Emphatic fingerspelling as code-mixing in American Sign Language

Montemurro, Kathryn; Brentari, Diane

doi:10.3765/plsa.v3i1.4357

Cited by 8 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A set of manual gestures correspond with a written orthography or phonetic system. Fingerspelling is often used to indicate names or places or new concepts from the spoken language but often have become integrated into the signed languages themselves as another linguistic strategy (Padden, 1998;Montemurro and Brentari, 2018).…”

Section: Sign Language Lingusiticsmentioning

confidence: 99%

Including Signed Languages in Natural Language Processing

Yin¹,

Moryossef²,

Hochgesang³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Signed languages are the primary means of communication for many deaf and hard of hearing individuals. Since signed languages exhibit all the fundamental linguistic properties of natural language, we believe that tools and theories of Natural Language Processing (NLP) are crucial towards its modeling. However, existing research in Sign Language Processing (SLP) seldom attempt to explore and leverage the linguistic organization of signed languages. This position paper calls on the NLP community to include signed languages as a research area with high social and scientific impact. We first discuss the linguistic properties of signed languages to consider during their modeling. Then, we review the limitations of current SLP models and identify the open challenges to extend NLP to signed languages. Finally, we urge (1) the adoption of an efficient tokenization method; (2) the development of linguistically-informed models; (3) the collection of real-world signed language data; (4) the inclusion of local signed language communities as an active and leading voice in the direction of research.

show abstract

Section: Sign Language Lingusiticsmentioning

confidence: 99%

Including Signed Languages in Natural Language Processing

Yin¹,

Moryossef²,

Hochgesang³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

show abstract

“…As in prior work on action localization [27], we train a detection network that takes as input both the image appearance and optical flow, represented as a motion vector for every pixel computed from two neighboring frames [28]. 5 For the detection network, we adapt the design of the Faster R-CNN object detector [30]. As in [30], the detector is based on an ImageNet-pretrained VGG-16 network [31,32].…”

Section: Signing Hand Detectionmentioning

confidence: 99%

“…Fingerspelling is mainly used for lexical items that do not have their own ASL signs, such as proper nouns or technical terms, which are often important content words. Overall, fingerspelling accounts for 12-35% [2] of ASL, and appears frequently in technical language, colloquial conversations involving names, conversations involving current events, emphatic forms, and the context of codeswitching between ASL and English [3,4,5]. Transcribing even only the fingerspelled portions of videos in online media could add a great deal of value, since these portions are often dense in content words.…”

Section: Introductionmentioning

confidence: 99%

American Sign Language Fingerspelling Recognition in the Wild

Shi

Rio

Keane

et al. 2018

2018 IEEE Spoken Language Technology Workshop (SLT)

Self Cite

View full text Add to dashboard Cite

We address the problem of American Sign Language fingerspelling recognition "in the wild", using videos collected from websites. We introduce the largest data set available so far for the problem of fingerspelling recognition, and the first using naturally occurring video data. Using this data set, we present the first attempt to recognize fingerspelling sequences in this challenging setting. Unlike prior work, our video data is extremely challenging due to low frame rates and visual variability. To tackle the visual challenges, we train a special-purpose signing hand detector using a small subset of our data. Given the hand detector output, a sequence model decodes the hypothesized fingerspelled letter sequence. For the sequence model, we explore attention-based recurrent encoder-decoders and CTC-based approaches. As the first attempt at fingerspelling recognition in the wild, this work is intended to serve as a baseline for future work on sign language recognition in realistic conditions. We find that, as expected, letter error rates are much higher than in previous work on more controlled data, and we analyze the sources of error and effects of model variants.Index Terms-American Sign Language, fingerspelling, connectionist temporal classification, attention models 2 Two-handed fingerspelling occasionally occurs, including in our data.

show abstract

“…FS is also used for emphasis and disambiguation (Padden & LeMaster, 1985). For example, a recent video corpus study by Montemurro and Brentari (2018) found that FS was often used in focus constructions to emphasize a key point, even when an ASL sign was available. In addition, ASL contains lexicalized fingerspelled loan signs (e.g., #BANK, #OFF, #JOB), in which a fingerspelled word has undergone phonological changes (e.g., movement shortening, handshape deletion) to conform with constraints within the native sign lexicon (Brentari & Padden, 2001).…”

Section: The Role Of Fingerspelling In Semantic Fluency Tasksmentioning

confidence: 99%

Comparing Semantic Fluency in American Sign Language and English

Sehyr

Giezen

Emmorey

2018

The Journal of Deaf Studies and Deaf Education

View full text Add to dashboard Cite

This study investigated the impact of language modality and age of acquisition on semantic fluency in American Sign Language (ASL) and English. Experiment 1 compared semantic fluency performance (e.g., name as many animals as possible in 1 min) for deaf native and early ASL signers and hearing monolingual English speakers. The results showed similar fluency scores in both modalities when fingerspelled responses were included for ASL. Experiment 2 compared ASL and English fluency scores in hearing native and late ASL-English bilinguals. Semantic fluency scores were higher in English (the dominant language) than ASL (the non-dominant language), regardless of age of ASL acquisition. Fingerspelling was relatively common in all groups of signers and was used primarily for low-frequency items. We conclude that semantic fluency is sensitive to language dominance and that performance can be compared across the spoken and signed modality, but fingerspelled responses should be included in ASL fluency scores.

show abstract

Emphatic fingerspelling as code-mixing in American Sign Language

Cited by 8 publications

References 12 publications

Including Signed Languages in Natural Language Processing

Including Signed Languages in Natural Language Processing

American Sign Language Fingerspelling Recognition in the Wild

Comparing Semantic Fluency in American Sign Language and English

Contact Info

Product

Resources

About