اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدLattice-Based Transformer Encoder for Neural Machine Translation
335
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
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.
قيم البحث
اقرأ أيضاً
Neural machine translation (NMT) is nowadays commonly applied at the subword level, using byte-pair encoding. A promising alternative approach focuses on character-level translation, which simplifies processing pipelines in NMT considerably. This app
roach, however, must consider relatively longer sequences, rendering the training process prohibitively expensive. In this paper, we discuss a novel, Transformer-based approach, that we compare, both in speed and in quality to the Transformer at subword and character levels, as well as previously developed character-level models. We evaluate our models on 4 language pairs from WMT15: DE-EN, CS-EN, FI-EN and RU-EN. The proposed novel architecture can be trained on a single GPU and is 34% percent faster than the character-level Transformer; still, the obtained results are at least on par with it. In addition, our proposed model outperforms the subword-level model in FI-EN and shows close results in CS-EN. To stimulate further research in this area and close the gap with subword-level NMT, we make all our code and models publicly available.
Attention-based Encoder-Decoder has the effective architecture for neural machine translation (NMT), which typically relies on recurrent neural networks (RNN) to build the blocks that will be lately called by attentive reader during the decoding proc
ess. This design of encoder yields relatively uniform composition on source sentence, despite the gating mechanism employed in encoding RNN. On the other hand, we often hope the decoder to take pieces of source sentence at varying levels suiting its own linguistic structure: for example, we may want to take the entity name in its raw form while taking an idiom as a perfectly composed unit. Motivated by this demand, we propose Multi-channel Encoder (MCE), which enhances encoding components with different levels of composition. More specifically, in addition to the hidden state of encoding RNN, MCE takes 1) the original word embedding for raw encoding with no composition, and 2) a particular design of external memory in Neural Turing Machine (NTM) for more complex composition, while all three encoding strategies are properly blended during decoding. Empirical study on Chinese-English translation shows that our model can improve by 6.52 BLEU points upon a strong open source NMT system: DL4MT1. On the WMT14 English- French task, our single shallow system achieves BLEU=38.8, comparable with the state-of-the-art deep models.
The prevalent approach to neural machine translation relies on bi-directional LSTMs to encode the source sentence. In this paper we present a faster and simpler architecture based on a succession of convolutional layers. This allows to encode the ent
ire source sentence simultaneously compared to recurrent networks for which computation is constrained by temporal dependencies. On WMT16 English-Romanian translation we achieve competitive accuracy to the state-of-the-art and we outperform several recently published results on the WMT15 English-German task. Our models obtain almost the same accuracy as a very deep LSTM setup on WMT14 English-French translation. Our convolutional encoder speeds up CPU decoding by more than two times at the same or higher accuracy as a strong bi-directional LSTM baseline.
Multi-modal neural machine translation (NMT) aims to translate source sentences into a target language paired with images. However, dominant multi-modal NMT models do not fully exploit fine-grained semantic correspondences between semantic units of d
ifferent modalities, which have potential to refine multi-modal representation learning. To deal with this issue, in this paper, we propose a novel graph-based multi-modal fusion encoder for NMT. Specifically, we first represent the input sentence and image using a unified multi-modal graph, which captures various semantic relationships between multi-modal semantic units (words and visual objects). We then stack multiple graph-based multi-modal fusion layers that iteratively perform semantic interactions to learn node representations. Finally, these representations provide an attention-based context vector for the decoder. We evaluate our proposed encoder on the Multi30K datasets. Experimental results and in-depth analysis show the superiority of our multi-modal NMT model.
Recent work on non-autoregressive neural machine translation (NAT) aims at improving the efficiency by parallel decoding without sacrificing the quality. However, existing NAT methods are either inferior to Transformer or require multiple decoding pa
sses, leading to reduced speedup. We propose the Glancing Language Model (GLM), a method to learn word interdependency for single-pass parallel generation models. With GLM, we develop Glancing Transformer (GLAT) for machine translation. With only single-pass parallel decoding, GLAT is able to generate high-quality translation with 8-15 times speedup. Experiments on multiple WMT language directions show that GLAT outperforms all previous single pass non-autoregressive methods, and is nearly comparable to Transformer, reducing the gap to 0.25-0.9 BLEU points.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
