paper-with-me

Papers

FeatureBART: Feature Based Sequence-to-Sequence Pre-Training for Low-Resource NMT

2022-10-01 · COLING 2022 10 · Abhisek Chakrabarty, Raj Dabre, Chenchen Ding, Hideki Tanaka, Masao Utiyama, Eiichiro Sumita

In this paper we present FeatureBART, a linguistically motivated sequence-to-sequence monolingual pre-training strategy in which syntactic features such as lemma, part-of-speech and dependency labels are incorporated into the span prediction based pre-training framework (BART). These automatically extracted features are incorporated via approaches such as concatenation and relevance mechanisms, among which the latter is known to be better than the former. When used for low-resource NMT as a downstream task, we show that these feature based models give large improvements in bilingual settings and modest ones in multilingual settings over their counterparts that do not use features.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

LEMMALow Resource NMTNMT

Similar Papers 제목 키워드 기반

Analysis of Multilingual Sequence-to-Sequence speech recognition systems

2018-11-07 · Martin Karafiát, Murali Karthick Baskar, Shinji Watanabe, Takaaki Hori 외

This paper investigates the applications of various multilingual approaches developed in conventional hidden Markov model (HMM) systems to sequence-to-sequence (seq2seq) automatic speech recognition (ASR). On a set compo…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Sequence-To-Sequence Speech Recognitionspeech-recognition+2

DeepExpress: Heterogeneous and Coupled Sequence Modeling for Express Delivery Prediction

2021-08-18 · Siyuan Ren, Bin Guo, Longbing Cao, Ke Li 외

The prediction of express delivery sequence, i.e., modeling and estimating the volumes of daily incoming and outgoing parcels for delivery, is critical for online business, logistics, and positive customer experience, an…

Prediction

Low Resource Multi-Task Sequence Tagging -- Revisiting Dynamic Conditional Random Fields

2020-05-01 · Jonas Pfeiffer, Edwin Simpson, Iryna Gurevych

We compare different models for low resource multi-task sequence tagging that leverage dependencies between label sequences for different tasks. Our analysis is aimed at datasets where each example has labels for multipl…

Multi-Task LearningSentence

Dynamic Adaptive Shared Experts with Grouped Multi-Head Attention Mixture of Experts

2025-09-05 · Cheng Li, Jiexiong Liu, Yixuan Chen, Jie ji arxiv

Transformer models based on the Mixture of Experts (MoE) architecture have made significant progress in long-sequence modeling, but existing models still have shortcomings in computational efficiency and the ability to c…

Computational Efficiency

Sequence to sequence pretraining for a less-resourced Slovenian language

2022-07-28 · Matej Ulčar, Marko Robnik-Šikonja

Large pretrained language models have recently conquered the area of natural language processing. As an alternative to predominant masked language modelling introduced in BERT, the T5 model has introduced a more general …

Language ModelingLanguage ModellingMachine TranslationOpen-Domain Question Answering+4