paper-with-me

Papers

Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting

2019-06-01 · NAACL 2019 6 · J. Edward Hu, Huda Khayrallah, Ryan Culkin, Patrick Xia, Tongfei Chen, Matt Post, Benjamin Van Durme

Lexically-constrained sequence decoding allows for explicit positive or negative phrase-based constraints to be placed on target output strings in generation tasks such as machine translation or monolingual text rewriting. We describe vectorized dynamic beam allocation, which extends work in lexically-constrained decoding to work with batching, leading to a five-fold improvement in throughput when working with positive constraints. Faster decoding enables faster exploration of constraint strategies: we illustrate this via data augmentation experiments with a monolingual rewriter applied to the tasks of natural language inference, question answering and machine translation, showing improvements in all three.

📄 PDF Abstract BibTeX

Code (1)

awslabs/sockeye 공식 구현 mxnet

Tasks

Data AugmentationMachine TranslationNatural Language InferenceQuestion AnsweringTranslation

Similar Papers 제목 키워드 기반

ParaBank: Monolingual Bitext Generation and Sentential Paraphrasing via Lexically-constrained Neural Machine Translation

2019-01-11 · J. Edward Hu, Rachel Rudinger, Matt Post, Benjamin Van Durme

We present ParaBank, a large-scale English paraphrase dataset that surpasses prior work in both quantity and quality. Following the approach of ParaNMT, we train a Czech-English neural machine translation (NMT) system to…

DiversityMachine TranslationNMTSemantic Similarity+4

Negative Lexically Constrained Decoding for Paraphrase Generation

2019-07-01 · ACL 2019 7 · Tomoyuki Kajiwara

Paraphrase generation can be regarded as monolingual translation. Unlike bilingual machine translation, paraphrase generation rewrites only a limited portion of an input sentence. Hence, previous methods based on machine…

Machine TranslationParaphrase GenerationSentenceText Simplification+1

Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation

2018-04-18 · NAACL 2018 6 · Matt Post, David Vilar

The end-to-end nature of neural machine translation (NMT) removes many ways of manually guiding the translation process that were available in older paradigms. Recent work, however, has introduced a new capability: lexic…

Machine TranslationNMTTranslation

Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding

2021-11-16 · ACL ARR September 2021 9 · Anonymous

Online alignment in machine translation refers to the task of aligning a target word to a source word when the target sequence has only been partially decoded. Good online alignments facilitate important applications suc…

Machine TranslationTranslation

Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding

2022-04-02 · ACL 2022 5 · Soumya Chatterjee, Sunita Sarawagi, Preethi Jyothi

Online alignment in machine translation refers to the task of aligning a target word to a source word when the target sequence has only been partially decoded. Good online alignments facilitate important applications suc…

Machine TranslationTranslation