paper-with-me

Papers

Multiple Pivot Languages and Strategic Decoder Initialization Helps Neural Machine Translation

2022-10-01 · loresmt (COLING) 2022 10 · Shivam Mhaskar, Pushpak Bhattacharyya

In machine translation, a pivot language can be used to assist the source to target translation model. In pivot-based transfer learning, the source to pivot and the pivot to target models are used to improve the performance of the source to target model. This technique works best when both source-pivot and pivot-target are high resource language pairs and the source-target is a low resource language pair. But in some cases, such as Indic languages, the pivot to target language pair is not a high resource one. To overcome this limitation, we use multiple related languages as pivot languages to assist the source to target model. We show that using multiple pivot languages gives 2.03 BLEU and 3.05 chrF score improvement over the baseline model. We show that strategic decoder initialization while performing pivot-based transfer learning with multiple pivot languages gives a 3.67 BLEU and 5.94 chrF score improvement over the baseline model.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMachine TranslationTransfer LearningTranslation

Similar Papers 제목 키워드 기반

A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation

2016-06-15 · COLING 2016 12 · Amrita Saha, Mitesh M. Khapra, Sarath Chandar, Janarthanan Rajendran 외

Interlingua based Machine Translation (MT) aims to encode multiple languages into a common linguistic representation and then decode sentences in multiple target languages from this representation. In this work we explor…

DecoderMachine TranslationTransliteration

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

2019-09-20 · IJCNLP 2019 11 · Yunsu Kim, Petre Petrov, Pavel Petrushkov, Shahram Khadivi 외

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-tar…

DecoderMachine TranslationNMTTransfer Learning+2

Utilizing Lexical Similarity between Related, Low-resource Languages for Pivot-based SMT

2017-02-23 · IJCNLP 2017 11 · Anoop Kunchukuttan, Maulik Shah, Pradyot Prakash, Pushpak Bhattacharyya

We investigate pivot-based translation between related languages in a low resource, phrase-based SMT setting. We show that a subword-level pivot-based SMT model using a related pivot language is substantially better than…

Translation

Enhancing Indic Handwritten Text Recognition Using Global Semantic Information

2022-12-15 · Ajoy Mondal, C. V. Jawahar

Handwritten Text Recognition (HTR) is more interesting and challenging than printed text due to uneven variations in the handwriting style of the writers, content, and time. HTR becomes more challenging for the Indic lan…

DecoderHandwritten Text RecognitionHTRLanguage Modelling

SteerEval: Inference-time Interventions Strengthen Multilingual Generalization in Neural Summarization Metrics

2026-01-22 · Silvia Casola, Ryan Soh-Eun Shim, Felicia Körner, Yuchen Mao 외 arxiv

An increasing body of work has leveraged multilingual language models for Natural Language Generation tasks such as summarization. A major empirical bottleneck in this area is the shortage of accurate and robust evaluati…