Neural machine translation systems require a number of stacked layers for deep models. But the prediction depends on the sentence representation of the top-most layer with no access to low-level representations. This makes it more difficult to train the model and poses a risk of information loss to prediction. In this paper, we propose a multi-layer representation fusion (MLRF) approach to fusing stacked layers. In particular, we design three fusion functions to learn a better representation from the stack. Experimental results show that our approach yields improvements of 0.92 and 0.56 BLEU points over the strong Transformer baseline on IWSLT German-English and NIST Chinese-English MT tasks respectively. The result is new state-of-the-art in German-English translation.
Neural machine translation (NMT) systems require large amounts of high quality in-domain parallel corpora for training. State-of-the-art NMT systems still face challenges related to out-of-vocabulary words and dealing with low-resource language pairs. In this paper, we propose and compare several models for fusion of bilingual lexicons with an end-to-end trained sequence-to-sequence model for machine translation. The result is a fusion model with two information sources for the decoder: a neural conditional language model and a bilingual lexicon. This fusion model learns how to combine both so…
Neural Machine Translation (NMT) can be used to generate fluent output. As such, language models have been investigated for incorporation with NMT. In prior investigations, two models have been used: a translation model and a language model. The translation model's predictions are weighted by the language model with a hand-crafted ratio in advance. However, these approaches fail to adopt the language model weighting with regard to the translation history. In another line of approach, language model prediction is incorporated into the translation model by jointly considering source and target i…
Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas, Universidad Nacional Autónoma de México（墨西哥国立自治大学应用数学与系统科学研究所）；Facultad de Estudios Superiores Acatlán, Universidad Nacional Autónoma de México（墨西哥国立自治大学阿卡特朗高等研究学院）；Centro de Estudios Lingüísticos y Literarios, El Colegio de México（墨西哥学院语言与文学研究中心）；Center for Data Science, New York University（纽约大学数据科学中心）
Machine translation from polysynthetic to fusional languages is a challenging task, which gets further complicated by the limited amount of parallel text available. Thus, translation performance is far from the state of the art for high-resource and more intensively studied language pairs. To shed light on the phenomena which hamper automatic translation to and from polysynthetic languages, we study translations from three low-resource, polysynthetic languages (Nahuatl, Wixarika and Yorem Nokki) into Spanish and vice versa. Doing so, we find that in a morpheme-to-morpheme alignment an importan…
Xiamen University（厦门大学）；Tencent Inc（腾讯公司）；University of Rochester（罗切斯特大学）
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 different 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 mul…
University of Edinburgh（爱丁堡大学）；New York University（纽约大学）；Aalborg University（奥尔堡大学）
Theoretical work in morphological typology offers the possibility of measuring morphological diversity on a continuous scale. However, literature in Natural Language Processing (NLP) typically labels a whole language with a strict type of morphology, e.g. fusional or agglutinative. In this work, we propose to reduce the rigidity of such claims, by quantifying morphological typology at the word and segment level. We consider Payne (2017)'s approach to classify morphology using two indices: synthesis (e.g. analytic to polysynthetic) and fusion (agglutinative to fusional). For computing synthesis…
Shanghai Jiao Tong University（上海交通大学）；National Institute of Information and Communications Technology（日本国立信息与通信技术研究所）
State-of-the-art Transformer-based neural machine translation (NMT) systems still follow a standard encoder-decoder framework, in which source sentence representation can be well done by an encoder with self-attention mechanism. Though Transformer-based encoder may effectively capture general information in its resulting source sentence representation, the backbone information, which stands for the gist of a sentence, is not specifically focused on. In this paper, we propose an explicit sentence compression method to enhance the source sentence representation for NMT. In practice, an explicit …
Neural Machine Translation (NMT) typically leverages monolingual data in training through backtranslation. We investigate an alternative simple method to use monolingual data for NMT training: We combine the scores of a pre-trained and fixed language model (LM) with the scores of a translation model (TM) while the TM is trained from scratch. To achieve that, we train the translation model to predict the residual probability of the training data added to the prediction of the LM. This enables the TM to focus its capacity on modeling the source sentence since it can rely on the LM for fluency. W…
National Institute of Information and Communications Technology（信息通信研究机构）
In neural machine translation (NMT), the most common practice is to stack a number of recurrent or feed-forward layers in the encoder and the decoder. As a result, the addition of each new layer improves the translation quality significantly. However, this also leads to a significant increase in the number of parameters. In this paper, we propose to share parameters across all the layers thereby leading to a recurrently stacked NMT model. We empirically show that the translation quality of a model that recurrently stacks a single layer 6 times is comparable to the translation quality of a mode…
How do we perform efficient inference while retaining high translation quality? Existing neural machine translation models, such as Transformer, achieve high performance, but they decode words one by one, which is inefficient. Recent non-autoregressive translation models speed up the inference, but their quality is still inferior. In this work, we propose DSLP, a highly efficient and high-performance model for machine translation. The key insight is to train a non-autoregressive Transformer with Deep Supervision and feed additional Layer-wise Predictions. We conducted extensive experiments on …
In this paper, we study the use of deep Transformer translation model for the CCMT 2022 Chinese-Thai low-resource machine translation task. We first explore the experiment settings (including the number of BPE merge operations, dropout probability, embedding size, etc.) for the low-resource scenario with the 6-layer Transformer. Considering that increasing the number of layers also increases the regularization on new model parameters (dropout modules are also introduced when using more layers), we adopt the highest performance setting but increase the depth of the Transformer to 24 layers to o…
Stony Brook University（石溪大学）；Amirkabir University of Technology（阿米尔卡比尔理工大学）
Neural Machine Translation (NMT) models are strong enough to convey semantic and syntactic information from the source language to the target language. However, these models are suffering from the need for a large amount of data to learn the parameters. As a result, for languages with scarce data, these models are at risk of underperforming. We propose to augment attention based neural network with reordering information to alleviate the lack of data. This augmentation improves the translation quality for both English to Persian and Persian to English by up to 6% BLEU absolute over the baselin…
Machine Intelligence Technology Lab, Alibaba DAMO Academy（阿里巴巴达摩院机器智能技术实验室）；Kingsoft AI Lab（金山人工智能实验室）；Institute of Advanced Technology, Westlake Institute for Advanced Study（西湖先进研究院先进技术研究所）；School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）；NiuTrans Research（牛译研究（NiuTrans Research））
Traditional neural machine translation is limited to the topmost encoder layer's context representation and cannot directly perceive the lower encoder layers. Existing solutions usually rely on the adjustment of network architecture, making the calculation more complicated or introducing additional structural restrictions. In this work, we propose layer-wise multi-view learning to solve this problem, circumventing the necessity to change the model structure. We regard each encoder layer's off-the-shelf output, a by-product in layer-by-layer encoding, as the redundant view for the input sentenc…
National Institute of Information and Communications Technology（信息通信技术研究所）
In deep neural network modeling, the most common practice is to stack a number of recurrent, convolutional, or feed-forward layers in order to obtain high-quality continuous space representations which in turn improves the quality of the network's prediction. Conventionally, each layer in the stack has its own parameters which leads to a significant increase in the number of model parameters. In this paper, we propose to share parameters across all layers thereby leading to a recurrently stacked neural network model. We report on an extensive case study on neural machine translation (NMT), whe…
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）；Qatar Computing Research Institute, HBKU（哈马德·本·哈利法大学卡塔尔计算研究所）
While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector representations learned by NMT models on morphological and syntactic tasks. In this paper, we investigate the representations learned at different layers of NMT encoders. We train NMT systems on parallel data and use the trained models to extract features for training a classifier on two tasks: part-of-speech and semantic tagging. We then measure the performance of the cl…
With the rapid development of artificial intelligence (AI), there is a trend in moving AI applications, such as neural machine translation (NMT), from cloud to mobile devices. Constrained by limited hardware resources and battery, the performance of on-device NMT systems is far from satisfactory. Inspired by conditional computation, we propose to improve the performance of on-device NMT systems with dynamic multi-branch layers. Specifically, we design a layer-wise dynamic multi-branch network with only one branch activated during training and inference. As not all branches are activated during…
BERT-enhanced neural machine translation (NMT) aims at leveraging BERT-encoded representations for translation tasks. A recently proposed approach uses attention mechanisms to fuse Transformer's encoder and decoder layers with BERT's last-layer representation and shows enhanced performance. However, their method doesn't allow for the flexible distribution of attention between the BERT representation and the encoder/decoder representation. In this work, we propose a novel BERT-enhanced NMT model called BERT-JAM which improves upon existing models from two aspects: 1) BERT-JAM uses joint-attenti…
Microsoft Research（微软研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
We explore the application of very deep Transformer models for Neural Machine Translation (NMT). Using a simple yet effective initialization technique that stabilizes training, we show that it is feasible to build standard Transformer-based models with up to 60 encoder layers and 12 decoder layers. These deep models outperform their baseline 6-layer counterparts by as much as 2.5 BLEU, and achieve new state-of-the-art benchmark results on WMT14 English-French (43.8 BLEU and 46.4 BLEU with back-translation) and WMT14 English-German (30.1 BLEU).The code and trained models will be publicly availa…
KingSoft AI Lab（金山人工智能实验室）；Massey University（梅西大学）
Although attention-based Neural Machine Translation has achieved remarkable progress in recent layers, it still suffers from issue of making insufficient use of the output of each layer. In transformer, it only uses the top layer of encoder and decoder in the subsequent process, which makes it impossible to take advantage of the useful information in other layers. To address this issue, we propose a residual tree aggregation of layers for Transformer(RTAL), which helps to fuse information across layers. Specifically, we try to fuse the information across layers by constructing a post-order bin…
The softmax layer in neural machine translation is designed to model the distribution over mutually exclusive tokens. Machine translation, however, is intrinsically uncertain: the same source sentence can have multiple semantically equivalent translations. Therefore, we propose to replace the softmax activation with a multi-label classification layer that can model ambiguity more effectively. We call our loss function Single-label Contrastive Objective for Non-Exclusive Sequences (SCONES). We show that the multi-label output layer can still be trained on single reference training data using th…
Cranberry-Lemon University（蔓越莓柠檬大学）；University of the Witwatersrand（威特沃特斯兰德大学）
In this work, we empirically confirm that non-autoregressive translation with an iterative refinement mechanism (IR-NAT) suffers from poor acceleration robustness because it is more sensitive to decoding batch size and computing device setting than autoregressive translation (AT). Inspired by it, we attempt to investigate how to combine the strengths of autoregressive and non-autoregressive translation paradigms better. To this end, we demonstrate through synthetic experiments that prompting a small number of AT's predictions can promote one-shot non-autoregressive translation to achieve the e…
Beihang University（北京航空航天大学）；Microsoft Research Asia（微软亚洲研究院）
Transformer structure, stacked by a sequence of encoder and decoder network layers, achieves significant development in neural machine translation. However, vanilla Transformer mainly exploits the top-layer representation, assuming the lower layers provide trivial or redundant information and thus ignoring the bottom-layer feature that is potentially valuable. In this work, we propose the Group-Transformer model (GTrans) that flexibly divides multi-layer representations of both encoder and decoder into different groups and then fuses these group features to generate target words. To corroborat…
Carnegie Mellon University（卡内基梅隆大学）；Tencent AI Lab（腾讯人工智能实验室）
With the promising progress of deep neural networks, layer aggregation has been used to fuse information across layers in various fields, such as computer vision and machine translation. However, most of the previous methods combine layers in a static fashion in that their aggregation strategy is independent of specific hidden states. Inspired by recent progress on capsule networks, in this paper we propose to use routing-by-agreement strategies to aggregate layers dynamically. Specifically, the algorithm learns the probability of a part (individual layer representations) assigned to a whole (…
National Institute of Information and Communications Technology（信息通信技术研究所）
This paper proposes a novel procedure for training an encoder-decoder based deep neural network which compresses NxM models into a single model enabling us to dynamically choose the number of encoder and decoder layers for decoding. Usually, the output of the last layer of the N-layer encoder is fed to the M-layer decoder, and the output of the last decoder layer is used to compute softmax loss. Instead, our method computes a single loss consisting of NxM losses: the softmax loss for the output of each of the M decoder layers derived using the output of each of the N encoder layers. A single m…
Nanjing University（南京大学）；Tencent AI Lab（腾讯人工智能实验室）
Advanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated linguistic structures. However, only the top layers of encoder and decoder are leveraged in the subsequent process, which misses the opportunity to exploit the useful information embedded in other layers. In this work, we propose to simultaneously expose all of these signals with layer aggregation and multi-layer attention mechanisms. In addition, we introduce an auxiliary regularization term to encourage different …
University of Edinburgh（爱丁堡大学）；University of Amsterdam（阿姆斯特丹大学）；University of Zurich（苏黎世大学）
The transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context. Lexical features are fed into the first layer and propagated through a deep network of hidden layers. We argue that the need to represent and propagate lexical features in each layer limits the model's capacity for learning and representing other information relevant to the task. To alleviate this bottleneck, we introduce gated shortcut connections between the embedding layer and each subsequent layer within the en…
KingSoft AI Lab（金山AI实验室）；University of Groningen（格罗宁根大学）
Learning deeper models is usually a simple and effective approach to improve model performance, but deeper models have larger model parameters and are more difficult to train. To get a deeper model, simply stacking more layers of the model seems to work well, but previous works have claimed that it cannot benefit the model. We propose to train a deeper model with recurrent mechanism, which loops the encoder and decoder blocks of Transformer in the depth direction. To address the increasing of model parameters, we choose to share parameters in different recursive moments. We conduct our experim…
Georgia Institute of Technology（佐治亚理工学院）；ByteDance（字节跳动）
Many multi-domain neural machine translation (NMT) models achieve knowledge transfer by enforcing one encoder to learn shared embedding across domains. However, this design lacks adaptation to individual domains. To overcome this limitation, we propose a novel multi-domain NMT model using individual modules for each domain, on which we apply word-level, adaptive and layer-wise domain mixing. We first observe that words in a sentence are often related to multiple domains. Hence, we assume each word has a domain proportion, which indicates its domain preference. Then word representations are obt…
The applications of recurrent neural networks in machine translation are increasing in natural language processing. Besides other languages, Bangla language contains a large amount of vocabulary. Improvement of English to Bangla machine translation would be a significant contribution to Bangla Language processing. This paper describes an architecture of English to Bangla machine translation system. The system has been implemented with the encoder-decoder recurrent neural network. The model uses a knowledge-based context vector for the mapping of English and Bangla words. Performances of the mo…
Effective fusion of data from multiple modalities, such as video, speech, and text, is challenging due to the heterogeneous nature of multimodal data. In this paper, we propose adaptive fusion techniques that aim to model context from different modalities effectively. Instead of defining a deterministic fusion operation, such as concatenation, for the network, we let the network decide "how" to combine a given set of multimodal features more effectively. We propose two networks: 1) Auto-Fusion, which learns to compress information from different modalities while preserving the context, and 2) …
Multimodal sentiment analysis is an important research area that predicts speaker's sentiment tendency through features extracted from textual, visual and acoustic modalities. The central challenge is the fusion method of the multimodal information. A variety of fusion methods have been proposed, but few of them adopt end-to-end translation models to mine the subtle correlation between modalities. Enlightened by recent success of Transformer in the area of machine translation, we propose a new fusion method, TransModality, to address the task of multimodal sentiment analysis. We assume that tr…
Saarland University（萨尔兰大学）；German Research Center for Artificial Intelligence（德国人工智能研究中心）；China Mobile Online Services（中移在线服务有限公司）；Tianjin University（天津大学）
Due to its effectiveness and performance, the Transformer translation model has attracted wide attention, most recently in terms of probing-based approaches. Previous work focuses on using or probing source linguistic features in the encoder. To date, the way word translation evolves in Transformer layers has not yet been investigated. Naively, one might assume that encoder layers capture source information while decoder layers translate. In this work, we show that this is not quite the case: translation already happens progressively in encoder layers and even in the input embeddings. More sur…
Zhejiang University（浙江大学）；Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）；City University of Hong Kong（香港城市大学）；Xiamen University（厦门大学）
Sign Language (SL), as the mother tongue of the deaf community, is a special visual language that most hearing people cannot understand. In recent years, neural Sign Language Translation (SLT), as a possible way for bridging communication gap between the deaf and the hearing people, has attracted widespread academic attention. We found that the current mainstream end-to-end neural SLT models, which tries to learning language knowledge in a weakly supervised manner, could not mine enough semantic information under the condition of low data resources. Therefore, we propose to introduce additiona…
Compared with unimodal data, multimodal data can provide more features to help the model analyze the sentiment of data. Previous research works rarely consider token-level feature fusion, and few works explore learning the common features related to sentiment in multimodal data to help the model fuse multimodal features. In this paper, we propose a Contrastive Learning and Multi-Layer Fusion (CLMLF) method for multimodal sentiment detection. Specifically, we first encode text and image to obtain hidden representations, and then use a multi-layer fusion module to align and fuse the token-level …
Lower Layers Matter: Alleviating Hallucination via Multi-Layer Fusion Contrastive Decoding with Truthfulness Refocused
Sun Yat-Sen University（中山大学）；Shenzhen MSU-BIT University（深圳MSU-BIT大学）；UNSW, Sydney, NSW 2052, Australia（新南威尔士大学，悉尼，新南威尔士州，2052，澳大利亚）；Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳高性能数据挖掘关键实验室，深圳先进技术研究院，中国科学院）
University of Macau（澳门大学）；Tencent AI Lab（腾讯 AI 实验室）；The University of Sydney（悉尼大学）
Encoder layer fusion (EncoderFusion) is a technique to fuse all the encoder layers (instead of the uppermost layer) for sequence-to-sequence (Seq2Seq) models, which has proven effective on various NLP tasks. However, it is still not entirely clear why and when EncoderFusion should work. In this paper, our main contribution is to take a step further in understanding EncoderFusion. Many of previous studies believe that the success of EncoderFusion comes from exploiting surface and syntactic information embedded in lower encoder layers. Unlike them, we find that the encoder embedding layer is mor…
National Technical University of Athens（雅典国立技术大学）；Athena Research Center（雅典娜研究中心）
Multimodal learning pipelines have benefited from the success of pretrained language models. However, this comes at the cost of increased model parameters. In this work, we propose Adapted Multimodal BERT (AMB), a BERT-based architecture for multimodal tasks that uses a combination of adapter modules and intermediate fusion layers. The adapter adjusts the pretrained language model for the task at hand, while the fusion layers perform task-specific, layer-wise fusion of audio-visual information with textual BERT representations. During the adaptation process the pre-trained language model param…
