Related papers: Character Transformations for Non-Autoregressive G…
Multilingual translation suffers from computational redundancy, especially when translating into multiple languages simultaneously. In addition, translation quality can suffer for low-resource languages. To address this, we introduce…
Natural language correction has the potential to help language learners improve their writing skills. While approaches with separate classifiers for different error types have high precision, they do not flexibly handle errors such as…
Recently, end-to-end models have been widely used in automatic speech recognition (ASR) systems. Two of the most representative approaches are connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models.…
Generative Error Correction (GEC) has emerged as a powerful post-processing method to enhance the performance of Automatic Speech Recognition (ASR) systems. However, we show that GEC models struggle to generalize beyond the specific types…
Reconstructing natural language from non-invasive electroencephalography (EEG) holds great promise as a language decoding technology for brain-computer interfaces (BCIs). However, EEG-based language decoding is still in its nascent stages,…
Combining end-to-end speech translation (ST) and non-autoregressive (NAR) generation is promising in language and speech processing for their advantages of less error propagation and low latency. In this paper, we investigate the potential…
Automatic pronunciation error detection (APED) plays an important role in the domain of language learning. As for the previous ASR-based APED methods, the decoded results need to be aligned with the target text so that the errors can be…
We present EdiT5 - a novel semi-autoregressive text-editing model designed to combine the strengths of non-autoregressive text-editing and autoregressive decoding. EdiT5 is faster during inference than conventional sequence-to-sequence…
Tokenization is a fundamental step in natural language processing, breaking text into units that computational models can process. While learned subword tokenizers have become the de-facto standard, they present challenges such as large…
End-to-end automatic speech recognition systems often fail to transcribe domain-specific named entities, causing catastrophic failures in downstream tasks. Numerous fast and lightweight named entity correction (NEC) models have been…
Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…
While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable. Generating adversarial examples as the augmented data has been proved to be useful to…
Commonly-used transformer language models depend on a tokenization schema which sets an unchangeable subword vocabulary prior to pre-training, destined to be applied to all downstream tasks regardless of domain shift, novel word formations,…
Evaluation of grammatical error correction (GEC) systems has primarily focused on essays written by non-native learners of English, which however is only part of the full spectrum of GEC applications. We aim to broaden the target domain of…
The study of ancient writings has great value for archaeology and philology. Essential forms of material are photographic characters, but manual photographic character recognition is extremely time-consuming and expertise-dependent.…
Grammatical error correction (GEC) is the task of detecting and correcting grammatical errors in texts written by second language learners. The statistical machine translation (SMT) approach to GEC, in which sentences written by second…
Digital ink promises to combine the flexibility and aesthetics of handwriting and the ability to process, search and edit digital text. Character recognition converts handwritten text into a digital representation, albeit at the cost of…
Decoder-only large language models have shown superior performance in the fluency-edit English Grammatical Error Correction, but their adaptation for minimal-edit English GEC is still underexplored. To improve their effectiveness in the…
Text-guided image editing involves modifying a source image based on a language instruction and, typically, requires changes to only small local regions. However, existing approaches generate the entire target image rather than selectively…
ChatGPT, a large-scale language model based on the advanced GPT-3.5 architecture, has shown remarkable potential in various Natural Language Processing (NLP) tasks. However, there is currently a dearth of comprehensive study exploring its…