LISN @ WMT 2021
This paper describes LISN’s submissions to two shared tasks at WMT’21. For the biomedical translation task, we have developed resource-heavy systems for the English-French language pair, using both out-of-domain and in-domain corpora. The target genre for this task (scientific abstracts) corresponds to texts that often have a standardized structure. Our systems attempt to take this structure into account using a hierarchical system of sentence-level tags. Translation systems were also prepared for the News task for the French-German language pair. The challenge was to perform unsupervised adaptation to the target domain (financial news). For this, we explored the potential of retrieval-based strategies, where sentences that are similar to test instances are used to prime the decoder.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderRetrievalSentenceTranslationSimilar Papers 제목 키워드 기반
Development of the Listening in Spatialized Noise-Sentences (LiSN-S) Test in Brazilian Portuguese: Presentation Software, Speech Stimuli, and Sentence Equivalence
The Listening in Spatialized Noise Sentences (LiSN-S) is a test to evaluate auditory spatial processing currently only available in the English language. It produces a three-dimensional auditory environment under headpho…
SentenceCritical analysis on efficiency and noise reduction methodologies of a switch mode power supply using LISN topology
This critical analysis offers a comprehensive overview of the efficiency and noise reduction methodologies applied in switch mode power supplies (SMPSs) and the emerging trends in the field. The study acknowledges that p…
LISN: Language-Instructed Social Navigation with VLM-based Controller Modulating
Towards human-robot coexistence, socially aware navigation is significant for mobile robots. Yet existing studies on this area focus mainly on path efficiency and pedestrian collision avoidance, which are essential but r…
Instruction FollowingScene UnderstandingCollision AvoidanceDetecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality
Recent work has shown that deep generative models can assign higher likelihood to out-of-distribution data sets than to their training data (Nalisnick et al., 2019; Choi et al., 2019). We posit that this phenomenon is ca…
Infrared Image Super-Resolution via Lightweight Information Split Network
Single image super-resolution (SR) is an established pixel-level vision task aimed at reconstructing a high-resolution image from its degraded low-resolution counterpart. Despite the notable advancements achieved by leve…
Image ReconstructionImage Super-ResolutionInfrared image super-resolutionSuper-Resolution