PyTorchKR Papers

최신 논문

총 5,082편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2110.05571

SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition

The Transformer architecture has been well adopted as a dominant architecture in most sequence transduction tasks including automatic speech recognition (ASR), since its attention mechanism excels in capturing long-range dependencies. While models built solely upon attention can be better parallelized than regular RNN, a novel network architecture, SRU++, was recently proposed. By combining the fast recurrence and attention mechanism, SRU++ exhibits strong capability in sequence modeling and achieves near-state-of-the-art results in various language modeling and machine translation tasks with improved compute efficiency. In this work, we present the advantages of applying SRU++ in ASR tasks by comparing with Conformer across multiple ASR benchmarks and study how the benefits can be generalized to long-form speech inputs. On the popular LibriSpeech benchmark, our SRU++ model achieves 2.0% / 4.7% WER on test-clean / test-other, showing competitive performances compared with the state-of-the-art Conformer encoder under the same set-up. Specifically, SRU++ can surpass Conformer on long-form speech input with a large margin, based on our analysis.

arXiv:2110.05847

Evaluation of Abstractive Summarisation Models with Machine Translation in Deliberative Processes

We present work on summarising deliberative processes for non-English languages. Unlike commonly studied datasets, such as news articles, this deliberation dataset reflects difficulties of combining multiple narratives, mostly of poor grammatical quality, in a single text. We report an extensive evaluation of a wide range of abstractive summarisation models in combination with an off-the-shelf machine translation model. Texts are translated into English, summarised, and translated back to the original language. We obtain promising results regarding the fluency, consistency and relevance of the summaries produced. Our approach is easy to implement for many languages for production purposes by simply changing the translation model.

arXiv:2110.05722공식 코드 · Papers with Code

LightSeq2: Accelerated Training for Transformer-based Models on GPUs

Transformer-based neural models are used in many AI applications. Training these models is expensive, as it takes huge GPU resources and long duration. It is challenging because typical data like sentences have variable lengths, and Transformer's computation patterns are more complex than convolutional neural networks. Existing systems either only focus on model inference or optimization for only BERT-like encoder models. In this paper, we present LightSeq2, a system to accelerate training for a general family of Transformer models on GPUs. We propose a series of GPU optimization techniques tailored to the specific computation flow and memory access patterns of Transformer models. LightSeq2 supports many model architectures, including BERT (encoder-only), GPT (decoder-only), Transformer (encoder-decoder), and vision Transformer. Our experiments for a variety of models and benchmarks show that LightSeq2 is consistently faster (1.4-3.5x) than previous systems on different GPUs. In particular, it gains 308% training speedup compared with existing systems on a large public machine translation benchmark (WMT14 English-German).

arXiv:2110.05423

Using Document Similarity Methods to create Parallel Datasets for Code Translation

Translating source code from one programming language to another is a critical, time-consuming task in modernizing legacy applications and codebases. Recent work in this space has drawn inspiration from the software naturalness hypothesis by applying natural language processing techniques towards automating the code translation task. However, due to the paucity of parallel data in this domain, supervised techniques have only been applied to a limited set of popular programming languages. To bypass this limitation, unsupervised neural machine translation techniques have been proposed to learn code translation using only monolingual corpora. In this work, we propose to use document similarity methods to create noisy parallel datasets of code, thus enabling supervised techniques to be applied for automated code translation without having to rely on the availability or expensive curation of parallel code datasets. We explore the noise tolerance of models trained on such automatically-created datasets and show that these models perform comparably to models trained on ground truth for reasonable levels of noise. Finally, we exhibit the practical utility of the proposed method by creating parallel datasets for languages beyond the ones explored in prior work, thus expanding the set of programming languages for automated code translation.

arXiv:2110.05151공식 코드 · Papers with Code

WeTS: A Benchmark for Translation Suggestion

Translation Suggestion (TS), which provides alternatives for specific words or phrases given the entire documents translated by machine translation (MT) \cite{lee2021intellicat}, has been proven to play a significant role in post editing (PE). However, there is still no publicly available data set to support in-depth research for this problem, and no reproducible experimental results can be followed by researchers in this community. To break this limitation, we create a benchmark data set for TS, called \emph{WeTS}, which contains golden corpus annotated by expert translators on four translation directions. Apart from the human-annotated golden corpus, we also propose several novel methods to generate synthetic corpus which can substantially improve the performance of TS. With the corpus we construct, we introduce the Transformer-based model for TS, and experimental results show that our model achieves State-Of-The-Art (SOTA) results on all four translation directions, including English-to-German, German-to-English, Chinese-to-English and English-to-Chinese. Codes and corpus can be found at \url{https://github.com/ZhenYangIACAS/WeTS.git}.

arXiv:2110.04655공식 코드 · Papers with Code

Disentangled Sequence to Sequence Learning for Compositional Generalization

There is mounting evidence that existing neural network models, in particular the very popular sequence-to-sequence architecture, struggle to systematically generalize to unseen compositions of seen components. We demonstrate that one of the reasons hindering compositional generalization relates to representations being entangled. We propose an extension to sequence-to-sequence models which encourages disentanglement by adaptively re-encoding (at each time step) the source input. Specifically, we condition the source representations on the newly decoded target context which makes it easier for the encoder to exploit specialized information for each prediction rather than capturing it all in a single forward pass. Experimental results on semantic parsing and machine translation empirically show that our proposal delivers more disentangled representations and better generalization.

arXiv:2110.05213공식 코드 · Papers with Code

It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation Data

Most existing simultaneous machine translation (SiMT) systems are trained and evaluated on offline translation corpora. We argue that SiMT systems should be trained and tested on real interpretation data. To illustrate this argument, we propose an interpretation test set and conduct a realistic evaluation of SiMT trained on offline translations. Our results, on our test set along with 3 existing smaller scale language pairs, highlight the difference of up-to 13.83 BLEU score when SiMT models are evaluated on translation vs interpretation data. In the absence of interpretation training data, we propose a translation-to-interpretation (T2I) style transfer method which allows converting existing offline translations into interpretation-style data, leading to up-to 2.8 BLEU improvement. However, the evaluation gap remains notable, calling for constructing large-scale interpretation corpora better suited for evaluating and developing SiMT systems.

arXiv:2110.04366공식 코드 · Papers with Code

Towards a Unified View of Parameter-Efficient Transfer Learning

Fine-tuning large pre-trained language models on downstream tasks has become the de-facto learning paradigm in NLP. However, conventional approaches fine-tune all the parameters of the pre-trained model, which becomes prohibitive as the model size and the number of tasks grow. Recent work has proposed a variety of parameter-efficient transfer learning methods that only fine-tune a small number of (extra) parameters to attain strong performance. While effective, the critical ingredients for success and the connections among the various methods are poorly understood. In this paper, we break down the design of state-of-the-art parameter-efficient transfer learning methods and present a unified framework that establishes connections between them. Specifically, we re-frame them as modifications to specific hidden states in pre-trained models, and define a set of design dimensions along which different methods vary, such as the function to compute the modification and the position to apply the modification. Through comprehensive empirical studies across machine translation, text summarization, language understanding, and text classification benchmarks, we utilize the unified view to identify important design choices in previous methods. Furthermore, our unified framework enables the transfer of design elements across different approaches, and as a result we are able to instantiate new parameter-efficient fine-tuning methods that tune less parameters than previous methods while being more effective, achieving comparable results to fine-tuning all parameters on all four tasks.

arXiv:2110.05448

Unsupervised Neural Machine Translation with Generative Language Models Only

We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models. Our method consists of three steps: few-shot amplification, distillation, and backtranslation. We first use the zero-shot translation ability of large pre-trained language models to generate translations for a small set of unlabeled sentences. We then amplify these zero-shot translations by using them as few-shot demonstrations for sampling a larger synthetic dataset. This dataset is distilled by discarding the few-shot demonstrations and then fine-tuning. During backtranslation, we repeatedly generate translations for a set of inputs and then fine-tune a single language model on both directions of the translation task at once, ensuring cycle-consistency by swapping the roles of gold monotext and generated translations when fine-tuning. By using our method to leverage GPT-3's zero-shot translation capability, we achieve a new state-of-the-art in unsupervised translation on the WMT14 English-French benchmark, attaining a BLEU score of 42.1.

arXiv:2110.03847

Machine Translation Verbosity Control for Automatic Dubbing

Automatic dubbing aims at seamlessly replacing the speech in a video document with synthetic speech in a different language. The task implies many challenges, one of which is generating translations that not only convey the original content, but also match the duration of the corresponding utterances. In this paper, we focus on the problem of controlling the verbosity of machine translation output, so that subsequent steps of our automatic dubbing pipeline can generate dubs of better quality. We propose new methods to control the verbosity of MT output and compare them against the state of the art with both intrinsic and extrinsic evaluations. For our experiments we use a public data set to dub English speeches into French, Italian, German and Spanish. Finally, we report extensive subjective tests that measure the impact of MT verbosity control on the final quality of dubbed video clips.

arXiv:2110.04260공식 코드 · Papers with Code

Taming Sparsely Activated Transformer with Stochastic Experts

Sparsely activated models (SAMs), such as Mixture-of-Experts (MoE), can easily scale to have outrageously large amounts of parameters without significant increase in computational cost. However, SAMs are reported to be parameter inefficient such that larger models do not always lead to better performance. While most on-going research focuses on improving SAMs models by exploring methods of routing inputs to experts, our analysis reveals that such research might not lead to the solution we expect, i.e., the commonly-used routing methods based on gating mechanisms do not work better than randomly routing inputs to experts. In this paper, we propose a new expert-based model, THOR (Transformer witH StOchastic ExpeRts). Unlike classic expert-based models, such as the Switch Transformer, experts in THOR are randomly activated for each input during training and inference. THOR models are trained using a consistency regularized loss, where experts learn not only from training data but also from other experts as teachers, such that all the experts make consistent predictions. We validate the effectiveness of THOR on machine translation tasks. Results show that THOR models are more parameter efficient in that they significantly outperform the Transformer and MoE models across various settings. For example, in multilingual translation, THOR outperforms the Switch Transformer by 2 BLEU scores, and obtains the same BLEU score as that of a state-of-the-art MoE model that is 18 times larger. Our code is publicly available at: https://github.com/microsoft/Stochastic-Mixture-of-Experts.

arXiv:2110.03067공식 코드 · Papers with Code

On Neurons Invariant to Sentence Structural Changes in Neural Machine Translation

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 translation model. We analyze neuron-level correlation of activations between paraphrases while discussing the methodology challenges and the need for confound analysis to isolate the effects of shallow cues. We find that similarity between activation patterns can be mostly accounted for by similarity in word choice and sentence length. Following that, we manipulate neuron activations to control the syntactic form of the output. We show this intervention to be somewhat successful, indicating that deep models capture sentence-structure distinctions, despite finding no such indication at the neuron level. To conduct our experiments, we develop a semi-automatic method to generate meaning-preserving minimal pair paraphrases (active-passive voice and adverbial clause-noun phrase) and compile a corpus of such pairs.

arXiv:2110.03054

On the Privacy Risks of Deploying Recurrent Neural Networks in Machine Learning Models

We study the privacy implications of training recurrent neural networks (RNNs) with sensitive training datasets. Considering membership inference attacks (MIAs), which aim to infer whether or not specific data records have been used in training a given machine learning model, we provide empirical evidence that a neural network's architecture impacts its vulnerability to MIAs. In particular, we demonstrate that RNNs are subject to a higher attack accuracy than feed-forward neural network (FFNN) counterparts. Additionally, we study the effectiveness of two prominent mitigation methods for preempting MIAs, namely weight regularization and differential privacy. For the former, we empirically demonstrate that RNNs may only benefit from weight regularization marginally as opposed to FFNNs. For the latter, we find that enforcing differential privacy through either of the following two methods leads to a less favorable privacy-utility trade-off in RNNs than alternative FFNNs: (i) adding Gaussian noise to the gradients calculated during training as a part of the so-called DP-SGD algorithm and (ii) adding Gaussian noise to the trainable parameters as a part of a post-training mechanism that we propose. As a result, RNNs can also be less amenable to mitigation methods, bringing us to the conclusion that the privacy risks pertaining to the recurrent architecture are higher than the feed-forward counterparts.

arXiv:2110.03036공식 코드 · Papers with Code

The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation

A "bigger is better" explosion in the number of parameters in deep neural networks has made it increasingly challenging to make state-of-the-art networks accessible in compute-restricted environments. Compression techniques have taken on renewed importance as a way to bridge the gap. However, evaluation of the trade-offs incurred by popular compression techniques has been centered on high-resource datasets. In this work, we instead consider the impact of compression in a data-limited regime. We introduce the term low-resource double bind to refer to the co-occurrence of data limitations and compute resource constraints. This is a common setting for NLP for low-resource languages, yet the trade-offs in performance are poorly studied. Our work offers surprising insights into the relationship between capacity and generalization in data-limited regimes for the task of machine translation. Our experiments on magnitude pruning for translations from English into Yoruba, Hausa, Igbo and German show that in low-resource regimes, sparsity preserves performance on frequent sentences but has a disparate impact on infrequent ones. However, it improves robustness to out-of-distribution shifts, especially for datasets that are very distinct from the training distribution. Our findings suggest that sparsity can play a beneficial role at curbing memorization of low frequency attributes, and therefore offers a promising solution to the low-resource double bind.

arXiv:2110.02869

Sequence-to-Sequence Lexical Normalization with Multilingual Transformers

Current benchmark tasks for natural language processing contain text that is qualitatively different from the text used in informal day to day digital communication. This discrepancy has led to severe performance degradation of state-of-the-art NLP models when fine-tuned on real-world data. One way to resolve this issue is through lexical normalization, which is the process of transforming non-standard text, usually from social media, into a more standardized form. In this work, we propose a sentence-level sequence-to-sequence model based on mBART, which frames the problem as a machine translation problem. As the noisy text is a pervasive problem across languages, not just English, we leverage the multi-lingual pre-training of mBART to fine-tune it to our data. While current approaches mainly operate at the word or subword level, we argue that this approach is straightforward from a technical standpoint and builds upon existing pre-trained transformer networks. Our results show that while word-level, intrinsic, performance evaluation is behind other methods, our model improves performance on extrinsic, downstream tasks through normalization compared to models operating on raw, unprocessed, social media text.

arXiv:2110.02791

Spell my name: keyword boosted speech recognition

Recognition of uncommon words such as names and technical terminology is important to understanding conversations in context. However, the ability to recognise such words remains a challenge in modern automatic speech recognition (ASR) systems. In this paper, we propose a simple but powerful ASR decoding method that can better recognise these uncommon keywords, which in turn enables better readability of the results. The method boosts the probabilities of given keywords in a beam search based on acoustic model predictions. The method does not require any training in advance. We demonstrate the effectiveness of our method on the LibriSpeeech test sets and also internal data of real-world conversations. Our method significantly boosts keyword accuracy on the test sets, while maintaining the accuracy of the other words, and as well as providing significant qualitative improvements. This method is applicable to other tasks such as machine translation, or wherever unseen and difficult keywords need to be recognised in beam search.

arXiv:2110.02488

ABC: Attention with Bounded-memory Control

Transformer architectures have achieved state-of-the-art results on a variety of sequence modeling tasks. However, their attention mechanism comes with a quadratic complexity in sequence lengths, making the computational overhead prohibitive, especially for long sequences. Attention context can be seen as a random-access memory with each token taking a slot. Under this perspective, the memory size grows linearly with the sequence length, and so does the overhead of reading from it. One way to improve the efficiency is to bound the memory size. We show that disparate approaches can be subsumed into one abstraction, attention with bounded-memory control (ABC), and they vary in their organization of the memory. ABC reveals new, unexplored possibilities. First, it connects several efficient attention variants that would otherwise seem apart. Second, this abstraction gives new insights--an established approach (Wang et al., 2020b) previously thought to be not applicable in causal attention, actually is. Last, we present a new instance of ABC, which draws inspiration from existing ABC approaches, but replaces their heuristic memory-organizing functions with a learned, contextualized one. Our experiments on language modeling, machine translation, and masked language model finetuning show that our approach outperforms previous efficient attention models; compared to the strong transformer baselines, it significantly improves the inference time and space efficiency with no or negligible accuracy loss.

arXiv:2110.02861공식 코드 · Papers with Code

8-bit Optimizers via Block-wise Quantization

Stateful optimizers maintain gradient statistics over time, e.g., the exponentially smoothed sum (SGD with momentum) or squared sum (Adam) of past gradient values. This state can be used to accelerate optimization compared to plain stochastic gradient descent but uses memory that might otherwise be allocated to model parameters, thereby limiting the maximum size of models trained in practice. In this paper, we develop the first optimizers that use 8-bit statistics while maintaining the performance levels of using 32-bit optimizer states. To overcome the resulting computational, quantization, and stability challenges, we develop block-wise dynamic quantization. Block-wise quantization divides input tensors into smaller blocks that are independently quantized. Each block is processed in parallel across cores, yielding faster optimization and high precision quantization. To maintain stability and performance, we combine block-wise quantization with two additional changes: (1) dynamic quantization, a form of non-linear optimization that is precise for both large and small magnitude values, and (2) a stable embedding layer to reduce gradient variance that comes from the highly non-uniform distribution of input tokens in language models. As a result, our 8-bit optimizers maintain 32-bit performance with a small fraction of the memory footprint on a range of tasks, including 1.5B parameter language modeling, GLUE finetuning, ImageNet classification, WMT'14 machine translation, MoCo v2 contrastive ImageNet pretraining+finetuning, and RoBERTa pretraining, without changes to the original optimizer hyperparameters. We open-source our 8-bit optimizers as a drop-in replacement that only requires a two-line code change.

arXiv:2110.01938공식 코드 · Papers with Code

Sicilian Translator: A Recipe for Low-Resource NMT

With 17,000 pairs of Sicilian-English translated sentences, Arba Sicula developed the first neural machine translator for the Sicilian language. Using small subword vocabularies, we trained small Transformer models with high dropout parameters and achieved BLEU scores in the upper 20s. Then we supplemented our dataset with backtranslation and multilingual translation and pushed our scores into the mid 30s. We also attribute our success to incorporating theoretical information in our dataset. Prior to training, we biased the subword vocabulary towards the desinences one finds in a textbook. And we included textbook exercises in our dataset.

arXiv:2110.01811공식 코드 · Papers with Code

On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation

Pre-training (PT) and back-translation (BT) are two simple and powerful methods to utilize monolingual data for improving the model performance of neural machine translation (NMT). This paper takes the first step to investigate the complementarity between PT and BT. We introduce two probing tasks for PT and BT respectively and find that PT mainly contributes to the encoder module while BT brings more benefits to the decoder. Experimental results show that PT and BT are nicely complementary to each other, establishing state-of-the-art performances on the WMT16 English-Romanian and English-Russian benchmarks. Through extensive analyses on sentence originality and word frequency, we also demonstrate that combining Tagged BT with PT is more helpful to their complementarity, leading to better translation quality. Source code is freely available at https://github.com/SunbowLiu/PTvsBT.