Search Results for author:
Found 85 papers, 19 papers with code
Parallel Sentence Extraction from Comparable Corpora with Neural Network Features
Parallel corpora are crucial for machine translation (MT), however they are quite scarce for most language pairs and domains.
An Empirical Comparison of Simple Domain Adaptation Methods for Neural Machine Translation
In this paper, we propose a novel domain adaptation method named "mixed fine tuning" for neural machine translation (NMT).
Enabling Multi-Source Neural Machine Translation By Concatenating Source Sentences In Multiple Languages
In this paper, we explore a simple solution to "Multi-Source Neural Machine Translation" (MSNMT) which only relies on preprocessing a N-way multilingual corpus without modifying the Neural Machine Translation (NMT) architecture or training procedure.
An Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation
In this paper, we propose a novel domain adaptation method named {``}mixed fine tuning{''} for neural machine translation (NMT).
MMCR4NLP: Multilingual Multiway Corpora Repository for Natural Language Processing
Multilinguality is gradually becoming ubiquitous in the sense that more and more researchers have successfully shown that using additional languages help improve the results in many Natural Language Processing tasks.
Kyoto University Participation to WAT 2017
We describe here our approaches and results on the WAT 2017 shared translation tasks.
Neural Machine Translation: Basics, Practical Aspects and Recent Trends
Machine Translation (MT) is a sub-field of NLP which has experienced a number of paradigm shifts since its inception.
Recurrent Stacking of Layers for Compact Neural Machine Translation Models
In neural machine translation (NMT), the most common practice is to stack a number of recurrent or feed-forward layers in the encoder and the decoder.
A Brief Survey of Multilingual Neural Machine Translation
We present a survey on multilingual neural machine translation (MNMT), which has gained a lot of traction in the recent years.
Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translation
In this paper, we propose two novel methods for domain adaptation for the attention-only neural machine translation (NMT) model, i. e., the Transformer.
Exploiting Out-of-Domain Parallel Data through Multilingual Transfer Learning for Low-Resource Neural Machine Translation
This paper proposes a novel multilingual multistage fine-tuning approach for low-resource neural machine translation (NMT), taking a challenging Japanese--Russian pair for benchmarking.
NICT's Machine Translation Systems for the WMT19 Similar Language Translation Task
Our primary submission to the task is the result of a simple combination of our SMT and NMT systems.
NICT's Supervised Neural Machine Translation Systems for the WMT19 News Translation Task
In this paper, we describe our supervised neural machine translation (NMT) systems that we developed for the news translation task for Kazakh↔English, Gujarati↔English, Chinese↔English, and English→Finnish translation directions.
NICT's Supervised Neural Machine Translation Systems for the WMT19 Translation Robustness Task
al., 2017) to improve translation quality for Japanese↔English.
Multi-Layer Softmaxing during Training Neural Machine Translation for Flexible Decoding with Fewer Layers
This paper proposes a novel procedure for training an encoder-decoder based deep neural network which compresses NxM models into a single model enabling us to dynamically choose the number of encoder and decoder layers for decoding.
NICT's participation to WAT 2019: Multilingualism and Multi-step Fine-Tuning for Low Resource NMT
In this paper we describe our submissions to WAT 2019 for the following tasks: English{--}Tamil translation and Russian{--}Japanese translation.
Overview of the 6th Workshop on Asian Translation
This paper presents the results of the shared tasks from the 6th workshop on Asian translation (WAT2019) including Ja↔En, Ja↔Zh scientific paper translation subtasks, Ja↔En, Ja↔Ko, Ja↔En patent translation subtasks, Hi↔En, My↔En, Km↔En, Ta↔En mixed domain subtasks and Ru↔Ja news commentary translation task.
Exploiting Multilingualism through Multistage Fine-Tuning for Low-Resource Neural Machine Translation
This paper highlights the impressive utility of multi-parallel corpora for transfer learning in a one-to-many low-resource neural machine translation (NMT) setting.
Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation
To address this, we examine a language independent framework for parallel corpus mining which is a quick and effective way to mine a parallel corpus from publicly available lectures at Coursera.
A Comprehensive Survey of Multilingual Neural Machine Translation
We present a survey on multilingual neural machine translation (MNMT), which has gained a lot of traction in the recent years.
Pre-training via Leveraging Assisting Languages and Data Selection for Neural Machine Translation
To this end, we propose to exploit monolingual corpora of other languages to complement the scarcity of monolingual corpora for the LOI.
Balancing Cost and Benefit with Tied-Multi Transformers
We propose and evaluate a novel procedure for training multiple Transformers with tied parameters which compresses multiple models into one enabling the dynamic choice of the number of encoder and decoder layers during decoding.
JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation
Monolingual pre-training approaches such as MASS (MAsked Sequence to Sequence) are extremely effective in boosting NMT quality for languages with small parallel corpora.
Pre-training via Leveraging Assisting Languages for Neural Machine Translation
Sequence-to-sequence (S2S) pre-training using large monolingual data is known to improve performance for various S2S NLP tasks.
Softmax Tempering for Training Neural Machine Translation Models
Neural machine translation (NMT) models are typically trained using a softmax cross-entropy loss where the softmax distribution is compared against smoothed gold labels.
Improving Low-Resource NMT through Relevance Based Linguistic Features Incorporation
In this study, linguistic knowledge at different levels are incorporated into the neural machine translation (NMT) framework to improve translation quality for language pairs with extremely limited data.
Multilingual Neural Machine Translation
The advent of neural machine translation (NMT) has opened up exciting research in building multilingual translation systems i. e. translation models that can handle more than one language pair.
Simultaneous Multi-Pivot Neural Machine Translation
Parallel corpora are indispensable for training neural machine translation (NMT) models, and parallel corpora for most language pairs do not exist or are scarce.
Recurrent Stacking of Layers in Neural Networks: An Application to Neural Machine Translation
Finally, we analyze the effects of recurrently stacked layers by visualizing the attentions of models that use recurrently stacked layers and models that do not.
YANMTT: Yet Another Neural Machine Translation Toolkit
In this paper we present our open-source neural machine translation (NMT) toolkit called "Yet Another Neural Machine Translation Toolkit" abbreviated as YANMTT which is built on top of the Transformers library.
IndicBART: A Pre-trained Model for Indic Natural Language Generation
We present IndicBART, a multilingual, sequence-to-sequence pre-trained model focusing on 11 Indic languages and English.
Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages
We, then, evaluate the impact of our cognate detection mechanism on neural machine translation (NMT), as a downstream task.
Cross-Lingual Information Retrieval
Cross-Lingual Word Embeddings
+5
IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages
Natural Language Generation (NLG) for non-English languages is hampered by the scarcity of datasets in these languages.
Fusion of Self-supervised Learned Models for MOS Prediction
This challenge aims to predict MOS scores of synthetic speech on two tracks, the main track and a more challenging sub-track: out-of-domain (OOD).
When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?
Meanwhile, the contrastive objective can implicitly utilize automatically learned word alignment, which has not been explored in many-to-many NMT.
MorisienMT: A Dataset for Mauritian Creole Machine Translation
In this paper, we describe MorisienMT, a dataset for benchmarking machine translation quality of Mauritian Creole.
MT Metrics Correlate with Human Ratings of Simultaneous Speech Translation
There have been several meta-evaluation studies on the correlation between human ratings and offline machine translation (MT) evaluation metrics such as BLEU, chrF2, BertScore and COMET.
IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation metrics for Indian Languages
In this paper, we fill this gap by creating an MQM dataset consisting of 7000 fine-grained annotations, spanning 5 Indian languages and 7 MT systems, and use it to establish correlations between annotator scores and scores obtained using existing automatic metrics.
An Empirical Study of Leveraging Knowledge Distillation for Compressing Multilingual Neural Machine Translation Models
Knowledge distillation (KD) is a well-known method for compressing neural models.
A Comprehensive Analysis of Adapter Efficiency
However, adapters have not been sufficiently analyzed to understand if PEFT translates to benefits in training/deployment efficiency and maintainability/extensibility.
Exploring the Impact of Layer Normalization for Zero-shot Neural Machine Translation
This paper studies the impact of layer normalization (LayerNorm) on zero-shot translation (ZST).
Variable-length Neural Interlingua Representations for Zero-shot Neural Machine Translation
The language-independency of encoded representations within multilingual neural machine translation (MNMT) models is crucial for their generalization ability on zero-shot translation.
Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models
This study investigates machine translation between related languages i. e., languages within the same family that share linguistic characteristics such as word order and lexical similarity.
CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation
We learn a regression model, CTQ Scorer (Contextual Translation Quality), that selects examples based on multiple features in order to maximize the translation quality.
IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages
Prior to this work, there was (i) no parallel training data spanning all 22 languages, (ii) no robust benchmarks covering all these languages and containing content relevant to India, and (iii) no existing translation models which support all the 22 scheduled languages of India.
Robustness of Multi-Source MT to Transcription Errors
Automatic speech translation is sensitive to speech recognition errors, but in a multilingual scenario, the same content may be available in various languages via simultaneous interpreting, dubbing or subtitling.
SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning
Automating figure caption generation helps move model understandings of scientific documents beyond text and will help authors write informative captions that facilitate communicating scientific findings.
Turning Whisper into Real-Time Transcription System
Whisper is one of the recent state-of-the-art multilingual speech recognition and translation models, however, it is not designed for real time transcription.
SelfSeg: A Self-supervised Sub-word Segmentation Method for Neural Machine Translation
Sub-word segmentation is an essential pre-processing step for Neural Machine Translation (NMT).
CreoleVal: Multilingual Multitask Benchmarks for Creoles
Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research.
Bilingual Corpus Mining and Multistage Fine-Tuning for Improving Machine Translation of Lecture Transcripts
To create the parallel corpora, we propose a dynamic programming based sentence alignment algorithm which leverages the cosine similarity of machine-translated sentences.
Natural Language Processing for Dialects of a Language: A Survey
Motivated by the performance degradation of NLP models for dialectic datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches.
PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities
To demonstrate this fact, we release a Pragmatics Understanding Benchmark (PUB) dataset consisting of fourteen tasks in four pragmatics phenomena, namely, Implicature, Presupposition, Reference, and Deixis.
An Empirical Study of In-context Learning in LLMs for Machine Translation
While we establish the significance of the quality of the target distribution over the source distribution of demonstrations, we further observe that perturbations sometimes act as regularizers, resulting in performance improvements.
MOS-FAD: Improving Fake Audio Detection Via Automatic Mean Opinion Score Prediction
We propose MOS-FAD, where MOS can be leveraged at two key points in FAD: training data selection and model fusion.
RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models models via Romanization
This study addresses the challenge of extending Large Language Models (LLMs) to non-English languages using non-Roman scripts.
Airavata: Introducing Hindi Instruction-tuned LLM
We announce the initial release of "Airavata," an instruction-tuned LLM for Hindi.
IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages
We hope that the datasets, tools, and resources released as a part of this work will not only propel the research and development of Indic LLMs but also establish an open-source blueprint for extending such efforts to other languages.
Do Not Worry if You Do Not Have Data: Building Pretrained Language Models Using Translationese
In this paper, we explore the utility of Translationese as synthetic data created using machine translation for pre-training language models (LMs).
A Morphology-Based Investigation of Positional Encodings
How does the importance of positional encoding in pre-trained language models (PLMs) vary across languages with different morphological complexity?
Sophisticated Lexical Databases - Simplified Usage: Mobile Applications and Browser Plugins For Wordnets
India is a country with 22 officially recognized languages and 17 of these have WordNets, a crucial resource.
NICT-5’s Submission To WAT 2021: MBART Pre-training And In-Domain Fine Tuning For Indic Languages
The objective of the task was to explore the utility of multilingual approaches using a variety of in-domain and out-of-domain parallel and monolingual corpora.
Overview of the 8th Workshop on Asian Translation
This paper presents the results of the shared tasks from the 8th workshop on Asian translation (WAT2021).
NICT’s Submission to the WAT 2022 Structured Document Translation Task
However, to our surprise, we find that existing multilingual NMT systems are able to handle the translation of text annotated with XML tags without any explicit training on data containing said tags.
Combining Sequence Distillation and Transfer Learning for Efficient Low-Resource Neural Machine Translation Models
This paper investigates a combination of SD and TL for training efficient NMT models for ELR settings, where we utilize TL with helping corpora twice: once for distilling the ELR corpora and then during compact model training.
Kyoto University MT System Description for IWSLT 2017
We describe here our Machine Translation (MT) model and the results we obtained for the IWSLT 2017 Multilingual Shared Task.
Overview of the 9th Workshop on Asian Translation
This paper presents the results of the shared tasks from the 9th workshop on Asian translation (WAT2022).
FeatureBART: Feature Based Sequence-to-Sequence Pre-Training for Low-Resource NMT
In this paper we present FeatureBART, a linguistically motivated sequence-to-sequence monolingual pre-training strategy in which syntactic features such as lemma, part-of-speech and dependency labels are incorporated into the span prediction based pre-training framework (BART).
NICT‘s Submission To WAT 2020: How Effective Are Simple Many-To-Many Neural Machine Translation Models?
In this paper we describe our team‘s (NICT-5) Neural Machine Translation (NMT) models whose translations were submitted to shared tasks of the 7th Workshop on Asian Translation.
Overview of the 7th Workshop on Asian Translation
This paper presents the results of the shared tasks from the 7th workshop on Asian translation (WAT2020).
Studying The Impact Of Document-level Context On Simultaneous Neural Machine Translation
To this end and in this paper and we propose wait-k simultaneous document-level NMT where we keep the context encoder as it is and replace the source sentence encoder and target language decoder with their wait-k equivalents.
Investigating Softmax Tempering for Training Neural Machine Translation Models
In low-resource scenarios and NMT models tend to perform poorly because the model training quickly converges to a point where the softmax distribution computed using logits approaches the gold label distribution.
