paper-with-me

Papers

Discrete Structural Planning for Generating Diverse Translations

2018-09-27 · Raphael Shu, Hideki Nakayama

Planning is important for humans when producing complex languages, which is a missing part in current language generation models. In this work, we add a planning phase in neural machine translation to control the global sentence structure ahead of translation. Our approach learns discrete structural representations to encode syntactic information of target sentences. During translation, we can either let beam search to choose the structural codes automatically or specify the codes manually. The word generation is then conditioned on the selected discrete codes. Experiments show that the translation performance remains intact by learning the codes to capture pure structural variations. Through structural planning, we are able to control the global sentence structure by manipulating the codes. By evaluating with a proposed structural diversity metric, we found that the sentences sampled using different codes have much higher diversity scores. In qualitative analysis, we demonstrate that the sampled paraphrase translations have drastically different structures.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityMachine TranslationSentenceText GenerationTranslation

Similar Papers 제목 키워드 기반

Discrete Structural Planning for Neural Machine Translation

2018-05-23 · Anonymous

Structural planning is important for producing long sentences, which is a missing part in current language generation models. In this work, we add a planning phase in neural machine translation to control the coarse stru…

Machine TranslationSentenceText GenerationTranslation

Discrete Structural Planning for Neural Machine Translation

2018-08-14 · Raphael Shu, Hideki Nakayama

Structural planning is important for producing long sentences, which is a missing part in current language generation models. In this work, we add a planning phase in neural machine translation to control the coarse stru…

Machine TranslationSentenceText GenerationTranslation

Bridging the Gap between Structural and Semantic Similarity in Diverse Planning

2023-10-02 · Mustafa F. Abdelwahed, Joan Espasa, Alice Toniolo, Ian P. Gent

Diverse planning is the problem of finding multiple plans for a given problem specification, which is at the core of many real-world applications. For example, diverse planning is a critical piece for the efficiency of p…

Semantic SimilaritySemantic Textual Similarity

Discrete Autoencoders for Sequence Models

2018-01-29 · ICLR 2018 1 · Łukasz Kaiser, Samy Bengio

Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models…

Language ModelingLanguage ModellingMachine TranslationTranslation

Generating Diverse Translation by Manipulating Multi-Head Attention

2019-11-21 · Zewei Sun, Shu-Jian Huang, Hao-Ran Wei, Xin-yu Dai 외

Transformer model has been widely used on machine translation tasks and obtained state-of-the-art results. In this paper, we report an interesting phenomenon in its encoder-decoder multi-head attention: different attenti…

Data AugmentationDecoderDiversityMachine Translation+3