paper-with-me

홈 › Papers

Gloss Alignment Using Word Embeddings

2023-08-08 · Harry Walsh, Ozge Mercanoglu Sincan, Ben Saunders, Richard Bowden

Capturing and annotating Sign language datasets is a time consuming and costly process. Current datasets are orders of magnitude too small to successfully train unconstrained \acf{slt} models. As a result, research has turned to TV broadcast content as a source of large-scale training data, consisting of both the sign language interpreter and the associated audio subtitle. However, lack of sign language annotation limits the usability of this data and has led to the development of automatic annotation techniques such as sign spotting. These spottings are aligned to the video rather than the subtitle, which often results in a misalignment between the subtitle and spotted signs. In this paper we propose a method for aligning spottings with their corresponding subtitles using large spoken language models. Using a single modality means our method is computationally inexpensive and can be utilized in conjunction with existing alignment techniques. We quantitatively demonstrate the effectiveness of our method on the \acf{mdgs} and \acf{bobsl} datasets, recovering up to a 33.22 BLEU-1 score in word alignment.

📄 PDF Abstract BibTeX arXiv:2308.04248

Code (0)

등록된 구현이 없습니다.

Tasks

Word AlignmentWord Embeddings

Similar Papers 제목 키워드 기반

Vec2Gloss: definition modeling leveraging contextualized vectors with Wordnet gloss

2023-05-29 · Yu-Hsiang Tseng, Mao-Chang Ku, Wei-Ling Chen, Yu-Lin Chang 외

Contextualized embeddings are proven to be powerful tools in multiple NLP tasks. Nonetheless, challenges regarding their interpretability and capability to represent lexical semantics still remain. In this paper, we prop…

Massively Multilingual Joint Segmentation and Glossing

2026-01-16 · Michael Ginn, Lindia Tjuatja, Enora Rice, Ali Marashian 외 arxiv

Automated interlinear gloss prediction with neural networks is a promising approach to accelerate language documentation efforts. However, while state-of-the-art models like GlossLM achieve high scores on glossing benchm…

Improving Contextual Representation with Gloss Regularized Pre-training

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Though achieving impressive results on many NLP tasks, the BERT-like masked language models (MLM) encounter the discrepancy between pre-training and inference. In light of this gap, we investigate the contextual represen…

Semantic SimilaritySemantic Textual SimilaritySentenceSTS+1

Improving Contextual Representation with Gloss Regularized Pre-training

2022-05-13 · Findings (NAACL) 2022 7 · Yu Lin, Zhecheng An, Peihao Wu, Zejun Ma

Though achieving impressive results on many NLP tasks, the BERT-like masked language models (MLM) encounter the discrepancy between pre-training and inference. In light of this gap, we investigate the contextual represen…

Semantic SimilaritySemantic Textual SimilaritySentenceSTS+1

BL.Research at SemEval-2022 Task 1: Deep networks for Reverse Dictionary using embeddings and LSTM autoencoders

2022-07-01 · SemEval (NAACL) 2022 7 · Nihed Bendahman, Julien Breton, Lina Nicolaieff, Mokhtar Boumedyen Billami 외

This paper describes our two deep learning systems that competed at SemEval-2022 Task 1 “CODWOE: Comparing Dictionaries and WOrd Embeddings”. We participated in the subtask for the reverse dictionary which consists in ge…

PositionReverse DictionaryWord Embeddings