An official website of the United States government
Sign words are the building blocks of any sign language. In this work, we present wSignGen, a word-conditioned 3D American Sign Language (ASL) generation model dedicated to synthesizing realistic and grammatically accurate motion sequences for sign words. Our approach leverages a transformer-based diffusion model, trained on a curated dataset of 3D motion meshes from word-level ASL videos. By integrating CLIP, wSignGen offers two advantages: image-based generation, which is particularly useful for children learning sign language but not yet able to read, and the ability to generalize to unseen synonyms. Experiments demonstrate that wSignGen significantly outperforms the baseline model in the task of sign word generation. Moreover, human evaluation experiments show that wSignGen can generate high-quality, grammatically correct ASL signs effectively conveyed through 3D avatars.
more »
« less
Revisiting Simple Neural Probabilistic Language Models
Recent progress in language modeling has been driven not only by advances in neural architectures, but also through hardware and optimization improvements. In this paper, we revisit the neural probabilistic language model (NPLM) of Bengio et al. (2003), which simply concatenates word embeddings within a fixed window and passes the result through a feed-forward network to predict the next word. When scaled up to modern hardware, this model (despite its many limitations) performs much better than expected on word-level language model benchmarks. Our analysis reveals that the NPLM achieves lower perplexity than a baseline Transformer with short input contexts but struggles to handle long-term dependencies. Inspired by this result, we modify the Transformer by replacing its first self-attention layer with the NPLM’s local concatenation layer, which results in small but consistent perplexity decreases across three word-level language modeling datasets.
more »
« less
- Award ID(s):
- 1955567
- PAR ID:
- 10254048
- Date Published:
- Journal Name:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Page Range / eLocation ID:
- 5181 to 5188
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The rapidly increasing size of deep-learning models has renewed interest in alternatives to digital-electronic computers as a means to dramatically reduce the energy cost of running state-of-the-art neural networks. Optical matrix-vector multipliers are best suited to performing computations with very large operands, which suggests that large Transformer models could be a good target for them. In this paper, we investigate---through a combination of simulations and experiments on prototype optical hardware---the feasibility and potential energy benefits of running Transformer models on future optical accelerators that perform matrix-vector multiplication. We use simulations, with noise models validated by small-scale optical experiments, to show that optical accelerators for matrix-vector multiplication should be able to accurately run a typical Transformer architecture model for language processing. We demonstrate that optical accelerators can achieve the same (or better) perplexity as digital-electronic processors at 8-bit precision, provided that the optical hardware uses sufficiently many photons per inference, which translates directly to a requirement on optical energy per inference. We studied numerically how the requirement on optical energy per inference changes as a function of the Transformer width $$d$$ and found that the optical energy per multiply--accumulate (MAC) scales approximately as $$\frac{1}{d}$$, giving an asymptotic advantage over digital systems. We also analyze the total system energy costs for optical accelerators running Transformers, including both optical and electronic costs, as a function of model size. We predict that well-engineered, large-scale optical hardware should be able to achieve a $$100 \times$$ energy-efficiency advantage over current digital-electronic processors in running some of the largest current Transformer models, and if both the models and the optical hardware are scaled to the quadrillion-parameter regime, optical accelerators could have a $$>8,000\times$$ energy-efficiency advantage. Under plausible assumptions about future improvements to electronics and Transformer quantization techniques (5× cheaper memory access, double the digital--analog conversion efficiency, and 4-bit precision), we estimate that the energy advantage for optical processors versus electronic processors operating at 300~fJ/MAC could grow to $$>100,000\times$$.more » « less
-
Neural language models (LMs) such as GPT-2 estimate the probability distribution over the next word by a softmax over the vocabulary. The softmax layer produces the distribution based on the dot products of a single hidden state and the embeddings of words in the vocabulary. However, we discover that this single hidden state cannot produce all probability distributions regardless of the LM size or training data size because the single hidden state embedding cannot be close to the embeddings of all the possible next words simultaneously when there are other interfering word embeddings between them. In this work, we demonstrate the importance of this limitation both theoretically and practically. Our work not only deepens our understanding of softmax bottleneck and mixture of softmax (MoS) but also inspires us to propose multi-facet softmax (MFS) to address the limitations of MoS. Extensive empirical analyses confirm our findings and show that against MoS, the proposed MFS achieves two-fold improvements in the perplexity of GPT-2 and BERT.more » « less
-
Pre-trained language models (PLMs) aim to learn universal language representations by conducting self-supervised training tasks on large-scale corpora. Since PLMs capture word semantics in different contexts, the quality of word representations highly depends on word frequency, which usually follows a heavy-tailed distributions in the pre-training corpus. Therefore, the embeddings of rare words on the tail are usually poorly optimized. In this work, we focus on enhancing language model pre-training by leveraging definitions of the rare words in dictionaries (e.g., Wiktionary). To incorporate a rare word definition as a part of input, we fetch its definition from the dictionary and append it to the end of the input text sequence. In addition to training with the masked language modeling objective, we propose two novel self-supervised pre-training tasks on word and sentence-level alignment between input text sequence and rare word definitions to enhance language modeling representation with dictionary. We evaluate the proposed Dict-BERT model on the language understanding benchmark GLUE and eight specialized domain benchmark datasets. Extensive experiments demonstrate that Dict-BERT can significantly improve the understanding of rare words and boost model performance on various NLP downstream tasks.more » « less
-
Humans convey their intentions through the usage of both verbal and nonverbal behaviors during face-to-face communication. Speaker intentions often vary dynamically depending on different nonverbal contexts, such as vocal patterns and facial expressions. As a result, when modeling human language, it is essential to not only consider the literal meaning of the words but also the nonverbal contexts in which these words appear. To better model human language, we first model expressive nonverbal representations by analyzing the fine-grained visual and acoustic patterns that occur during word segments. In addition, we seek to capture the dynamic nature of nonverbal intents by shifting word representations based on the accompanying nonverbal behaviors. To this end, we propose the Recurrent Attended Variation Embedding Network (RAVEN) that models the fine-grained structure of nonverbal subword sequences and dynamically shifts word representations based on nonverbal cues. Our proposed model achieves competitive performance on two publicly available datasets for multimodal sentiment analysis and emotion recognition. We also visualize the shifted word representations in different nonverbal contexts and summarize common patterns regarding multimodal variations of word representations.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.18653/v1/2021.naacl-main.407
