Effidit: Your AI Writing Assistant
Not on the map. Why?
Abstract (arXiv)
In this technical report, we introduce Effidit (Efficient and Intelligent Editing), a digital writing assistant that facilitates users to write higher-quality text more efficiently by using artificial intelligence (AI) technologies. Previous writing assistants typically provide the function of error checking (to detect and correct spelling and grammatical errors) and limited text-rewriting functionality. With the emergence of large-scale neural language models, some systems support automatically completing a sentence or a paragraph. In Effidit, we significantly expand the capacities of a writing assistant by providing functions in five categories: text completion, error checking, text polishing, keywords to sentences (K2S), and cloud input methods (cloud IME). In the text completion category, Effidit supports generation-based sentence completion, retrieval-based sentence completion, and phrase completion. In contrast, many other writing assistants so far only provide one or two of the three functions. For text polishing, we have three functions: (context-aware) phrase polishing, sentence paraphrasing, and sentence expansion, whereas many other writing assistants often support one or two functions in this category. The main contents of this report include major modules of Effidit, methods for implementing these modules, and evaluation results of some key methods.
Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 26 of its 45 references that are in the map. First posted on arXiv 3 Aug 2022.
Builds on
26 of 45 references.
References · 26
- 2017Attention Is All You Needcited by 60,361
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
- 2017Billion-scale similarity search with GPUscited by 2,497
- 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
- 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
- 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
- 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
- 2019How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddingscited by 784
14 more
- 2019Neural Text Generation with Unlikelihood Trainingcited by 503
- 2021Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depthcited by 419
- 2022A Contrastive Framework for Neural Text Generationcited by 225
- 2019The Second Conversational Intelligence Challenge (ConvAI2)cited by 179
- 2020GECToR -- Grammatical Error Correction: Tag, Not Rewritecited by 177
- 2020Enabling Language Models to Fill in the Blankscited by 122
- 2020Spelling Error Correction with Soft-Masked BERTcited by 90
- 2022Language Models Can See: Plugging Visual Controls in Text Generationcited by 90
- 2021Adaptive Semiparametric Language Modelscited by 83
- 2021TaCL: Improving BERT Pre-training with Token-aware Contrastive Learningcited by 32
- 2021Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correctioncited by 19
- 2020TexSmart: A Text Understanding System for Fine-Grained NER and Enhanced Semantic Analysiscited by 9
- 2019CASE: Context-Aware Semantic Expansioncited by 3
- 2022Pretraining Chinese BERT for Detecting Word Insertion and Deletion Errorscited by 1
Built on by
Citing papers per year: 2023: 4; 2024: 4.
8 papers.
- 2024With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generationcited by 37
- 2023Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistancecited by 33
- 2023Interactive Natural Language Processingcited by 31
- 2023Copy Is All You Needcited by 27
- 2024Towards Modeling Learner Performance with Large Language Modelscited by 21
- 2024Survey of User Interface Design and Interaction Techniques in Generative AI Applicationscited by 4
- 2023Designing Mixed-Initiative Video Gamescited by 0
- 2024An Empirical Investigation of Domain Adaptation Ability for Chinese Spelling Check Modelscited by 0
- 2024Survey of User Interface Design and Interaction Techniques in Generative AI Applications28 Oct 2024
- 2024Towards Modeling Learner Performance with Large Language Models29 Feb 2024
- 2024An Empirical Investigation of Domain Adaptation Ability for Chinese Spelling Check Models26 Jan 2024
- 2024With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generation21 Jan 2024
- 2023Copy Is All You Need13 Jul 2023
- 2023Designing Mixed-Initiative Video Games8 Jul 2023
- 2023Interactive Natural Language Processing22 May 2023
- 2023Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance22 May 2023