paper-with-me

홈 › Papers

What Role Does BERT Play in the Neural Machine Translation Encoder?

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Pre-trained language models have been widely applied in various natural language processing tasks. But when it comes to neural machine translation, things are a little different. The differences between the embedding spaces created by BERT and NMT encoder may be one of the main reasons for the difficulty of integrating pre-trained LMs into NMT models. Previous studies illustrate the best way of integration is introducing the output of BERT into the encoder with some extra modules. Nevertheless, it is still unrevealed whether these additional modules will affect the embedding spaces created by the NMT encoder or not and what kind of information the NMT encoder takes advantage of from the output of BERT. In this paper, we start by comparing the changes of embedding spaces after introducing BERT into the NMT encoder trained on different machine translation tasks. Although the changing trends of these embedding spaces vary, introducing BERT into the NMT encoder will not affect the space of the last layer significantly. Subsequent evaluation on several semantic and syntactic tasks proves the NMT encoder is facilitated by the rich syntactic information contained in the output of BERT to boost the translation quality.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTTranslation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Adam 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?

2022-12-21 · Ningyu Xu, Tao Gui, Ruotian Ma, Qi Zhang 외

Multilingual BERT (mBERT) has demonstrated considerable cross-lingual syntactic ability, whereby it enables effective zero-shot cross-lingual transfer of syntactic knowledge. The transfer is more successful between some …

Cross-Lingual TransferDiversityZero-Shot Cross-Lingual Transfer

When Role-playing, Do Models Believe What They Say?

2026-06-09 · Benjamin Sturgeon, David Africa, Sid Black arxiv

Language models can state that "the Earth orbits the Sun" and, when role-playing Aristotle, assert the opposite. Recent work argues that persona adoption is fundamental to how language models behave, with models selectin…

Tapping BERT for Preposition Sense Disambiguation

2021-11-27 · Siddhesh Pawar, Shyam Thombre, Anirudh Mittal, Girishkumar Ponkiya 외

Prepositions are frequently occurring polysemous words. Disambiguation of prepositions is crucial in tasks like semantic role labelling, question answering, text entailment, and noun compound paraphrasing. In this paper,…

Question Answering

Does BERT Recognize an Agent? Modeling Dowty’s Proto-Roles with Contextual Embeddings

2022-10-01 · COLING 2022 10 · Mattia Proietti, Gianluca Lebani, Alessandro Lenci

Contextual embeddings build multidimensional representations of word tokens based on their context of occurrence. Such models have been shown to achieve a state-of-the-art performance on a wide variety of tasks. Yet, the…

Tapping BERT for Preposition Sense Disambiguation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Prepositions are frequently occurring polysemous words. Disambiguation of prepositions is crucial in tasks like semantic role labelling, question answering, text entailment, and noun compound paraphrasing. In this paper,…

Question Answering