Machine Translation Aided Bilingual Data-to-Text Generation and Semantic Parsing
We present a system for bilingual Data-ToText Generation and Semantic Parsing. We use a text-to-text generator to learn a single model that works for both languages on each of the tasks. The model is aided by machine translation during both pre-training and fine-tuning. We evaluate the system on WebNLG 2020 data 1 , which consists of RDF triples in English and natural language sentences in English and Russian for both the tasks. We achieve considerable gains over monolingual models, especially on unseen relations and Russian.
Code (0)
등록된 구현이 없습니다.
Tasks
Data-to-Text GenerationMachine TranslationSemantic ParsingText GenerationTranslationSimilar Papers 제목 키워드 기반
Mining Bilingual Word Pairs from Comparable Corpus using Apache Spark Framework
Bilingual dictionaries are essential resources in many areas of natural language processing tasks, but resource-scarce and less popular language pairs rarely have such. Efficient automatic methods for inducting bilingual…
Machine TranslationNMTTranslationMultiple Captions Embellished Multilingual Multi-Modal Neural Machine Translation
Neural machine translation based on bilingual text with limited training data suffers from lexical diversity, which lowers the rare word translation accuracy and reduces the generalizability of the translation system. In…
Cross-Lingual TransferDiversityMachine TranslationTranslation+1Ranking suggestions for black-box interactive translation prediction systems with multilayer perceptrons
The objective of interactive translation prediction (ITP), a paradigm of computer-aided translation, is to assist professional translators by offering context-based computer-generated suggestions as they type. While most…
Machine TranslationTranslationBuilding Multiword Expressions Bilingual Lexicons for Domain Adaptation of an Example-Based Machine Translation System
We describe in this paper a hybrid ap-proach to build automatically bilingual lexicons of Multiword Expressions (MWEs) from parallel corpora. We more specifically investigate the impact of using a domain-specific bilingu…
Domain AdaptationInformation RetrievalMachine TranslationTranslationBiTIIMT: A Bilingual Text-infilling Method for Interactive Machine Translation
Interactive neural machine translation (INMT) is able to guarantee high-quality translations by taking human interactions into account. Existing IMT systems relying on lexical constrained decoding (LCD) enable humans to …
Machine TranslationSentenceText InfillingTranslation