paper-with-me

Papers

Towards Example-Based NMT with Multi-Levenshtein Transformers

2023-10-13 · Maxime Bouthors, Josep Crego, François Yvon

Retrieval-Augmented Machine Translation (RAMT) is attracting growing attention. This is because RAMT not only improves translation metrics, but is also assumed to implement some form of domain adaptation. In this contribution, we study another salient trait of RAMT, its ability to make translation decisions more transparent by allowing users to go back to examples that contributed to these decisions. For this, we propose a novel architecture aiming to increase this transparency. This model adapts a retrieval-augmented version of the Levenshtein Transformer and makes it amenable to simultaneously edit multiple fuzzy matches found in memory. We discuss how to perform training and inference in this model, based on multi-way alignment algorithms and imitation learning. Our experiments show that editing several examples positively impacts translation scores, notably increasing the number of target spans that are copied from existing instances.

📄 PDF Abstract BibTeX arXiv:2310.08967

Code (1)

maxwell1447/fairseq 공식 구현 pytorch

Tasks

Domain AdaptationImitation LearningMachine TranslationNMTRetrievalTranslation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 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…
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…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

A New String Edit Distance and Applications

2022-03-11 · Taylor Petty, Jan Hannig, Tunde I Huszar, Hari Iyer

String edit distances have been used for decades in applications ranging from spelling correction and web search suggestions to DNA analysis. Most string edit distances are variations of the Levenshtein distance and cons…

DNA analysisSpelling Correction

Interpreting Sequence-Levenshtein distance for determining error type and frequency between two embedded sequences of equal length

2023-10-19 · Robert Logan, Amy W. Wehe, Dori C. Woods, Jon Tilly 외

Levenshtein distance is a commonly used edit distance metric, typically applied in language processing, and to a lesser extent, in molecular biology analysis. Biological nucleic acid sequences are often embedded in longe…

A Comprehensive Approach to Misspelling Correction with BERT and Levenshtein Distance

2024-07-24 · Amirreza Naziri, Hossein Zeinali

Writing, as an omnipresent form of human communication, permeates nearly every aspect of contemporary life. Consequently, inaccuracies or errors in written communication can lead to profound consequences, ranging from fi…

Language ModelingLanguage Modelling

Optimizing example selection for retrieval-augmented machine translation with translation memories

2024-05-23 · Maxime Bouthors, Josep Crego, François Yvon

Retrieval-augmented machine translation leverages examples from a translation memory by retrieving similar instances. These examples are used to condition the predictions of a neural decoder. We aim to improve the upstre…

DecoderMachine TranslationRetrievalSentence+1

Sequence Covering Similarity for Symbolic Sequence Comparison

2018-01-22 · Pierre-François Marteau

This paper introduces the sequence covering similarity, that we formally define for evaluating the similarity between a symbolic sequence (string) and a set of symbolic sequences (strings). From this covering similarity …