paper-with-me

Papers

Neuron Interaction Based Representation Composition for Neural Machine Translation

2019-11-22 · Jian Li, Xing Wang, Baosong Yang, Shuming Shi, Michael R. Lyu, Zhaopeng Tu

Recent NLP studies reveal that substantial linguistic information can be attributed to single neurons, i.e., individual dimensions of the representation vectors. We hypothesize that modeling strong interactions among neurons helps to better capture complex information by composing the linguistic properties embedded in individual neurons. Starting from this intuition, we propose a novel approach to compose representations learned by different components in neural machine translation (e.g., multi-layer networks or multi-head attention), based on modeling strong interactions among neurons in the representation vectors. Specifically, we leverage bilinear pooling to model pairwise multiplicative interactions among individual neurons, and a low-rank approximation to make the model computationally feasible. We further propose extended bilinear pooling to incorporate first-order representations. Experiments on WMT14 English-German and English-French translation tasks show that our model consistently improves performances over the SOTA Transformer baseline. Further analyses demonstrate that our approach indeed captures more syntactic and semantic information as expected.

📄 PDF Abstract BibTeX arXiv:1911.09877

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

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

Identifying and Controlling Important Neurons in Neural Machine Translation

2018-11-03 · ICLR 2019 5 · Anthony Bau, Yonatan Belinkov, Hassan Sajjad, Nadir Durrani 외

Neural machine translation (NMT) models learn representations containing substantial linguistic information. However, it is not clear if such information is fully distributed or if some of it can be attributed to individ…

Machine TranslationNMTTranslation

Identifying and Controlling Important Neurons in Neural Machine Translation

2018-10-22 · NIPS Workshop IRASL 2018 · Anonymous

Neural machine translation (NMT) models learn representations containing substantial linguistic information. However, it is not clear if such information is fully distributed or if some of it can be attributed to individ…

Machine TranslationNMTTranslation

On Neurons Invariant to Sentence Structural Changes in Neural Machine Translation

2021-10-06 · Gal Patel, Leshem Choshen, Omri Abend

We present a methodology that explores how sentence structure is reflected in neural representations of machine translation systems. We demonstrate our model-agnostic approach with the Transformer English-German translat…

Machine TranslationSentenceTranslation

Fourier-Invertible Neural Encoder (FINE) for Homogeneous Flows

2025-05-21 · Anqiao Ouyang, Hongyi Ke, Qi Wang

Invertible neural architectures have recently attracted attention for their compactness, interpretability, and information-preserving properties. In this work, we propose the Fourier-Invertible Neural Encoder (FINE), whi…

Dimensionality ReductionPhysics-informed machine learningRepresentation Learning

Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation

2022-05-30 · ACL 2022 5 · Verna Dankers, Christopher G. Lucas, Ivan Titov

Unlike literal expressions, idioms' meanings do not directly follow from their parts, posing a challenge for neural machine translation (NMT). NMT models are often unable to translate idioms accurately and over-generate …

Machine TranslationNMTTranslation