Multilingual neural machine translation has shown the capability of directly translating between language pairs unseen in training, i.e. zero-shot translation. Despite being conceptually attractive, it often suffers from low output quality. The difficulty of generalizing to new translation directions suggests the model representations are highly specific to those language pairs seen in training. We demonstrate that a main factor causing the language-specific representations is the positional correspondence to input tokens. We show that this can be easily alleviated by removing residual connections in an encoder layer. With this modification, we gain up to 18.5 BLEU points on zero-shot translation while retaining quality on supervised directions. The improvements are particularly prominent between related languages, where our proposed model outperforms pivot-based translation. Moreover, our approach allows easy integration of new languages, which substantially expands translation coverage. By thorough inspections of the hidden layer outputs, we show that our approach indeed leads to more language-independent representations.
Video-guided machine translation as one of multimodal neural machine translation tasks targeting on generating high-quality text translation by tangibly engaging both video and text. In this work, we presented our video-guided machine translation system in approaching the Video-guided Machine Translation Challenge 2020. This system employs keyframe-based video feature extractions along with the video feature positional encoding. In the evaluation phase, our system scored 36.60 corpus-level BLEU-4 and achieved the 1st place on the Video-guided Machine Translation Challenge 2020.
NTT Communication Science Laboratories（NTT通信科学实验室）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）
Non-autoregressive neural machine translation (NAT) usually employs sequence-level knowledge distillation using autoregressive neural machine translation (AT) as its teacher model. However, a NAT model often outputs shorter sentences than an AT model. In this work, we propose sequence-level knowledge distillation (SKD) using perturbed length-aware positional encoding and apply it to a student model, the Levenshtein Transformer. Our method outperformed a standard Levenshtein Transformer by 2.5 points in bilingual evaluation understudy (BLEU) at maximum in a WMT14 German to English translation. …
Translation Heads: Disentangling meaning from language in LLM-based machine translation
Department of XXX, University of YYY, Location, Country（XXX系，YYY大学，地点，国家）；School of ZZZ, Institute of WWW, Location, Country（ZZZ学院，WWW研究所，地点，国家）；Inria, Paris, France（Inria，巴黎，法国）
Recent work has shown that a multilingual neural machine translation (NMT) model can be used to judge how well a sentence paraphrases another sentence in the same language (Thompson and Post, 2020); however, attempting to generate paraphrases from such a model using standard beam search produces trivial copies or near copies. We introduce a simple paraphrase generation algorithm which discourages the production of n-grams that are present in the input. Our approach enables paraphrase generation in many languages from a single multilingual NMT model. Furthermore, the amount of lexical diversity…
Instituto de Telecomunicações（电信研究所）；Unbabel；INESC-ID（里斯本系统与计算机工程研究所）；Instituto Superior Técnico（高等技术学院）；LUMLIS (Lisbon ELLIS Unit)（LUMLIS（里斯本ELLIS单元））
Trainable evaluation metrics for machine translation (MT) exhibit strong correlation with human judgements, but they are often hard to interpret and might produce unreliable scores under noisy or out-of-domain data. Recent work has attempted to mitigate this with simple uncertainty quantification techniques (Monte Carlo dropout and deep ensembles), however these techniques (as we show) are limited in several ways -- for example, they are unable to distinguish between different kinds of uncertainty, and they are time and memory consuming. In this paper, we propose more powerful and efficient un…
In 2018, Mikolov et al. introduced the positional language model, which has characteristics of attention-based neural machine translation models and which achieved state-of-the-art performance on the intrinsic word analogy task. However, the positional model is not practically fast and it has never been evaluated on qualitative criteria or extrinsic tasks. We propose a constrained positional model, which adapts the sparse attention mechanism from neural machine translation to improve the speed of the positional model. We evaluate the positional and constrained positional models on three novel …
Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Key Laboratory of Intelligent Information Processing（智能信息处理重点实验室）；Key Laboratory of AI Safety, Chinese Academy of Sciences（中国科学院人工智能安全重点实验室）
Most online message threads inherently will be cluttered and any new user or an existing user visiting after a hiatus will have a difficult time understanding whats being discussed in the thread. Similarly cluttered responses in a message thread makes analyzing the messages a difficult problem. The need for disentangling the clutter is much higher when the platform where the discussion is taking place does not provide functions to retrieve reply relations of the messages. This introduces an interesting problem to which \cite{wang2011learning} phrases as a structural learning problem. We create…
University of Melbourne（墨尔本大学）；Microsoft Research（微软研究院）；Carnegie Mellon University（卡内基梅隆大学）；Monash University（莫纳什大学）
Neural encoder-decoder models of machine translation have achieved impressive results, rivalling traditional translation models. However their modelling formulation is overly simplistic, and omits several key inductive biases built into traditional models. In this paper we extend the attentional neural translation model to include structural biases from word based alignment models, including positional bias, Markov conditioning, fertility and agreement over translation directions. We show improvements over a baseline attentional model and standard phrase-based model over several language pairs…
University of Macau（澳门大学）；Tencent AI Lab（腾讯人工智能实验室）
Self-attention networks (SAN) have attracted a lot of interests due to their high parallelization and strong performance on a variety of NLP tasks, e.g. machine translation. Due to the lack of recurrence structure such as recurrent neural networks (RNN), SAN is ascribed to be weak at learning positional information of words for sequence modeling. However, neither this speculation has been empirically confirmed, nor explanations for their strong performances on machine translation tasks when "lacking positional information" have been explored. To this end, we propose a novel word reordering det…
Transformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus simultaneously on different parts of the input. However, recent works have shown that most attention heads learn simple, and often redundant, positional patterns. In this paper, we propose to replace all but one attention head of each encoder layer with simple fixed -- non-learnable -- attentive patterns that are solely based on position and do not require any external knowledge. Our …
Shanghai Jiao Tong University（上海交通大学）；National Institute of Information and Communications Technology (NICT)（日本信息通信研究机构（NICT））
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 posi…
Uppsala University（乌普萨拉大学）；University of Edinburgh（爱丁堡大学）；University of Zurich（苏黎世大学）
In this paper, we try to understand neural machine translation (NMT) via simplifying NMT architectures and training encoder-free NMT models. In an encoder-free model, the sums of word embeddings and positional embeddings represent the source. The decoder is a standard Transformer or recurrent neural network that directly attends to embeddings via attention mechanisms. Experimental results show (1) that the attention mechanism in encoder-free models acts as a strong feature extractor, (2) that the word embeddings in encoder-free models are competitive to those in conventional models, (3) that n…
The recent advances introduced by neural machine translation (NMT) are rapidly expanding the application fields of machine translation, as well as reshaping the quality level to be targeted. In particular, if translations have to fit some given layout, quality should not only be measured in terms of adequacy and fluency, but also length. Exemplary cases are the translation of document files, subtitles, and scripts for dubbing, where the output length should ideally be as close as possible to the length of the input text. This paper addresses for the first time, to the best of our knowledge, th…
Apple（苹果公司）；Facebook AI Research（Facebook 人工智能研究院）；Herophilus, Inc.（Herophilus 公司）
Without positional information, attention-based Transformer neural networks are permutation-invariant. Absolute or relative positional embeddings are the most popular ways to feed Transformer models with positional information. Absolute positional embeddings are simple to implement, but suffer from generalization issues when evaluating on sequences longer than seen at training time. Relative positions are more robust to input length change, but are more complex to implement and yield inferior model throughput due to extra computational and memory costs. In this paper, we propose an augmentatio…
University of Edinburgh（爱丁堡大学）；Facebook AI（脸书人工智能研究院）
There has been recent success in pre-training on monolingual data and fine-tuning on Machine Translation (MT), but it remains unclear how to best leverage a pre-trained model for a given MT task. This paper investigates the benefits and drawbacks of freezing parameters, and adding new ones, when fine-tuning a pre-trained model on MT. We focus on 1) Fine-tuning a model trained only on English monolingual data, BART. 2) Fine-tuning a model trained on monolingual data from 25 languages, mBART. For BART we get the best performance by freezing most of the model parameters, and adding extra position…
Tsinghua University（清华大学）；Chinese Academy of Medical Sciences/Peking Union Medical College（中国医学科学院/北京协和医学院）
Objective: Today's neural machine translation (NMT) can achieve near human-level translation quality and greatly facilitates international communications, but the lack of parallel corpora poses a key problem to the development of translation systems for highly specialized domains, such as biomedicine. This work presents an unsupervised algorithm for deriving parallel corpora from document-level translations by using sentence alignment and explores how training materials affect the performance of biomedical NMT systems. Materials and Methods: Document-level translations are mixed to train bilin…
University Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔理工学院）；LIG（格勒诺布尔信息实验室）
The main aim of this paper is to investigate automatic quality assessment for spoken language translation (SLT). More precisely, we investigate SLT errors that can be due to transcription (ASR) or to translation (MT) modules. This paper investigates automatic detection of SLT errors using a single classifier based on joint ASR and MT features. We evaluate both 2-class (good/bad) and 3-class (good/badASR/badMT ) labeling tasks. The 3-class problem necessitates to disentangle ASR and MT errors in the speech translation output and we propose two label extraction methods for this non trivial step.…
CONFLATOR: Incorporating Switching Point based Rotatory Positional Encodings for Code-Mixed Language Modeling
San Diego State University（圣地亚哥州立大学）；San Jose State University（圣何塞州立大学）；Wipro AI Labs（威普罗人工智能实验室）；University of California Los Angeles（加利福尼亚大学洛杉矶分校）；Stanford University（斯坦福大学）；University of South Carolina（南卡罗来纳大学）；Amazon AI（亚马逊人工智能）
National Institute of Information and Communications Technology (NICT)（信息通信研究机构（NICT））
In Transformer-based neural machine translation (NMT), the positional encoding mechanism helps the self-attention networks to learn the source representation with order dependency, which makes the Transformer-based NMT achieve state-of-the-art results for various translation tasks. However, Transformer-based NMT only adds representations of positions sequentially to word vectors in the input sentence and does not explicitly consider reordering information in this sentence. In this paper, we first empirically investigate the relationship between source reordering information and translation per…
The University of Sydney（悉尼大学）；Tencent AI Lab（腾讯人工智能实验室）
Position encoding (PE), an essential part of self-attention networks (SANs), is used to preserve the word order information for natural language processing tasks, generating fixed position indices for input sequences. However, in cross-lingual scenarios, e.g. machine translation, the PEs of source and target sentences are modeled independently. Due to word order divergences in different languages, modeling the cross-lingual positional relationships might help SANs tackle this problem. In this paper, we augment SANs with \emph{cross-lingual position representations} to model the bilingually awa…
The performance of Neural Machine Translation (NMT) depends significantly on the size of the available parallel corpus. Due to this fact, low resource language pairs demonstrate low translation performance compared to high resource language pairs. The translation quality further degrades when NMT is performed for morphologically rich languages. Even though the web contains a large amount of information, most people in Sri Lanka are unable to read and understand English properly. Therefore, there is a huge requirement of translating English content to local languages to share information among …
The University of Hong Kong（香港大学）；Microsoft Research（微软研究院）；Shanghai University of Finance and Economics（上海财经大学）；Texas A&M University（德州农工大学）
This paper demonstrates that multilingual pretraining and multilingual fine-tuning are both critical for facilitating cross-lingual transfer in zero-shot translation, where the neural machine translation (NMT) model is tested on source languages unseen during supervised training. Following this idea, we present SixT+, a strong many-to-English NMT model that supports 100 source languages but is trained with a parallel dataset in only six source languages. SixT+ initializes the decoder embedding and the full encoder with XLM-R large and then trains the encoder and decoder layers with a simple tw…
Directly training a document-to-document (Doc2Doc) neural machine translation (NMT) via Transformer from scratch, especially on small datasets usually fails to converge. Our dedicated probing tasks show that 1) both the absolute position and relative position information gets gradually weakened or even vanished once it reaches the upper encoder layers, and 2) the vanishing of absolute position information in encoder output causes the training failure of Doc2Doc NMT. To alleviate this problem, we propose a position-aware Transformer (P-Transformer) to enhance both the absolute and relative posi…
Carnegie Mellon University（卡内基梅隆大学）；Instituto Superior Técnico（高等技术学院）；Instituto de Telecomunicações（电信研究所）；Unbabel
Context-aware machine translation models are designed to leverage contextual information, but often fail to do so. As a result, they inaccurately disambiguate pronouns and polysemous words that require context for resolution. In this paper, we ask several questions: What contexts do human translators use to resolve ambiguous words? Are models paying large amounts of attention to the same context? What if we explicitly train them to do so? To answer these questions, we introduce SCAT (Supporting Context for Ambiguous Translations), a new English-French dataset comprising supporting context word…
The Insertion Transformer is well suited for long form text generation due to its parallel generation capabilities, requiring $O(\log_2 n)$ generation steps to generate $n$ tokens. However, modeling long sequences is difficult, as there is more ambiguity captured in the attention mechanism. This work proposes the Big Bidirectional Insertion Representations for Documents (Big BIRD), an insertion-based model for document-level translation tasks. We scale up the insertion-based models to long form documents. Our key contribution is introducing sentence alignment via sentence-positional embeddings…
Transformers are being used extensively across several sequence modeling tasks. Significant research effort has been devoted to experimentally probe the inner workings of Transformers. However, our conceptual and theoretical understanding of their power and inherent limitations is still nascent. In particular, the roles of various components in Transformers such as positional encodings, attention heads, residual connections, and feedforward networks, are not clear. In this paper, we take a step towards answering these questions. We analyze the computational power as captured by Turing-complete…
We propose a machine-translation approach to automatically generate a playlist title from a set of music tracks. We take a sequence of track IDs as input and a sequence of words in a playlist title as output, adapting the sequence-to-sequence framework based on Recurrent Neural Network (RNN) and Transformer to the music data. Considering the orderless nature of music tracks in a playlist, we propose two techniques that remove the order of the input sequence. One is data augmentation by shuffling and the other is deleting the positional encoding. We also reorganize the existing music playlist d…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Simultaneous machine translation (SiMT) starts translating while receiving the streaming source inputs, and hence the source sentence is always incomplete during translating. Different from the full-sentence MT using the conventional seq-to-seq architecture, SiMT often applies prefix-to-prefix architecture, which forces each target word to only align with a partial source prefix to adapt to the incomplete source in streaming inputs. However, the source words in the front positions are always illusoryly considered more important since they appear in more prefixes, resulting in position bias, wh…
Carnegie Mellon University（卡内基梅隆大学）；University of California, Berkeley（加州大学伯克利分校）；Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）
Autoregressive sequence models achieve state-of-the-art performance in domains like machine translation. However, due to the autoregressive factorization nature, these models suffer from heavy latency during inference. Recently, non-autoregressive sequence models were proposed to reduce the inference time. However, these models assume that the decoding process of each token is conditionally independent of others. Such a generation process sometimes makes the output sentence inconsistent, and thus the learned non-autoregressive models could only achieve inferior accuracy compared to their autor…
ADAT: Time-Series-Aware Adaptive Transformer Architecture for Sign Language Translation
College of Information Technology, United Arab Emirates University（阿联酋大学信息技术学院）；Emirates Center for Mobility Research, United Arab Emirates University（阿联酋大学阿联酋移动性研究中心）
The main aim of translation is an accurate transfer of meaning so that the result is not only grammatically and lexically correct but also communicatively adequate. This paper stresses the need for discourse analysis the aim of which is to preserve the communicative meaning in English--Polish machine translation. Unlike English, which is a positional language with word order grammatically determined, Polish displays a strong tendency to order constituents according to their degree of salience, so that the most informationally salient elements are placed towards the end of the clause regardless…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Johns Hopkins University（约翰斯·霍普金斯大学）；Maastricht University（马斯特里赫特大学）；Carnegie Mellon University（卡内基梅隆大学）
Transformer models are powerful sequence-to-sequence architectures that are capable of directly mapping speech inputs to transcriptions or translations. However, the mechanism for modeling positions in this model was tailored for text modeling, and thus is less ideal for acoustic inputs. In this work, we adapt the relative position encoding scheme to the Speech Transformer, where the key addition is relative distance between input states in the self-attention network. As a result, the network can better adapt to the variable distributions present in speech data. Our experiments show that our r…
Mechanisms for encoding positional information are central for transformer-based language models. In this paper, we analyze the position embeddings of existing language models, finding strong evidence of translation invariance, both for the embeddings themselves and for their effect on self-attention. The degree of translation invariance increases during training and correlates positively with model performance. Our findings lead us to propose translation-invariant self-attention (TISA), which accounts for the relative position between tokens in an interpretable fashion without needing convent…
To participate in the Isometric Spoken Language Translation Task of the IWSLT 2022 evaluation, constrained condition, AppTek developed neural Transformer-based systems for English-to-German with various mechanisms of length control, ranging from source-side and target-side pseudo-tokens to encoding of remaining length in characters that replaces positional encoding. We further increased translation length compliance by sentence-level selection of length-compliant hypotheses from different system variants, as well as rescoring of N-best candidates from a single system. Length-compliant back-tra…
Hong Kong Applied Science and Technology Research Institute Company Limited（香港应用科技研究院有限公司）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
The Transformer based neural networks have been showing significant advantages on most evaluations of various natural language processing and other sequence-to-sequence tasks due to its inherent architecture based superiorities. Although the main architecture of the Transformer has been continuously being explored, little attention was paid to the positional encoding module. In this paper, we enhance the sinusoidal positional encoding algorithm by maximizing the variances between encoded consecutive positions to obtain additional promotion. Furthermore, we propose an augmented Transformer arch…
