PyTorchKR Papers

최신 논문

총 5,206편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2010.01771공식 코드 · Papers with Code

Improving AMR Parsing with Sequence-to-Sequence Pre-training

In the literature, the research on abstract meaning representation (AMR) parsing is much restricted by the size of human-curated dataset which is critical to build an AMR parser with good performance. To alleviate such data size restriction, pre-trained models have been drawing more and more attention in AMR parsing. However, previous pre-trained models, like BERT, are implemented for general purpose which may not work as expected for the specific task of AMR parsing. In this paper, we focus on sequence-to-sequence (seq2seq) AMR parsing and propose a seq2seq pre-training approach to build pre-trained models in both single and joint way on three relevant tasks, i.e., machine translation, syntactic parsing, and AMR parsing itself. Moreover, we extend the vanilla fine-tuning method to a multi-task learning fine-tuning method that optimizes for the performance of AMR parsing while endeavors to preserve the response of pre-trained models. Extensive experimental results on two English benchmark datasets show that both the single and joint pre-trained models significantly improve the performance (e.g., from 71.5 to 80.2 on AMR 2.0), which reaches the state of the art. The result is very encouraging since we achieve this with seq2seq models rather than complex models. We make our code and model available at https://github.com/xdqkid/S2S-AMR-Parser.

arXiv:2010.01667

Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation

To improve the performance of Neural Machine Translation~(NMT) for low-resource languages~(LRL), one effective strategy is to leverage parallel data from a related high-resource language~(HRL). However, multilingual data has been found more beneficial for NMT models that translate from the LRL to a target language than the ones that translate into the LRLs. In this paper, we aim to improve the effectiveness of multilingual transfer for NMT models that translate \emph{into} the LRL, by designing a better decoder word embedding. Extending upon a general-purpose multilingual encoding method Soft Decoupled Encoding~\citep{SDE}, we propose DecSDE, an efficient character n-gram based embedding specifically designed for the NMT decoder. Our experiments show that DecSDE leads to consistent gains of up to 1.8 BLEU on translation from English to four different languages.

arXiv:2010.02164공식 코드 · Papers with Code

A Streaming Approach For Efficient Batched Beam Search

We propose an efficient batching strategy for variable-length decoding on GPU architectures. During decoding, when candidates terminate or are pruned according to heuristics, our streaming approach periodically "refills" the batch before proceeding with a selected subset of candidates. We apply our method to variable-width beam search on a state-of-the-art machine translation model. Our method decreases runtime by up to 71% compared to a fixed-width beam search baseline and 17% compared to a variable-width baseline, while matching baselines' BLEU. Finally, experiments show that our method can speed up decoding in other domains, such as semantic and syntactic parsing.

arXiv:2010.01998공식 코드 · Papers with Code

X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset

Even though SRL is researched for many languages, major improvements have mostly been obtained for English, for which more resources are available. In fact, existing multilingual SRL datasets contain disparate annotation styles or come from different domains, hampering generalization in multilingual learning. In this work, we propose a method to automatically construct an SRL corpus that is parallel in four languages: English, French, German, Spanish, with unified predicate and role annotations that are fully comparable across languages. We apply high-quality machine translation to the English CoNLL-09 dataset and use multilingual BERT to project its high-quality annotations to the target languages. We include human-validated test sets that we use to measure the projection quality, and show that projection is denser and more precise than a strong baseline. Finally, we train different SOTA models on our novel corpus for mono- and multilingual SRL, showing that the multilingual annotations improve performance especially for the weaker languages.

arXiv:2010.00710공식 코드 · Papers with Code

Nearest Neighbor Machine Translation

We introduce $k$-nearest-neighbor machine translation ($k$NN-MT), which predicts tokens with a nearest neighbor classifier over a large datastore of cached examples, using representations from a neural translation model for similarity search. This approach requires no additional training and scales to give the decoder direct access to billions of examples at test time, resulting in a highly expressive model that consistently improves performance across many settings. Simply adding nearest neighbor search improves a state-of-the-art German-English translation model by 1.5 BLEU. $k$NN-MT allows a single model to be adapted to diverse domains by using a domain-specific datastore, improving results by an average of 9.2 BLEU over zero-shot transfer, and achieving new state-of-the-art results -- without training on these domains. A massively multilingual model can also be specialized for particular language pairs, with improvements of 3 BLEU for translating from English into German and Chinese. Qualitatively, $k$NN-MT is easily interpretable; it combines source and target context to retrieve highly relevant examples.

arXiv:2010.01063

Syntax Representation in Word Embeddings and Neural Networks -- A Survey

Neural networks trained on natural language processing tasks capture syntax even though it is not provided as a supervision signal. This indicates that syntactic analysis is essential to the understating of language in artificial intelligence systems. This overview paper covers approaches of evaluating the amount of syntactic information included in the representations of words for different neural network architectures. We mainly summarize re-search on English monolingual data on language modeling tasks and multilingual data for neural machine translation systems and multilingual language models. We describe which pre-trained models and representations of language are best suited for transfer to syntactic tasks.

arXiv:2010.00247

WeChat Neural Machine Translation Systems for WMT20

We participate in the WMT 2020 shared news translation task on Chinese to English. Our system is based on the Transformer (Vaswani et al., 2017a) with effective variants and the DTMT (Meng and Zhang, 2019) architecture. In our experiments, we employ data selection, several synthetic data generation approaches (i.e., back-translation, knowledge distillation, and iterative in-domain knowledge transfer), advanced finetuning approaches and self-bleu based model ensemble. Our constrained Chinese to English system achieves 36.9 case-sensitive BLEU score, which is the highest among all submissions.

arXiv:2009.14326

Attention-Driven Body Pose Encoding for Human Activity Recognition

This article proposes a novel attention-based body pose encoding for human activity recognition that presents a enriched representation of body-pose that is learned. The enriched data complements the 3D body joint position data and improves model performance. In this paper, we propose a novel approach that learns enhanced feature representations from a given sequence of 3D body joints. To achieve this encoding, the approach exploits 1) a spatial stream which encodes the spatial relationship between various body joints at each time point to learn spatial structure involving the spatial distribution of different body joints 2) a temporal stream that learns the temporal variation of individual body joints over the entire sequence duration to present a temporally enhanced representation. Afterwards, these two pose streams are fused with a multi-head attention mechanism. % adapted from neural machine translation. We also capture the contextual information from the RGB video stream using a Inception-ResNet-V2 model combined with a multi-head attention and a bidirectional Long Short-Term Memory (LSTM) network. %Moreover, we whose performance is enhanced through the multi-head attention mechanism. Finally, the RGB video stream is combined with the fused body pose stream to give a novel end-to-end deep model for effective human activity recognition.

arXiv:2009.14658

Learning Hard Retrieval Decoder Attention for Transformers

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by jointly attending to information from different representation subspaces at different positions. In this paper, we present an approach to learning a hard retrieval attention where an attention head only attends to one token in the sentence rather than all tokens. The matrix multiplication between attention probabilities and the value sequence in the standard scaled dot-product attention can thus be replaced by a simple and efficient retrieval operation. We show that our hard retrieval attention mechanism is 1.43 times faster in decoding, while preserving translation quality on a wide range of machine translation tasks when used in the decoder self- and cross-attention networks.

arXiv:2009.14395공식 코드 · Papers with Code

Can Automatic Post-Editing Improve NMT?

Automatic post-editing (APE) aims to improve machine translations, thereby reducing human post-editing effort. APE has had notable success when used with statistical machine translation (SMT) systems but has not been as successful over neural machine translation (NMT) systems. This has raised questions on the relevance of APE task in the current scenario. However, the training of APE models has been heavily reliant on large-scale artificial corpora combined with only limited human post-edited data. We hypothesize that APE models have been underperforming in improving NMT translations due to the lack of adequate supervision. To ascertain our hypothesis, we compile a larger corpus of human post-edits of English to German NMT. We empirically show that a state-of-art neural APE model trained on this corpus can significantly improve a strong in-domain NMT system, challenging the current understanding in the field. We further investigate the effects of varying training data sizes, using artificial training data, and domain specificity for the APE task. We release this new corpus under CC BY-NC-SA 4.0 license at https://github.com/shamilcm/pedra.

arXiv:2009.14824

On Romanization for Model Transfer Between Scripts in Neural Machine Translation

Transfer learning is a popular strategy to improve the quality of low-resource machine translation. For an optimal transfer of the embedding layer, the child and parent model should share a substantial part of the vocabulary. This is not the case when transferring to languages with a different script. We explore the benefit of romanization in this scenario. Our results show that romanization entails information loss and is thus not always superior to simpler vocabulary transfer methods, but can improve the transfer between related languages with different scripts. We compare two romanization tools and find that they exhibit different degrees of information loss, which affects translation quality. Finally, we extend romanization to the target side, showing that this can be a successful strategy when coupled with a simple deromanization model.

arXiv:2009.13818공식 코드 · Papers with Code

A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation

Adversarial training has been shown effective at endowing the learned representations with stronger generalization ability. However, it typically requires expensive computation to determine the direction of the injected perturbations. In this paper, we introduce a set of simple yet effective data augmentation strategies dubbed cutoff, where part of the information within an input sentence is erased to yield its restricted views (during the fine-tuning stage). Notably, this process relies merely on stochastic sampling and thus adds little computational overhead. A Jensen-Shannon Divergence consistency loss is further utilized to incorporate these augmented samples into the training objective in a principled manner. To verify the effectiveness of the proposed strategies, we apply cutoff to both natural language understanding and generation problems. On the GLUE benchmark, it is demonstrated that cutoff, in spite of its simplicity, performs on par or better than several competitive adversarial-based approaches. We further extend cutoff to machine translation and observe significant gains in BLEU scores (based upon the Transformer Base model). Moreover, cutoff consistently outperforms adversarial training and achieves state-of-the-art results on the IWSLT2014 German-English dataset.

arXiv:2009.12431

XTE: Explainable Text Entailment

Text entailment, the task of determining whether a piece of text logically follows from another piece of text, is a key component in NLP, providing input for many semantic applications such as question answering, text summarization, information extraction, and machine translation, among others. Entailment scenarios can range from a simple syntactic variation to more complex semantic relationships between pieces of text, but most approaches try a one-size-fits-all solution that usually favors some scenario to the detriment of another. Furthermore, for entailments requiring world knowledge, most systems still work as a "black box", providing a yes/no answer that does not explain the underlying reasoning process. In this work, we introduce XTE - Explainable Text Entailment - a novel composite approach for recognizing text entailment which analyzes the entailment pair to decide whether it must be resolved syntactically or semantically. Also, if a semantic matching is involved, we make the answer interpretable, using external knowledge bases composed of structured lexical definitions to generate natural language justifications that explain the semantic relationship holding between the pieces of text. Besides outperforming well-established entailment algorithms, our composite approach gives an important step towards Explainable AI, allowing the inference model interpretation, making the semantic reasoning process explicit and understandable.

arXiv:2009.13270

Dissecting Lottery Ticket Transformers: Structural and Behavioral Study of Sparse Neural Machine Translation

Recent work on the lottery ticket hypothesis has produced highly sparse Transformers for NMT while maintaining BLEU. However, it is unclear how such pruning techniques affect a model's learned representations. By probing Transformers with more and more low-magnitude weights pruned away, we find that complex semantic information is first to be degraded. Analysis of internal activations reveals that higher layers diverge most over the course of pruning, gradually becoming less complex than their dense counterparts. Meanwhile, early layers of sparse models begin to perform more encoding. Attention mechanisms remain remarkably consistent as sparsity increases.

arXiv:2009.13267공식 코드 · Papers with Code

Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models

The discrepancy between maximum likelihood estimation (MLE) and task measures such as BLEU score has been studied before for autoregressive neural machine translation (NMT) and resulted in alternative training algorithms (Ranzato et al., 2016; Norouzi et al., 2016; Shen et al., 2016; Wu et al., 2018). However, MLE training remains the de facto approach for autoregressive NMT because of its computational efficiency and stability. Despite this mismatch between the training objective and task measure, we notice that the samples drawn from an MLE-based trained NMT support the desired distribution -- there are samples with much higher BLEU score comparing to the beam decoding output. To benefit from this observation, we train an energy-based model to mimic the behavior of the task measure (i.e., the energy-based model assigns lower energy to samples with higher BLEU score), which is resulted in a re-ranking algorithm based on the samples drawn from NMT: energy-based re-ranking (EBR). We use both marginal energy models (over target sentence) and joint energy models (over both source and target sentences). Our EBR with the joint energy model consistently improves the performance of the Transformer-based NMT: +4 BLEU points on IWSLT'14 German-English, +3.0 BELU points on Sinhala-English, +1.2 BLEU on WMT'16 English-German tasks.

arXiv:2009.12622

Automatic Arabic Dialect Identification Systems for Written Texts: A Survey

Arabic dialect identification is a specific task of natural language processing, aiming to automatically predict the Arabic dialect of a given text. Arabic dialect identification is the first step in various natural language processing applications such as machine translation, multilingual text-to-speech synthesis, and cross-language text generation. Therefore, in the last decade, interest has increased in addressing the problem of Arabic dialect identification. In this paper, we present a comprehensive survey of Arabic dialect identification research in written texts. We first define the problem and its challenges. Then, the survey extensively discusses in a critical manner many aspects related to Arabic dialect identification task. So, we review the traditional machine learning methods, deep learning architectures, and complex learning approaches to Arabic dialect identification. We also detail the features and techniques for feature representations used to train the proposed systems. Moreover, we illustrate the taxonomy of Arabic dialects studied in the literature, the various levels of text processing at which Arabic dialect identification are conducted (e.g., token, sentence, and document level), as well as the available annotated resources, including evaluation benchmark corpora. Open challenges and issues are discussed at the end of the survey.

arXiv:2009.13117

Generative latent neural models for automatic word alignment

Word alignments identify translational correspondences between words in a parallel sentence pair and are used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems or to perform quality estimation. Variational autoencoders have been recently used in various of natural language processing to learn in an unsupervised way latent representations that are useful for language generation tasks. In this paper, we study these models for the task of word alignment and propose and assess several evolutions of a vanilla variational autoencoders. We demonstrate that these techniques can yield competitive results as compared to Giza++ and to a strong neural network alignment system for two language pairs.

arXiv:2009.13116

Neural Baselines for Word Alignment

Word alignments identify translational correspondences between words in a parallel sentence pair and is used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems , or to perform quality estimation. In most areas of natural language processing, neural network models nowadays constitute the preferred approach, a situation that might also apply to word alignment models. In this work, we study and comprehensively evaluate neural models for unsupervised word alignment for four language pairs, contrasting several variants of neural models. We show that in most settings, neural versions of the IBM-1 and hidden Markov models vastly outperform their discrete counterparts. We also analyze typical alignment errors of the baselines that our models overcome to illustrate the benefits-and the limitations-of these new models for morphologically rich languages.

arXiv:2009.13102공식 코드 · Papers with Code

Deep Transformers with Latent Depth

The Transformer model has achieved state-of-the-art performance in many sequence modeling tasks. However, how to leverage model capacity with large or variable depths is still an open challenge. We present a probabilistic framework to automatically learn which layer(s) to use by learning the posterior distributions of layer selection. As an extension of this framework, we propose a novel method to train one shared Transformer network for multilingual machine translation with different layer selection posteriors for each language pair. The proposed method alleviates the vanishing gradient issue and enables stable training of deep Transformers (e.g. 100 layers). We evaluate on WMT English-German machine translation and masked language modeling tasks, where our method outperforms existing approaches for training deeper Transformers. Experiments on multilingual machine translation demonstrate that this approach can effectively leverage increased model capacity and bring universal improvement for both many-to-one and one-to-many translation with diverse language pairs.

arXiv:2009.13398

Aspects of Terminological and Named Entity Knowledge within Rule-Based Machine Translation Models for Under-Resourced Neural Machine Translation Scenarios

Rule-based machine translation is a machine translation paradigm where linguistic knowledge is encoded by an expert in the form of rules that translate text from source to target language. While this approach grants extensive control over the output of the system, the cost of formalising the needed linguistic knowledge is much higher than training a corpus-based system, where a machine learning approach is used to automatically learn to translate from examples. In this paper, we describe different approaches to leverage the information contained in rule-based machine translation systems to improve a corpus-based one, namely, a neural machine translation model, with a focus on a low-resource scenario. Three different kinds of information were used: morphological information, named entities and terminology. In addition to evaluating the general performance of the system, we systematically analysed the performance of the proposed approaches when dealing with the targeted phenomena. Our results suggest that the proposed models have limited ability to learn from external information, and most approaches do not significantly alter the results of the automatic evaluation, but our preliminary qualitative evaluation shows that in certain cases the hypothesis generated by our system exhibit favourable behaviour such as keeping the use of passive voice.