PyTorchKR Papers

최신 논문

총 5,082편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2105.09501공식 코드 · Papers with Code

Contrastive Learning for Many-to-many Multilingual Neural Machine Translation

Existing multilingual machine translation approaches mainly focus on English-centric directions, while the non-English directions still lag behind. In this work, we aim to build a many-to-many translation system with an emphasis on the quality of non-English language directions. Our intuition is based on the hypothesis that a universal cross-language representation leads to better multilingual translation performance. To this end, we propose mRASP2, a training method to obtain a single unified multilingual translation model. mRASP2 is empowered by two techniques: a) a contrastive learning scheme to close the gap among representations of different languages, and b) data augmentation on both multiple parallel and monolingual data to further align token representations. For English-centric directions, mRASP2 outperforms existing best unified model and achieves competitive or even better performance than the pre-trained and fine-tuned model mBART on tens of WMT's translation directions. For non-English directions, mRASP2 achieves an improvement of average 10+ BLEU compared with the multilingual Transformer baseline. Code, data and trained models are available at https://github.com/PANXiao1994/mRASP2.

arXiv:2105.09259공식 코드 · Papers with Code

Learning Language Specific Sub-network for Multilingual Machine Translation

Multilingual neural machine translation aims at learning a single translation model for multiple languages. These jointly trained models often suffer from performance degradation on rich-resource language pairs. We attribute this degeneration to parameter interference. In this paper, we propose LaSS to jointly train a single unified multilingual MT model. LaSS learns Language Specific Sub-network (LaSS) for each language pair to counter parameter interference. Comprehensive experiments on IWSLT and WMT datasets with various Transformer architectures show that LaSS obtains gains on 36 language pairs by up to 1.2 BLEU. Besides, LaSS shows its strong generalization performance at easy extension to new language pairs and zero-shot translation.LaSS boosts zero-shot translation with an average of 8.3 BLEU on 30 language pairs. Codes and trained models are available at https://github.com/NLP-Playground/LaSS.

arXiv:2105.08840공식 코드 · Papers with Code

Training Heterogeneous Features in Sequence to Sequence Tasks: Latent Enhanced Multi-filter Seq2Seq Model

In language processing, training data with extremely large variance may lead to difficulty in the language model's convergence. It is difficult for the network parameters to adapt sentences with largely varied semantics or grammatical structures. To resolve this problem, we introduce a model that concentrates the each of the heterogeneous features in the input sentences. Building upon the encoder-decoder architecture, we design a latent-enhanced multi-filter seq2seq model (LEMS) that analyzes the input representations by introducing a latent space transformation and clustering. The representations are extracted from the final hidden state of the encoder and lie in the latent space. A latent space transformation is applied for enhancing the quality of the representations. Thus the clustering algorithm can easily separate samples based on the features of these representations. Multiple filters are trained by the features from their corresponding clusters, and the heterogeneity of the training data can be resolved accordingly. We conduct two sets of comparative experiments on semantic parsing and machine translation, using the Geo-query dataset and Multi30k English-French to demonstrate the enhancement our model has made respectively.

arXiv:2105.08807

Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixing

We describe models focused at the understudied problem of translating between monolingual and code-mixed language pairs. More specifically, we offer a wide range of models that convert monolingual English text into Hinglish (code-mixed Hindi and English). Given the recent success of pretrained language models, we also test the utility of two recent Transformer-based encoder-decoder models (i.e., mT5 and mBART) on the task finding both to work well. Given the paucity of training data for code-mixing, we also propose a dependency-free method for generating code-mixed texts from bilingual distributed representations that we exploit for improving language model performance. In particular, armed with this additional data, we adopt a curriculum learning approach where we first finetune the language models on synthetic data then on gold code-mixed data. We find that, although simple, our synthetic code-mixing method is competitive with (and in some cases is even superior to) several standard methods (backtranslation, method based on equivalence constraint theory) under a diverse set of conditions. Our work shows that the mT5 model, finetuned following the curriculum learning procedure, achieves best translation performance (12.67 BLEU). Our models place first in the overall ranking of the English-Hinglish official shared task.

arXiv:2105.08928공식 코드 · Papers with Code

Investigating Math Word Problems using Pretrained Multilingual Language Models

In this paper, we revisit math word problems~(MWPs) from the cross-lingual and multilingual perspective. We construct our MWP solvers over pretrained multilingual language models using sequence-to-sequence model with copy mechanism. We compare how the MWP solvers perform in cross-lingual and multilingual scenarios. To facilitate the comparison of cross-lingual performance, we first adapt the large-scale English dataset MathQA as a counterpart of the Chinese dataset Math23K. Then we extend several English datasets to bilingual datasets through machine translation plus human annotation. Our experiments show that the MWP solvers may not be transferred to a different language even if the target expressions have the same operator set and constants. But for both cross-lingual and multilingual cases, it can be better generalized if problem types exist on both source language and target language.

arXiv:2105.08504공식 코드 · Papers with Code

Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation

Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words, and shows poor robustness to copy noise in training data or domain shift. Recent work has tied these shortcomings to beam search -- the de facto standard inference algorithm in NMT -- and Eikema & Aziz (2020) propose to use Minimum Bayes Risk (MBR) decoding on unbiased samples instead. In this paper, we empirically investigate the properties of MBR decoding on a number of previously reported biases and failure cases of beam search. We find that MBR still exhibits a length and token frequency bias, owing to the MT metrics used as utility functions, but that MBR also increases robustness against copy noise in the training data and domain shift.

arXiv:2105.08351공식 코드 · Papers with Code

Solving the electronic Schrödinger equation for multiple nuclear geometries with weight-sharing deep neural networks

Accurate numerical solutions for the Schr\"odinger equation are of utmost importance in quantum chemistry. However, the computational cost of current high-accuracy methods scales poorly with the number of interacting particles. Combining Monte Carlo methods with unsupervised training of neural networks has recently been proposed as a promising approach to overcome the curse of dimensionality in this setting and to obtain accurate wavefunctions for individual molecules at a moderately scaling computational cost. These methods currently do not exploit the regularity exhibited by wavefunctions with respect to their molecular geometries. Inspired by recent successful applications of deep transfer learning in machine translation and computer vision tasks, we attempt to leverage this regularity by introducing a weight-sharing constraint when optimizing neural network-based models for different molecular geometries. That is, we restrict the optimization process such that up to 95 percent of weights in a neural network model are in fact equal across varying molecular geometries. We find that this technique can accelerate optimization when considering sets of nuclear geometries of the same molecule by an order of magnitude and that it opens a promising route towards pre-trained neural network wavefunctions that yield high accuracy even across different molecules.

arXiv:2105.07622

Ensemble-based Transfer Learning for Low-resource Machine Translation Quality Estimation

Quality Estimation (QE) of Machine Translation (MT) is a task to estimate the quality scores for given translation outputs from an unknown MT system. However, QE scores for low-resource languages are usually intractable and hard to collect. In this paper, we focus on the Sentence-Level QE Shared Task of the Fifth Conference on Machine Translation (WMT20), but in a more challenging setting. We aim to predict QE scores of given translation outputs when barely none of QE scores of that paired languages are given during training. We propose an ensemble-based predictor-estimator QE model with transfer learning to overcome such QE data scarcity challenge by leveraging QE scores from other miscellaneous languages and translation results of targeted languages. Based on the evaluation results, we provide a detailed analysis of how each of our extension affects QE models on the reliability and the generalization ability to perform transfer learning under multilingual tasks. Finally, we achieve the best performance on the ensemble model combining the models pretrained by individual languages as well as different levels of parallel trained corpus with a Pearson's correlation of 0.298, which is 2.54 times higher than baselines.

arXiv:2105.07476

Data Augmentation for Sign Language Gloss Translation

Sign language translation (SLT) is often decomposed into video-to-gloss recognition and gloss-to-text translation, where a gloss is a sequence of transcribed spoken-language words in the order in which they are signed. We focus here on gloss-to-text translation, which we treat as a low-resource neural machine translation (NMT) problem. However, unlike traditional low-resource NMT, gloss-to-text translation differs because gloss-text pairs often have a higher lexical overlap and lower syntactic overlap than pairs of spoken languages. We exploit this lexical overlap and handle syntactic divergence by proposing two rule-based heuristics that generate pseudo-parallel gloss-text pairs from monolingual spoken language text. By pre-training on the thus obtained synthetic data, we improve translation from American Sign Language (ASL) to English and German Sign Language (DGS) to German by up to 3.14 and 2.20 BLEU, respectively.

arXiv:2105.07316공식 코드 · Papers with Code

From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding

The lack of publicly available evaluation data for low-resource languages limits progress in Spoken Language Understanding (SLU). As key tasks like intent classification and slot filling require abundant training data, it is desirable to reuse existing data in high-resource languages to develop models for low-resource scenarios. We introduce xSID, a new benchmark for cross-lingual Slot and Intent Detection in 13 languages from 6 language families, including a very low-resource dialect. To tackle the challenge, we propose a joint learning approach, with English SLU training data and non-English auxiliary tasks from raw text, syntax and translation for transfer. We study two setups which differ by type and language coverage of the pre-trained embeddings. Our results show that jointly learning the main tasks with masked language modeling is effective for slots, while machine translation transfer works best for intent classification.

arXiv:2105.07149

DirectQE: Direct Pretraining for Machine Translation Quality Estimation

Machine Translation Quality Estimation (QE) is a task of predicting the quality of machine translations without relying on any reference. Recently, the predictor-estimator framework trains the predictor as a feature extractor, which leverages the extra parallel corpora without QE labels, achieving promising QE performance. However, we argue that there are gaps between the predictor and the estimator in both data quality and training objectives, which preclude QE models from benefiting from a large number of parallel corpora more directly. We propose a novel framework called DirectQE that provides a direct pretraining for QE tasks. In DirectQE, a generator is trained to produce pseudo data that is closer to the real QE data, and a detector is pretrained on these data with novel objectives that are akin to the QE task. Experiments on widely used benchmarks show that DirectQE outperforms existing methods, without using any pretraining models such as BERT. We also give extensive analyses showing how fixing the two gaps contributes to our improvements.

arXiv:2105.07205

Rethinking Skip Connection with Layer Normalization in Transformers and ResNets

Skip connection, is a widely-used technique to improve the performance and the convergence of deep neural networks, which is believed to relieve the difficulty in optimization due to non-linearity by propagating a linear component through the neural network layers. However, from another point of view, it can also be seen as a modulating mechanism between the input and the output, with the input scaled by a pre-defined value one. In this work, we investigate how the scale factors in the effectiveness of the skip connection and reveal that a trivial adjustment of the scale will lead to spurious gradient exploding or vanishing in line with the deepness of the models, which could be addressed by normalization, in particular, layer normalization, which induces consistent improvements over the plain skip connection. Inspired by the findings, we further propose to adaptively adjust the scale of the input by recursively applying skip connection with layer normalization, which promotes the performance substantially and generalizes well across diverse tasks including both machine translation and image classification datasets.

arXiv:2105.06679공식 코드 · Papers with Code

Dynamic Multi-Branch Layers for On-Device Neural Machine Translation

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 training, we propose shared-private reparameterization to ensure sufficient training for each branch. At almost the same computational cost, our method achieves improvements of up to 1.7 BLEU points on the WMT14 English-German translation task and 1.8 BLEU points on the WMT20 Chinese-English translation task over the Transformer model, respectively. Compared with a strong baseline that also uses multiple branches, the proposed method is up to 1.5 times faster with the same number of parameters.

arXiv:2105.06977공식 코드 · Papers with Code

Do Context-Aware Translation Models Pay the Right Attention?

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 words for 14K translations that professional translators found useful for pronoun disambiguation. Using SCAT, we perform an in-depth analysis of the context used to disambiguate, examining positional and lexical characteristics of the supporting words. Furthermore, we measure the degree of alignment between the model's attention scores and the supporting context from SCAT, and apply a guided attention strategy to encourage agreement between the two.

arXiv:2105.05752

Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders

Encoder pre-training is promising in end-to-end Speech Translation (ST), given the fact that speech-to-translation data is scarce. But ST encoders are not simple instances of Automatic Speech Recognition (ASR) or Machine Translation (MT) encoders. For example, we find that ASR encoders lack the global context representation, which is necessary for translation, whereas MT encoders are not designed to deal with long but locally attentive acoustic sequences. In this work, we propose a Stacked Acoustic-and-Textual Encoding (SATE) method for speech translation. Our encoder begins with processing the acoustic sequence as usual, but later behaves more like an MT encoder for a global representation of the input sequence. In this way, it is straightforward to incorporate the pre-trained models into the system. Also, we develop an adaptor module to alleviate the representation inconsistency between the pre-trained ASR encoder and MT encoder, and develop a multi-teacher knowledge distillation method to preserve the pre-training knowledge. Experimental results on the LibriSpeech En-Fr and MuST-C En-De ST tasks show that our method achieves state-of-the-art BLEU scores of 18.3 and 25.2. To our knowledge, we are the first to develop an end-to-end ST system that achieves comparable or even better BLEU performance than the cascaded ST counterpart when large-scale ASR and MT data is available.

arXiv:2105.05498공식 코드 · Papers with Code

Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction

Accurate terminology translation is crucial for ensuring the practicality and reliability of neural machine translation (NMT) systems. To address this, lexically constrained NMT explores various methods to ensure pre-specified words and phrases appear in the translation output. However, in many cases, those methods are studied on general domain corpora, where the terms are mostly uni- and bi-grams (>98%). In this paper, we instead tackle a more challenging setup consisting of domain-specific corpora with much longer n-gram and highly specialized terms. Inspired by the recent success of masked span prediction models, we propose a simple and effective training strategy that achieves consistent improvements on both terminology and sentence-level translation for three domain-specific corpora in two language pairs.

arXiv:2105.04971

Backretrieval: An Image-Pivoted Evaluation Metric for Cross-Lingual Text Representations Without Parallel Corpora

Cross-lingual text representations have gained popularity lately and act as the backbone of many tasks such as unsupervised machine translation and cross-lingual information retrieval, to name a few. However, evaluation of such representations is difficult in the domains beyond standard benchmarks due to the necessity of obtaining domain-specific parallel language data across different pairs of languages. In this paper, we propose an automatic metric for evaluating the quality of cross-lingual textual representations using images as a proxy in a paired image-text evaluation dataset. Experimentally, Backretrieval is shown to highly correlate with ground truth metrics on annotated datasets, and our analysis shows statistically significant improvements over baselines. Our experiments conclude with a case study on a recipe dataset without parallel cross-lingual data. We illustrate how to judge cross-lingual embedding quality with Backretrieval, and validate the outcome with a small human study.

arXiv:2105.04846

Can You Traducir This? Machine Translation for Code-Switched Input

Code-Switching (CSW) is a common phenomenon that occurs in multilingual geographic or social contexts, which raises challenging problems for natural language processing tools. We focus here on Machine Translation (MT) of CSW texts, where we aim to simultaneously disentangle and translate the two mixed languages. Due to the lack of actual translated CSW data, we generate artificial training data from regular parallel texts. Experiments show this training strategy yields MT systems that surpass multilingual systems for code-switched texts. These results are confirmed in an alternative task aimed at providing contextual translations for a L2 writing assistant.

arXiv:2105.04616

Automatic Classification of Human Translation and Machine Translation: A Study from the Perspective of Lexical Diversity

By using a trigram model and fine-tuning a pretrained BERT model for sequence classification, we show that machine translation and human translation can be classified with an accuracy above chance level, which suggests that machine translation and human translation are different in a systematic way. The classification accuracy of machine translation is much higher than of human translation. We show that this may be explained by the difference in lexical diversity between machine translation and human translation. If machine translation has independent patterns from human translation, automatic metrics which measure the deviation of machine translation from human translation may conflate difference with quality. Our experiment with two different types of automatic metrics shows correlation with the result of the classification task. Therefore, we suggest the difference in lexical diversity between machine translation and human translation be given more attention in machine translation evaluation.

arXiv:2105.03842공식 코드 · Papers with Code

FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition

Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER) than original ASR outputs. Previous works usually use a sequence-to-sequence model to correct an ASR output sentence autoregressively, which causes large latency and cannot be deployed in online ASR services. A straightforward solution to reduce latency, inspired by non-autoregressive (NAR) neural machine translation, is to use an NAR sequence generation model for ASR error correction, which, however, comes at the cost of significantly increased ASR error rate. In this paper, observing distinctive error patterns and correction operations (i.e., insertion, deletion, and substitution) in ASR, we propose FastCorrect, a novel NAR error correction model based on edit alignment. In training, FastCorrect aligns each source token from an ASR output sentence to the target tokens from the corresponding ground-truth sentence based on the edit distance between the source and target sentences, and extracts the number of target tokens corresponding to each source token during edition/correction, which is then used to train a length predictor and to adjust the source tokens to match the length of the target sentence for parallel generation. In inference, the token number predicted by the length predictor is used to adjust the source tokens for target sequence generation. Experiments on the public AISHELL-1 dataset and an internal industrial-scale ASR dataset show the effectiveness of FastCorrect for ASR error correction: 1) it speeds up the inference by 6-9 times and maintains the accuracy (8-14% WER reduction) compared with the autoregressive correction model; and 2) it outperforms the popular NAR models adopted in neural machine translation and text edition by a large margin.