paper-with-me

Papers

Lattice-Based Transformer Encoder for Neural Machine Translation

2019-06-04 · ACL 2019 7 · Fengshun Xiao, Jiangtong Li, Hai Zhao, Rui Wang, Kehai Chen

Neural machine translation (NMT) takes deterministic sequences for source representations. However, either word-level or subword-level segmentations have multiple choices to split a source sequence with different word segmentors or different subword vocabulary sizes. We hypothesize that the diversity in segmentations may affect the NMT performance. To integrate different segmentations with the state-of-the-art NMT model, Transformer, we propose lattice-based encoders to explore effective word or subword representation in an automatic way during training. We propose two methods: 1) lattice positional encoding and 2) lattice-aware self-attention. These two methods can be used together and show complementary to each other to further improve translation performance. Experiment results show superiorities of lattice-based encoders in word-level and subword-level representations over conventional Transformer encoder.

📄 PDF Abstract BibTeX arXiv:1906.01282

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityMachine TranslationNMTTranslation

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

Lattice Transformer for Speech Translation

2019-06-13 · ACL 2019 7 · Pei Zhang, Boxing Chen, Niyu Ge, Kai Fan

Recent advances in sequence modeling have highlighted the strengths of the transformer architecture, especially in achieving state-of-the-art machine translation results. However, depending on the up-stream systems, e.g.…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeech-recognition+2

Lattice-Based Recurrent Neural Network Encoders for Neural Machine Translation

2016-09-25 · Jinsong Su, Zhixing Tan, Deyi Xiong, Rongrong Ji 외

Neural machine translation (NMT) heavily relies on word-level modelling to learn semantic representations of input sentences. However, for languages without natural word delimiters (e.g., Chinese) where input sentences h…

Machine TranslationNMTSentenceTranslation

Sequence-to-Lattice Models for Fast Translation

2021-11-01 · Findings (EMNLP) 2021 11 · Yuntian Deng, Alexander Rush

Non-autoregressive machine translation (NAT) approaches enable fast generation by utilizing parallelizable generative processes. The remaining bottleneck in these models is their decoder layers; unfortunately unlike in a…

DecoderMachine TranslationTranslation

Neural Lattice Search for Domain Adaptation in Machine Translation

2017-11-01 · IJCNLP 2017 11 · Huda Khayrallah, Gaurav Kumar, Kevin Duh, Matt Post 외

Domain adaptation is a major challenge for neural machine translation (NMT). Given unknown words or new domains, NMT systems tend to generate fluent translations at the expense of adequacy. We present a stack-based latti…

Domain AdaptationMachine TranslationNMTTranslation

Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices

2016-12-12 · EACL 2017 4 · Felix Stahlberg, Adrià De Gispert, Eva Hasler, Bill Byrne

We present a novel scheme to combine neural machine translation (NMT) with traditional statistical machine translation (SMT). Our approach borrows ideas from linearised lattice minimum Bayes-risk decoding for SMT. The NM…

DecoderMachine TranslationNMTTranslation