| Challenge: | SYSTRAN participates in Document-level generation and trans-lation (DGT) task . data-to-text generation tasks are difficult because of the content selection and text generation data. |
| Approach: | They propose a Transformer-based datato-text generation model which jointly learns content selection and text generation. |
| Outcome: | The proposed model outperforms current state-of-the-art system on BLEU, content selection precision and content ordering metics. |
Similar Papers
Naver Labs Europe’s Systems for the Document-Level Generation and Translation Task at WNGT 2019 (D19-56)
Copied to clipboard
| Challenge: | Recent advances in machine translation and natural language generation have created many challenges in this field especially when context is considered. |
| Approach: | They propose to leverage data from machine translation and natural language generation tasks to do transfer learning between MT, NLG and MT with source-side metadata. |
| Outcome: | The proposed approach outperforms the previous state-of-the-art on the Rotowire NLG task. |
Findings of the Third Workshop on Neural Generation and Translation (D19-56)
Copied to clipboard
Hiroaki Hayashi, Yusuke Oda, Alexandra Birch, Ioannis Konstas, Andrew Finch, Minh-Thang Luong, Graham Neubig, Katsuhito Sudoh
| Challenge: | The 3rd Workshop on Neural Machine Translation and Generation (WNGT) was held in concert with the annual conference of the Empirical Methods in Natural Language Processing (EMNLP 2019). |
| Approach: | They describe the results of the third workshop on Neural Generation and Translation held in concert with the annual conference of the Empirical Methods in Natural Language Processing (EMNLP 2019). |
| Outcome: | The results of the 3rd Workshop on Neural Machine Translation and Generation (WNGT) were summarized in Sections 3 and 4. |
SYSTRAN @ WAT 2019: Russian-Japanese News Commentary task (D19-52)
Copied to clipboard
| Challenge: | Several data sets were provided for the task, but the data was limited and the distance and richness of the language pair were very challenging. |
| Approach: | They describe the SYSTRAN neural MT systems employed for the 6th Workshop on Asian Translation (WAT) they use the neural Transformer architecture learned over the provided resources and perform synthetic data generation experiments which aim at alleviating the data scarcity problem. |
| Outcome: | The proposed systems rank first according to automatic evaluations based on the neural Transformer architecture learned over the provided resources. |
Selecting, Planning, and Rewriting: A Modular Approach for Data-to-Document Generation and Translation (D19-56)
Copied to clipboard
| Challenge: | Existing systems for document-level generation and translation are too complex to capture the complexity of the problem. |
| Approach: | They propose to adapt a large scale system trained on WMT data to a document in a different language. |
| Outcome: | The proposed system generates a textual document from structured data or a document in a different language. |
From Research to Production and Back: Ludicrously Fast Neural Machine Translation (D19-56)
Copied to clipboard
Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan, Alham Fikri Aji, Kenneth Heafield, Roman Grundkiewicz, Nikolay Bogoychev
| Challenge: | Using the dominating submissions to the previous edition of the shared task, we develop improved teacher-student training via multi-agent dual-learning and noisy backward-forward translation for Transformer-based student models. |
| Approach: | They propose to use multi-agent dual-learning and noisy backward-forward translation to improve teacher-student training for Transformer-based student models. |
| Outcome: | The proposed model outperforms submissions to the previous edition of the WNGT efficiency shared task by 4 BLEU points and 10 BLUE points respectively. |
University of Edinburgh’s submission to the Document-level Generation and Translation Shared Task (D19-56)
Copied to clipboard
| Challenge: | University of Edinburgh participated in all six tracks: NLG, MT, and MT+NLG with English and German as targeted languages. |
| Approach: | The University of Edinburgh participated in all six tracks: NLG, MT, and MT+NLG . they submitted a multilingual system based on the Content Selection and Planning model . |
| Outcome: | The University of Edinburgh participated in all six tracks with English and German as target languages. |
Guiding Neural Machine Translation with Semantic Kernels (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Empirical studies show that our approach gains approximately an improvement of 1 BLEU score on most benchmarks over the Transformer baseline. |
| Approach: | They propose to extract several semantic kernels from a source sentence to capture global semantic information. |
| Outcome: | Empirical results show that the proposed approach improves 1 BLEU score on benchmarks . it is also 1.7 times faster than previous works on average at inference time . |
CVIT’s submissions to WAT-2019 (D19-52)
Copied to clipboard
| Challenge: | In this paper, we explore multiway-models for Indian languages. |
| Approach: | They propose to use a Transformer architecture to experiment with multilingual models and methods for low-resource languages. |
| Outcome: | The proposed system is feasible in low-resource languages. |
Supervised neural machine translation based on data augmentation and improved training & inference process (D19-52)
Copied to clipboard
| Challenge: | This paper describes the neural machine translation systems for the shared translation tasks of WAT 2019 . |
| Approach: | They propose a model for translation tasks of WAT 2019 that employs a Transformer model as the baseline and a deep layer model to improve translation quality. |
| Outcome: | The proposed methods can improve translation quality over traditional statistical machine translation (SMT) The proposed models can improve the translation quality of Japanese-English and Japanese-Chinese corpus. |
The Concordia NLG Surface Realizer at SRST 2019 (D19-63)
Copied to clipboard
| Challenge: | The goal of Natural Language Generation (NLG) is to produce natural texts given structured data. |
| Approach: | They propose a model for the shallow track of the 2019 NLG Surface Realization Shared Task . they divided the problem into two sub-problems: reordering and inflecting . |
| Outcome: | The proposed model reconstructs sentences whose word order and word inflections were removed. |