| Challenge: | A challenge in on-device text classification is to build highly accurate models that fit in small memory footprint and have low latency. |
| Approach: | They propose an on-device neural network which learns compact projection vectors from raw text using structured and context-dependent partition projections. |
| Outcome: | The proposed model outperforms baseline models and surpasses RNN, CNN and BiLSTM models on dialog act and intent prediction. |
Similar Papers
Self-Governing Neural Networks for On-Device Short Text Classification (D18-1)
Copied to clipboard
| Challenge: | Existing deep neural networks have a tiny memory footprint and low computational capacity compared to high performance computing systems such as CPUs, GPUs and TPUs on the cloud. |
| Approach: | They propose on-device self-governing neural networks which learn compact projection vectors with local sensitive hashing. |
| Outcome: | The proposed models perform better on dialog act classification tasks while maintaining high accuracy. |
Self-Governing Neural Networks for On-Device Short Text Classification (D18-1)
Copied to clipboard
| Challenge: | Existing deep neural networks have a tiny memory footprint and low computational capacity compared to high performance computing systems such as CPUs, GPUs and TPUs on the cloud. |
| Approach: | They propose on-device self-governing neural networks which learn compact projection vectors with local sensitive hashing. |
| Outcome: | The proposed models perform better on dialog act classification tasks while maintaining high accuracy. |
ProSeqo: Projection Sequence Networks for On-Device Text Classification (D19-1)
Copied to clipboard
| Challenge: | ProSeqo is a novel on-device sequence model for text classification . it uses dynamic recurrent projections without the need to store or look up pre-trained embeddings. |
| Approach: | They propose a novel on-device sequence model for text classification using recurrent projections that uses dynamic recursion projections without the need to store or look up any pre-trained embeddings. |
| Outcome: | The proposed model outperforms state-of-the-art neural and on-device approaches for short and long text classification tasks while maintaining low memory footprint and high accuracy. |
Fast Word Predictor for On-Device Application (2020.coling-demos)
Copied to clipboard
| Challenge: | a proposed word prediction model is developed for a chat application serving more than 100 million users. |
| Approach: | They propose a fast word predictor that reduces memory size and inference time on mobile devices. |
| Outcome: | The proposed model reduces memory size and inference time on a mobile device compared with a standard neural network . it achieves robust performance by learning on large text corpora and is available on microsoft's chat app . |
PRADO: Projection Attention Networks for Document Classification On-Device (D19-1)
Copied to clipboard
| Challenge: | Recent advances in deep learning have improved the performance of on-device neural networks for long text classification. |
| Approach: | They propose a projection attention neural network PRADO that combines trainable projections with attention and convolutions to train tiny neural networks that achieve high performance on multiple long document classification tasks. |
| Outcome: | The proposed model achieves high performance on multiple long document classification tasks while maintaining compact size. |
On-Device Text Representations Robust To Misspellings via Projections (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent advances in Locality-Sensitive Hashing (LSH)-based projection networks have demonstrated state-of-the-art performance in various classification tasks without explicit word embedding lookup tables by computing on-the fly text representations. |
| Approach: | They propose to use locality-sensitive hashing to compute on-the-fly text representations without explicit word embedding tables. |
| Outcome: | The proposed classifiers are more robust to common misspellings and perturbations of the input text compared to biLSTMs and fine-tuned BERT based methods. |
On-Device Neural Language Model Based Word Prediction (C18-2)
Copied to clipboard
| Challenge: | Currently, on-device keyboards have limited memory and response time for word prediction . a proposed on-device neural language model based word prediction method is available for mobile devices . |
| Approach: | They propose an on-device neural language model based word prediction method that optimizes run-time memory and provides a real-time prediction environment. |
| Outcome: | The proposed model outperforms existing methods for word prediction in keystroke savings and word prediction rate and has been commercialized. |
On-device System of Compositional Multi-tasking in Large Language Models (2025.emnlp-industry)
Copied to clipboard
Ondrej Bohdal, Konstantinos Theodosiadis, Asterios Mpatziakas, Dimitrios Filippidis, Iro Spyrou, Christos Zonios, Anastasios Drosou, Dimosthenis Ioannidis, Kyenghun Lee, Jijoong Moon, Hyeonmok Ko, Mete Ozay, Umberto Michieli
| Challenge: | Existing approaches to generative AI for large language models struggle when executing complex tasks simultaneously. |
| Approach: | They propose a novel approach tailored specifically for compositional multi-tasking scenarios . they add a learnable projection layer on top of the combined summarization and translation adapters. |
| Outcome: | The proposed approach performs well and is fast in both cloud-based and on-device implementations. |
Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging (D18-1)
Copied to clipboard
| Challenge: | Low-resource languages lack manual annotated data to learn basic models such as part-of-speech (POS) taggers. |
| Approach: | They propose a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision in a uniform framework. |
| Outcome: | The proposed model scales to hundreds of low-resource languages without access to gold annotated data. |
Gated Multi-Task Network for Text Classification (N18-2)
Copied to clipboard
| Challenge: | Existing approaches to multitask learning share the features without distinguishing the usefulness of the features, generating undesired interference between tasks. |
| Approach: | They propose to introduce a gate mechanism into multi-task CNN and propose a new gated sharing unit which can filter the feature flows between tasks and greatly reduce the interference. |
| Outcome: | The proposed approach can learn selection rules automatically and gain a great improvement over strong baselines. |