On the differences between BERT and MT encoder spaces and how to address them in translation tasks
暂无分享,去创建一个
Jörg Tiedemann | Mathias Creutz | Hande Celikkanat | Raúl Vázquez | H. Çelikkanat | J. Tiedemann | Mathias Creutz | Raúl Vázquez
[1] Sam Witteveen,et al. Paraphrasing with Large Language Models , 2019, EMNLP.
[2] Jörg Tiedemann,et al. OpusTools and Parallel Corpus Diagnostics , 2020, LREC.
[3] Philipp Koehn,et al. Findings of the 2015 Workshop on Statistical Machine Translation , 2015, WMT@EMNLP.
[4] Jörg Tiedemann,et al. Parallel Data, Tools and Interfaces in OPUS , 2012, LREC.
[5] Eneko Agirre,et al. SemEval-2016 Task 1: Semantic Textual Similarity, Monolingual and Cross-Lingual Evaluation , 2016, *SEMEVAL.
[6] Garrison W. Cottrell,et al. Content and cluster analysis: Assessing representational similarity in neural systems , 2000 .
[7] Eiichiro Sumita,et al. Recycling a Pre-trained BERT Encoder for Neural Machine Translation , 2019, EMNLP.
[8] Yijia Liu,et al. Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing , 2019, EMNLP.
[9] Danqi Chen,et al. of the Association for Computational Linguistics: , 2001 .
[10] Richard Socher,et al. Learned in Translation: Contextualized Word Vectors , 2017, NIPS.
[11] Hermann Ney,et al. A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.
[12] Robert L. Mercer,et al. The Mathematics of Statistical Machine Translation: Parameter Estimation , 1993, CL.
[13] Marjan Ghazvininejad,et al. Multilingual Denoising Pre-training for Neural Machine Translation , 2020, Transactions of the Association for Computational Linguistics.
[14] Rico Sennrich,et al. The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives , 2019, EMNLP.
[15] Jascha Sohl-Dickstein,et al. SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability , 2017, NIPS.
[16] Lei Li,et al. Towards Making the Most of BERT in Neural Machine Translation , 2020, AAAI.
[17] Philipp Koehn,et al. Europarl: A Parallel Corpus for Statistical Machine Translation , 2005, MTSUMMIT.
[18] Dan Klein,et al. Multilingual Alignment of Contextual Word Representations , 2020, ICLR.
[19] Tomoki Toda,et al. Speech Recognition by Simply Fine-Tuning Bert , 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[20] Thomas Wolf,et al. HuggingFace's Transformers: State-of-the-art Natural Language Processing , 2019, ArXiv.
[21] Willem Zuidema,et al. Blackbox Meets Blackbox: Representational Similarity & Stability Analysis of Neural Language Models and Brains , 2019, BlackboxNLP@ACL.
[22] Omer Levy,et al. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension , 2019, ACL.
[23] Nikolaus Kriegeskorte,et al. Frontiers in Systems Neuroscience Systems Neuroscience , 2022 .
[24] Laure Thompson,et al. The strange geometry of skip-gram with negative sampling , 2017, EMNLP.
[25] Guillaume Lample,et al. What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties , 2018, ACL.
[26] Mirella Lapata,et al. Text Summarization with Pretrained Encoders , 2019, EMNLP.
[27] Anders Søgaard,et al. A Survey of Cross-lingual Word Embedding Models , 2017, J. Artif. Intell. Res..
[28] Kawin Ethayarajh,et al. How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings , 2019, EMNLP.
[29] Ilya Sutskever,et al. Language Models are Unsupervised Multitask Learners , 2019 .
[30] Douwe Kiela,et al. SentEval: An Evaluation Toolkit for Universal Sentence Representations , 2018, LREC.
[31] Elahe Rahimtoroghi,et al. What Happens To BERT Embeddings During Fine-tuning? , 2020, BLACKBOXNLP.
[32] Mattia Antonino Di Gangi,et al. MuST-C: a Multilingual Speech Translation Corpus , 2019, NAACL.
[33] Tie-Yan Liu,et al. Incorporating BERT into Neural Machine Translation , 2020, ICLR.
[34] Xu Tan,et al. MASS: Masked Sequence to Sequence Pre-training for Language Generation , 2019, ICML.
[35] Yoshua Bengio,et al. An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks , 2013, ICLR.
[36] H. Hotelling. Relations Between Two Sets of Variates , 1936 .
[37] Christopher D. Manning,et al. A Structural Probe for Finding Syntax in Word Representations , 2019, NAACL.
[38] Vassilina Nikoulina,et al. On the use of BERT for Neural Machine Translation , 2019, EMNLP.
[39] Afra Alishahi,et al. Correlating Neural and Symbolic Representations of Language , 2019, ACL.
[40] Luke S. Zettlemoyer,et al. Deep Contextualized Word Representations , 2018, NAACL.
[41] Regina Barzilay,et al. Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing , 2019, NAACL.
[42] Samy Bengio,et al. Insights on representational similarity in neural networks with canonical correlation , 2018, NeurIPS.
[43] Ming-Wei Chang,et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.