Kim, Julian Schamper, Shahram Khadivi, Hermann Ney

Back-translation - data augmentation by translating target monolingual data - is a crucial component in modern neural machine translation (NMT).

Data Augmentation Machine Translation +3

Learning from Chunk-based Feedback in Neural Machine Translation

no code implementations ACL 2018 Pavel Petrushkov, Shahram Khadivi, Evgeny Matusov

We empirically investigate learning from partial feedback in neural machine translation (NMT), when partial feedback is collected by asking users to highlight a correct chunk of a translation.

Machine Translation NMT +1

Can Neural Machine Translation be Improved with User Feedback?

no code implementations NAACL 2018 Julia Kreutzer, Shahram Khadivi, Evgeny Matusov, Stefan Riezler

We present the first real-world application of methods for improving neural machine translation (NMT) with human reinforcement, based on explicit and implicit user feedback collected on the eBay e-commerce platform.

Machine Translation NMT +1

Neural and Statistical Methods for Leveraging Meta-information in Machine Translation

no code implementations MTSummit 2017 Shahram Khadivi, Patrick Wilken, Leonard Dahlmann, Evgeny Matusov

In this paper, we discuss different methods which use meta information and richer context that may accompany source language input to improve machine translation quality.

Machine Translation Translation

Graph-Based Semi-Supervised Conditional Random Fields For Spoken Language Understanding Using Unaligned Data

1 code implementation ALTA 2014 Mohammad Aliannejadi, Masoud Kiaeeha, Shahram Khadivi, Saeed Shiry Ghidary

We experiment graph-based Semi-Supervised Learning (SSL) of Conditional Random Fields (CRF) for the application of Spoken Language Understanding (SLU) on unaligned data.

Spoken Language Understanding

Neural Machine Translation on Scarce-Resource Condition: A case-study on Persian-English

no code implementations7 Jan 2017 Mohaddeseh Bastan, Shahram Khadivi, Mohammad Mehdi Homayounpour

This new loss function yields a total of 1. 87 point improvements in terms of BLEU score in the translation quality.

NMT Translation +2

Guided Alignment Training for Topic-Aware Neural Machine Translation

2 code implementations AMTA 2016 Wenhu Chen, Evgeny Matusov, Shahram Khadivi, Jan-Thorsten Peter

In this paper, we propose an effective way for biasing the attention mechanism of a sequence-to-sequence neural machine translation (NMT) model towards the well-studied statistical word alignment models.

Domain Adaptation Machine Translation +3

A Holistic Approach to Bilingual Sentence Fragment Extraction from Comparable Corpora

no code implementations LREC 2012 Mahdi Khademian, Kaveh Taghipour, Saab Mansour, Shahram Khadivi

Achieving accurate translation, especially in multiple domain documents with statistical machine translation systems, requires more and more bilingual texts and this need becomes more critical when training such systems for language pairs with scarce training data.

Boundary Detection Machine Translation +1

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