ACL 2019 论文列表

Modern NLP applications have enjoyed a great boost utilizing neural networks models. Such deep neural models, however, are not applicable to most human languages due to the lack of annotated training data for various NLP tasks. Cross-lingual transfer learning (CLTL) is a viable method for building NLP models for a low-resource target language by leveraging labeled data from other (source) languages. In this work, we focus on the multilingual transfer setting where training data in multiple source languages is leveraged to further boost target language performance. Unlike most existing methods that rely only on language-invariant features for CLTL, our approach coherently utilizes both language-invariant and language-specific features at instance level. Our model leverages adversarial networks to learn language-invariant features, and mixture-of-experts models to dynamically exploit the similarity between the target language and each individual source language. This enables our model to learn effectively what to share between various languages in the multilingual setup. Moreover, when coupled with unsupervised multilingual embeddings, our model can operate in a zero-resource setting where neither target language training data nor cross-lingual resources are available. Our model achieves significant performance gains over prior art, as shown in an extensive set of experiments over multiple text classification and sequence tagging tasks including a large-scale industry dataset.

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 positional encoding and 2) lattice-aware self-attention. These two methods can be used together and show complementary to each other to further improve translation performance. Experiment results show superiorities of lattice-based encoders in word-level and subword-level representations over conventional Transformer encoder.

In this paper, we propose a multilingual unsupervised NMT scheme which jointly trains multiple languages with a shared encoder and multiple decoders. Our approach is based on denoising autoencoding of each language and back-translating between English and multiple non-English languages. This results in a universal encoder which can encode any language participating in training into an inter-lingual representation, and language-specific decoders. Our experiments using only monolingual corpora show that multilingual unsupervised model performs better than the separately trained bilingual models achieving improvement of up to 1.48 BLEU points on WMT test sets. We also observe that even if we do not train the network for all possible translation directions, the network is still able to translate in a many-to-many fashion leveraging encoder’s ability to generate interlingual representation.

The training objective of neural machine translation (NMT) is to minimize the loss between the words in the translated sentences and those in the references. In NMT, there is a natural correspondence between the source sentence and the target sentence. However, this relationship has only been represented using the entire neural network and the training objective is computed in word-level. In this paper, we propose a sentence-level agreement module to directly minimize the difference between the representation of source and target sentence. The proposed agreement module can be integrated into NMT as an additional training objective function and can also be used to enhance the representation of the source sentences. Empirical results on the NIST Chinese-to-English and WMT English-to-German tasks show the proposed agreement module can significantly improve the NMT performance.

Self-attention networks have received increasing research attention. By default, the hidden states of each word are hierarchically calculated by attending to all words in the sentence, which assembles global information. However, several studies pointed out that taking all signals into account may lead to overlooking neighboring information (e.g. phrase pattern). To address this argument, we propose a hybrid attention mechanism to dynamically leverage both of the local and global information. Specifically, our approach uses a gating scalar for integrating both sources of the information, which is also convenient for quantifying their contributions. Experiments on various neural machine translation tasks demonstrate the effectiveness of the proposed method. The extensive analyses verify that the two types of contexts are complementary to each other, and our method gives highly effective improvements in their integration.

This paper proposes a novel method to inject custom terminology into neural machine translation at run time. Previous works have mainly proposed modifications to the decoding algorithm in order to constrain the output to include run-time-provided target terms. While being effective, these constrained decoding methods add, however, significant computational overhead to the inference step, and, as we show in this paper, can be brittle when tested in realistic conditions. In this paper we approach the problem by training a neural MT system to learn how to use custom terminology when provided with the input. Comparative experiments show that our method is not only more effective than a state-of-the-art implementation of constrained decoding, but is also as fast as constraint-free decoding.

Given a rough, word-by-word gloss of a source language sentence, target language natives can uncover the latent, fully-fluent rendering of the translation. In this work we explore this intuition by breaking translation into a two step process: generating a rough gloss by means of a dictionary and then ‘translating’ the resulting pseudo-translation, or ‘Translationese’ into a fully fluent translation. We build our Translationese decoder once from a mish-mash of parallel data that has the target language in common and then can build dictionaries on demand using unsupervised techniques, resulting in rapidly generated unsupervised neural MT systems for many source languages. We apply this process to 14 test languages, obtaining better or comparable translation results on high-resource languages than previously published unsupervised MT studies, and obtaining good quality results for low-resource languages that have never been used in an unsupervised MT scenario.

Automatic post-editing (APE) seeks to automatically refine the output of a black-box machine translation (MT) system through human post-edits. APE systems are usually trained by complementing human post-edited data with large, artificial data generated through back-translations, a time-consuming process often no easier than training a MT system from scratch. in this paper, we propose an alternative where we fine-tune pre-trained BERT models on both the encoder and decoder of an APE system, exploring several parameter sharing strategies. By only training on a dataset of 23K sentences for 3 hours on a single GPU we obtain results that are competitive with systems that were trained on 5M artificial sentences. When we add this artificial data our method obtains state-of-the-art results.

Neural machine translation (NMT) is notoriously sensitive to noises, but noises are almost inevitable in practice. One special kind of noise is the homophone noise, where words are replaced by other words with similar pronunciations. We propose to improve the robustness of NMT to homophone noises by 1) jointly embedding both textual and phonetic information of source sentences, and 2) augmenting the training dataset with homophone noises. Interestingly, to achieve better translation quality and more robustness, we found that most (though not all) weights should be put on the phonetic rather than textual information. Experiments show that our method not only significantly improves the robustness of NMT to homophone noises, but also surprisingly improves the translation quality on some clean test sets.

Soft-attention based Neural Machine Translation (NMT) models have achieved promising results on several translation tasks. These models attend all the words in the source sequence for each target token, which makes them ineffective for long sequence translation. In this work, we propose a hard-attention based NMT model which selects a subset of source tokens for each target token to effectively handle long sequence translation. Due to the discrete nature of the hard-attention mechanism, we design a reinforcement learning algorithm coupled with reward shaping strategy to efficiently train it. Experimental results show that the proposed model performs better on long sequences and thereby achieves significant BLEU score improvement on English-German (EN-DE) and English-French (ENFR) translation tasks compared to the soft attention based NMT.

Simultaneous translation, which translates sentences before they are finished, is use- ful in many scenarios but is notoriously dif- ficult due to word-order differences. While the conventional seq-to-seq framework is only suitable for full-sentence translation, we pro- pose a novel prefix-to-prefix framework for si- multaneous translation that implicitly learns to anticipate in a single translation model. Within this framework, we present a very sim- ple yet surprisingly effective “wait-k” policy trained to generate the target sentence concur- rently with the source sentence, but always k words behind. Experiments show our strat- egy achieves low latency and reasonable qual- ity (compared to full-sentence translation) on 4 directions: zh↔en and de↔en.

Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential information. Over-translation and under-translation errors often occur for the above reason, especially in the long sentence translation scenario. In this paper, we propose two approaches to retrieve the target sequential information for NAT to enhance its translation ability while preserving the fast-decoding property. Firstly, we propose a sequence-level training method based on a novel reinforcement algorithm for NAT (Reinforce-NAT) to reduce the variance and stabilize the training procedure. Secondly, we propose an innovative Transformer decoder named FS-decoder to fuse the target sequential information into the top layer of the decoder. Experimental results on three translation tasks show that the Reinforce-NAT surpasses the baseline NAT system by a significant margin on BLEU without decelerating the decoding speed and the FS-decoder achieves comparable translation performance to the autoregressive Transformer with considerable speedup.

Neural Machine Translation (NMT) has achieved notable success in recent years. Such a framework usually generates translations in isolation. In contrast, human translators often refer to reference data, either rephrasing the intricate sentence fragments with common terms in source language, or just accessing to the golden translation directly. In this paper, we propose a Reference Network to incorporate referring process into translation decoding of NMT. To construct a reference book, an intuitive way is to store the detailed translation history with extra memory, which is computationally expensive. Instead, we employ Local Coordinates Coding (LCC) to obtain global context vectors containing monolingual and bilingual contextual information for NMT decoding. Experimental results on Chinese-English and English-German tasks demonstrate that our proposed model is effective in improving the translation quality with lightweight computation cost.

It has been previously noted that neural machine translation (NMT) is very sensitive to domain shift. In this paper, we argue that this is a dual effect of the highly lexicalized nature of NMT, resulting in failure for sentences with large numbers of unknown words, and lack of supervision for domain-specific words. To remedy this problem, we propose an unsupervised adaptation method which fine-tunes a pre-trained out-of-domain NMT model using a pseudo-in-domain corpus. Specifically, we perform lexicon induction to extract an in-domain lexicon, and construct a pseudo-parallel in-domain corpus by performing word-for-word back-translation of monolingual in-domain target sentences. In five domains over twenty pairwise adaptation settings and two model architectures, our method achieves consistent improvements without using any in-domain parallel sentences, improving up to 14 BLEU over unadapted models, and up to 2 BLEU over strong back-translation baselines.

Transformers have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling. We propose a novel neural architecture Transformer-XL that enables learning dependency beyond a fixed length without disrupting temporal coherence. It consists of a segment-level recurrence mechanism and a novel positional encoding scheme. Our method not only enables capturing longer-term dependency, but also resolves the context fragmentation problem. As a result, Transformer-XL learns dependency that is 80% longer than RNNs and 450% longer than vanilla Transformers, achieves better performance on both short and long sequences, and is up to 1,800+ times faster than vanilla Transformers during evaluation. Notably, we improve the state-of-the-art results of bpc/perplexity to 0.99 on enwiki8, 1.08 on text8, 18.3 on WikiText-103, 21.8 on One Billion Word, and 54.5 on Penn Treebank (without finetuning). When trained only on WikiText-103, Transformer-XL manages to generate reasonably coherent, novel text articles with thousands of tokens. Our code, pretrained models, and hyperparameters are available in both Tensorflow and PyTorch.

The success of neural networks comes hand in hand with a desire for more interpretability. We focus on text classifiers and make them more interpretable by having them provide a justification–a rationale–for their predictions. We approach this problem by jointly training two neural network models: a latent model that selects a rationale (i.e. a short and informative part of the input text), and a classifier that learns from the words in the rationale alone. Previous work proposed to assign binary latent masks to input positions and to promote short selections via sparsity-inducing penalties such as L0 regularisation. We propose a latent model that mixes discrete and continuous behaviour allowing at the same time for binary selections and gradient-based training without REINFORCE. In our formulation, we can tractably compute the expected value of penalties such as L0, which allows us to directly optimise the model towards a pre-specified text selection rate. We show that our approach is competitive with previous work on rationale extraction, and explore further uses in attention mechanisms.

Analysis methods which enable us to better understand the representations and functioning of neural models of language are increasingly needed as deep learning becomes the dominant approach in NLP. Here we present two methods based on Representational Similarity Analysis (RSA) and Tree Kernels (TK) which allow us to directly quantify how strongly the information encoded in neural activation patterns corresponds to information represented by symbolic structures such as syntax trees. We first validate our methods on the case of a simple synthetic language for arithmetic expressions with clearly defined syntax and semantics, and show that they exhibit the expected pattern of results. We then our methods to correlate neural representations of English sentences with their constituency parse trees.

Attention mechanisms have recently boosted performance on a range of NLP tasks. Because attention layers explicitly weight input components’ representations, it is also often assumed that attention can be used to identify information that models found important (e.g., specific contextualized word tokens). We test whether that assumption holds by manipulating attention weights in already-trained text classification models and analyzing the resulting differences in their predictions. While we observe some ways in which higher attention weights correlate with greater impact on model predictions, we also find many ways in which this does not hold, i.e., where gradient-based rankings of attention weights better predict their effects than their magnitudes. We conclude that while attention noisily predicts input components’ overall importance to a model, it is by no means a fail-safe indicator.

We present FIESTA, a model selection approach that significantly reduces the computational resources required to reliably identify state-of-the-art performance from large collections of candidate models. Despite being known to produce unreliable comparisons, it is still common practice to compare model evaluations based on single choices of random seeds. We show that reliable model selection also requires evaluations based on multiple train-test splits (contrary to common practice in many shared tasks). Using bandit theory from the statistics literature, we are able to adaptively determine appropriate numbers of data splits and random seeds used to evaluate each model, focusing computational resources on the evaluation of promising models whilst avoiding wasting evaluations on models with lower performance. Furthermore, our user-friendly Python implementation produces confidence guarantees of correctly selecting the optimal model. We evaluate our algorithms by selecting between 8 target-dependent sentiment analysis methods using dramatically fewer model evaluations than current model selection approaches.