paper-with-me

Papers

Hierarchical Attention Transformer Architecture For Syntactic Spell Correction

2020-05-11 · Abhishek Niranjan, M Ali Basha Shaik, Kushal Verma

The attention mechanisms are playing a boosting role in advancements in sequence-to-sequence problems. Transformer architecture achieved new state of the art results in machine translation, and it's variants are since being introduced in several other sequence-to-sequence problems. Problems which involve a shared vocabulary, can benefit from the similar semantic and syntactic structure in the source and target sentences. With the motivation of building a reliable and fast post-processing textual module to assist all the text-related use cases in mobile phones, we take on the popular spell correction problem. In this paper, we propose multi encoder-single decoder variation of conventional transformer. Outputs from the three encoders with character level 1-gram, 2-grams and 3-grams inputs are attended in hierarchical fashion in the decoder. The context vectors from the encoders clubbed with self-attention amplify the n-gram properties at the character level and helps in accurate decoding. We demonstrate our model on spell correction dataset from Samsung Research, and report significant improvement of 0.11\%, 0.32\% and 0.69\% in character (CER), word (WER) and sentence (SER) error rates from existing state-of-the-art machine-translation architectures. Our architecture is also trains ~7.8 times faster, and is only about 1/3 in size from the next most accurate model.

📄 PDF Abstract BibTeX arXiv:2005.04876

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMachine TranslationSentenceTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Representational correlates of hierarchical phrase structure in deep language models

2021-01-01 · Matteo Alleman, Jonathan Mamou, Miguel A Del Rio, Hanlin Tang 외

While contextual representations from Transformer-based architectures have set a new standard for many NLP tasks, there is not yet a complete accounting of their inner workings. In particular, it is not entirely clear wh…

SensitivitySentence

Hierarchical Transformer Encoders for Vietnamese Spelling Correction

2021-05-28 · Hieu Tran, Cuong V. Dinh, Long Phan, Son T. Nguyen

In this paper, we propose a Hierarchical Transformer model for Vietnamese spelling correction problem. The model consists of multiple Transformer encoders and utilizes both character-level and word-level to detect errors…

Spelling Correction

Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Network

2021-11-23 · Ru Peng, Nankai Lin, Yi Fang, Shengyi Jiang 외

Syntax knowledge contributes its powerful strength in Neural machine translation (NMT) tasks. Early NMT works supposed that syntax details can be automatically learned from numerous texts via attention networks. However,…

Machine TranslationNMTTranslation

Hierarchical Character Tagger for Short Text Spelling Error Correction

2021-09-29 · WNUT (ACL) 2021 11 · Mengyi Gao, Canran Xu, Peng Shi

State-of-the-art approaches to spelling error correction problem include Transformer-based Seq2Seq models, which require large training sets and suffer from slow inference time; and sequence labeling models based on Tran…

Language ModelingLanguage Modelling

Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts

2023-04-07 · Queenie Luo, Yung-Sung Chuang

Scholars in the humanities rely heavily on ancient manuscripts to study history, religion, and socio-political structures in the past. Many efforts have been devoted to digitizing these precious manuscripts using OCR tec…

Optical Character RecognitionOptical Character Recognition (OCR)Spelling Correction