Sub-word segmentation is an essential pre-processing step for Neural Mac...
Whisper is one of the recent state-of-the-art multilingual speech recogn...
In scholarly documents, figures provide a straightforward way of
communi...
Automatic speech translation is sensitive to speech recognition errors, ...
India has a rich linguistic landscape with languages from 4 major langua...
Large language models have demonstrated the capability to perform well o...
This study investigates machine translation between related languages i....
The language-independency of encoded representations within multilingual...
This paper studies the impact of layer normalization (LayerNorm) on zero...
Adapters have been positioned as a parameter-efficient fine-tuning (PEFT...
Knowledge distillation (KD) is a well-known method for compressing neura...
The rapid growth of machine translation (MT) systems has necessitated
co...
There have been several studies on the correlation between human ratings...
In this paper, we describe MorisienMT, a dataset for benchmarking machin...
Word alignment has proven to benefit many-to-many neural machine transla...
We participated in the mean opinion score (MOS) prediction challenge, 20...
Cognates are variants of the same lexical form across different language...
In this paper we present IndicBART, a multilingual, sequence-to-sequence...
In this paper we present our open-source neural machine translation (NMT...
In deep neural network modeling, the most common practice is to stack a
...
Parallel corpora are indispensable for training neural machine translati...
Neural machine translation (NMT) models are typically trained using a so...
Neural machine translation (NMT) needs large parallel corpora for
state-...
We propose and evaluate a novel procedure for training multiple Transfor...
Sequence-to-sequence (S2S) pre-training using large monolingual data is ...
We present a survey on multilingual neural machine translation (MNMT), w...
Lectures translation is a case of spoken language translation and there ...
This paper proposes a novel procedure for training an encoder-decoder ba...
This paper proposes a novel multilingual multistage fine-tuning approach...
In this paper, we propose two novel methods for domain adaptation for th...
We present a survey on multilingual neural machine translation (MNMT), w...
In Neural Machine Translation (NMT), the most common practice is to stac...
Multilinguality is gradually becoming ubiquitous in the sense that more ...
In this paper, we propose a novel and elegant solution to "Multi-Source
...
In this paper, we propose a novel domain adaptation method named "mixed ...