CUED@WMT19:EWC\&LMs

2019-08-01 · WS 2019 8 · Felix Stahlberg, Danielle Saunders, Adri{\`a} de Gispert, Bill Byrne

Two techniques provide the fabric of the Cambridge University Engineering Department{'}s (CUED) entry to the WMT19 evaluation campaign: elastic weight consolidation (EWC) and different forms of language modelling (LMs). We report substantial gains by fine-tuning very strong baselines on former WMT test sets using a combination of checkpoint averaging and EWC. A sentence-level Transformer LM and a document-level LM based on a modified Transformer architecture yield further gains. As in previous years, we also extract n-gram probabilities from SMT lattices which can be seen as a source-conditioned n-gram LM.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModellingSentence

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

EWC The methon to overcome catastrophic forgetting in neural network while continual learning

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Position-Wise Feed-Forward Layer 설명 없음

Residual Connection 설명 없음

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Mapping de l'espace spectral vers l'espace visuel de la parole : les voyelles du fran\ccais en langue fran\ccaise parl\'ee compl\'et\'ee (Mapping of the spectral space to the visual speech space for French vowels cued in Cued Speech) [in French]

2012-06-01 · JEPTALNRECITAL 2012 6 · Zuheng Ming, Gang Feng, Denis Beautemps

Cued-Agent: A Collaborative Multi-Agent System for Automatic Cued Speech Recognition

2025-08-01 · Guanjie Huang, Danny H. K. Tsang, Shan Yang, Guangzhi Lei 외 arxiv

Cued Speech (CS) is a visual communication system that combines lip-reading with hand coding to facilitate communication for individuals with hearing impairments. Automatic CS Recognition (ACSR) aims to convert CS hand g…

Speech Recognition

Cued Speech Generation Leveraging a Pre-trained Audiovisual Text-to-Speech Model

2025-01-08 · Sanjana Sankar, Martin Lenglet, Gerard Bailly, Denis Beautemps 외

This paper presents a novel approach for the automatic generation of Cued Speech (ACSG), a visual communication system used by people with hearing impairment to better elicit the spoken language. We explore transfer lear…

text-to-speech Text to Speech Transfer Learning

Robust Small-Scale Pedestrian Detection With Cued Recall via Memory Learning

2021-01-01 · ICCV 2021 10 · Jung Uk Kim, Sungjune Park, Yong Man Ro

Although the visual appearances of small-scale objects are not well observed, humans can recognize them by associating the visual cues of small objects from their memorized appearance. It is called cued recall. In th…

Pedestrian Detection

Visual communication of object concepts at different levels of abstraction

2021-06-05 · Justin Yang, Judith E. Fan

People can produce drawings of specific entities (e.g., Garfield), as well as general categories (e.g., "cat"). What explains this ability to produce such varied drawings of even highly familiar object concepts? We hypot…