Search for: All records

The lexical quality hypothesis proposes that the quality of phonological, orthographic, and semantic representations impacts reading comprehension. In Study 1, we evaluated the contributions of lexical quality to reading comprehension in 97 deaf and 98 hearing adults matched for reading ability. While phonological awareness was a strong predictor for hearing readers, for deaf readers, orthographic precision and semantic knowledge, not phonology, predicted reading comprehension (assessed by two different tests). For deaf readers, the architecture of the reading system adapts by shifting reliance from (coarse-grained) phonological representations to high-quality orthographic and semantic representations. In Study 2, we examined the contribution of American Sign Language (ASL) variables to reading comprehension in 83 deaf adults. Fingerspelling (FS) and ASL comprehension skills predicted reading comprehension. We suggest that FS might reinforce orthographic-to-semantic mappings and that sign language comprehension may serve as a linguistic basis for the development of skilled reading in deaf signers.

 

Sign language recognition and translation technologies have the potential to increase access and inclusion of deaf signing communities, but research progress is bottlenecked by a lack of representative data. We introduce a new resource for American Sign Language (ASL) modeling, the Sem-Lex Benchmark. The Benchmark is the current largest of its kind, consisting of over 84k videos of isolated sign productions from deaf ASL signers who gave informed consent and received compensation. Human experts aligned these videos with other sign language resources including ASL-LEX, SignBank, and ASL Citizen, enabling useful expansions for sign and phonological feature recognition. We present a suite of experiments which make use of the linguistic information in ASL-LEX, evaluating the practicality and fairness of the Sem-Lex Benchmark for isolated sign recognition (ISR). We use an SL-GCN model to show that the phonological features are recognizable with 85% accuracy, and that they are effective as an auxiliary target to ISR. Learning to recognize phonological features alongside gloss results in a 6% improvement for few-shot ISR accuracy and a 2% improvement for ISR accuracy overall. Instructions for downloading the data can be found at https://github.com/leekezar/SemLex. 

Like speech, signs are composed of discrete, recombinable features called phonemes. Prior work shows that models which can recognize phonemes are better at sign recognition, motivating deeper exploration into strategies for modeling sign language phonemes. In this work, we learn graph convolution networks to recognize the sixteen phoneme “types” found in ASL-LEX2.0. Specifically, we explore how learning strategies like multi-task and curriculum learning can leverage mutually useful information between phoneme types to facilitate the remodeling of sign language phonemes. Results on the Sem-Lex Benchmark show that curriculum learning yields an average accuracy of 87% across all phoneme types, outperforming fine-tuning and multi-task strategies for most phonemetypes. 

We use insights from research on American Sign Language (ASL) phonology to train models for isolated sign language recognition (ISLR), a step towards automatic sign language understanding. Our key insight is to explicitly recognize the role of phonology in sign production to achieve more accurate ISLR than existing work which does not consider sign language phonology. We train ISLR models that take in pose estimations of a signer producing a single sign to predict not only the sign but additionally its phonological characteristics, such as the handshape. These auxiliary predictions lead to a nearly 9% absolute gain in sign recognition accuracy on the WLASL benchmark, with consistent improvements in ISLR regardless of the underlying prediction model architecture. This work has the potential to accelerate linguistic research in the domain of signed languages and reduce communication barriers between deaf and hearing people. 

Letter recognition plays an important role in reading and follows different phases of processing, from early visual feature detection to the access of abstract letter representations. Deaf ASL–English bilinguals experience orthography in two forms: English letters and fingerspelling. However, the neurobiological nature of fingerspelling representations, and the relationship between the two orthographies, remains unexplored. We examined the temporal dynamics of single English letter and ASL fingerspelling font processing in an unmasked priming paradigm with centrally presented targets for 200 ms preceded by 100 ms primes. Event-related brain potentials were recorded while participants performed a probe detection task. Experiment 1 examined English letter-to-letter priming in deaf signers and hearing non-signers. We found that English letter recognition is similar for deaf and hearing readers, extending previous findings with hearing readers to unmasked presentations. Experiment 2 examined priming effects between English letters and ASL fingerspelling fonts in deaf signers only. We found that fingerspelling fonts primed both fingerspelling fonts and English letters, but English letters did not prime fingerspelling fonts, indicating a priming asymmetry between letters and fingerspelling fonts. We also found an N400-like priming effect when the primes were fingerspelling fonts which might reflect strategic access to the lexical names of letters. The studies suggest that deaf ASL–English bilinguals process English letters and ASL fingerspelling differently and that the two systems may have distinct neural representations. However, the fact that fingerspelling fonts can prime English letters suggests that the two orthographies may share abstract representations to some extent. 

Picture-naming tasks provide critical data for theories of lexical representation and retrieval and have been performed successfully in sign languages. However, the specific influences of lexical or phonological factors and stimulus properties on sign retrieval are poorly understood. To examine lexical retrieval in American Sign Language (ASL), we conducted a timed picture-naming study using 524 pictures (272 objects and 251 actions). We also compared ASL naming with previous data for spoken English for a subset of 425 pictures. Deaf ASL signers named object pictures faster and more consistently than action pictures, as previously reported for English speakers. Lexical frequency, iconicity, better name agreement, and lower phonological complexity each facilitated naming reaction times (RT)s. RTs were also faster for pictures named with shorter signs (measured by average response duration). Target name agreement was higher for pictures with more iconic and shorter ASL names. The visual complexity of pictures slowed RTs and decreased target name agreement. RTs and target name agreement were correlated for ASL and English, but agreement was lower for ASL, possibly due to the English bias of the pictures. RTs were faster for ASL, which we attributed to a smaller lexicon. Overall, the results suggest that models of lexical retrieval developed for spoken languages can be adopted for signed languages, with the exception that iconicity should be included as a factor. The open-source picture-naming data set for ASL serves as an important, first-of-its-kind resource for researchers, educators, or clinicians for a variety of research, instructional, or assessment purposes. 

Abstract ASL-LEX is a publicly available, large-scale lexical database for American Sign Language (ASL). We report on the expanded database (ASL-LEX 2.0) that contains 2,723 ASL signs. For each sign, ASL-LEX now includes a more detailed phonological description, phonological density and complexity measures, frequency ratings (from deaf signers), iconicity ratings (from hearing non-signers and deaf signers), transparency (“guessability”) ratings (from non-signers), sign and videoclip durations, lexical class, and more. We document the steps used to create ASL-LEX 2.0 and describe the distributional characteristics for sign properties across the lexicon and examine the relationships among lexical and phonological properties of signs. Correlation analyses revealed that frequent signs were less iconic and phonologically simpler than infrequent signs and iconic signs tended to be phonologically simpler than less iconic signs. The complete ASL-LEX dataset and supplementary materials are available at https://osf.io/zpha4/ and an interactive visualization of the entire lexicon can be accessed on the ASL-LEX page: http://asl-lex.org/.