EMNLP 2018 论文列表

Corpus-based approaches to machine translation rely on the availability of clean parallel corpora. Such resources are scarce, and because of the automatic processes involved in their preparation, they are often noisy. This paper describes an unsupervised method for detecting translation divergences in parallel sentences. We rely on a neural network that computes cross-lingual sentence similarity scores, which are then used to effectively filter out divergent translations. Furthermore, similarity scores predicted by the network are used to identify and fix some partial divergences, yielding additional parallel segments. We evaluate these methods for English-French and English-German machine translation tasks, and show that using filtered/corrected corpora actually improves MT performance.

We introduce a novel multi-source technique for incorporating source syntax into neural machine translation using linearized parses. This is achieved by employing separate encoders for the sequential and parsed versions of the same source sentence; the resulting representations are then combined using a hierarchical attention mechanism. The proposed model improves over both seq2seq and parsed baselines by over 1 BLEU on the WMT17 English-German task. Further analysis shows that our multi-source syntactic model is able to translate successfully without any parsed input, unlike standard parsed methods. In addition, performance does not deteriorate as much on long sentences as for the baselines.

Due to the benefits of model compactness, multilingual translation (including many-to-one, many-to-many and one-to-many) based on a universal encoder-decoder architecture attracts more and more attention. However, previous studies show that one-to-many translation based on this framework cannot perform on par with the individually trained models. In this work, we introduce three strategies to improve one-to-many multilingual translation by balancing the shared and unique features. Within the architecture of one decoder for all target languages, we first exploit the use of unique initial states for different target languages. Then, we employ language-dependent positional embeddings. Finally and especially, we propose to divide the hidden cells of the decoder into shared and language-dependent ones. The extensive experiments demonstrate that our proposed methods can obtain remarkable improvements over the strong baselines. Moreover, our strategies can achieve comparable or even better performance than the individually trained translation models.

Neural Machine Translation (NMT) can be improved by including document-level contextual information. For this purpose, we propose a hierarchical attention model to capture the context in a structured and dynamic manner. The model is integrated in the original NMT architecture as another level of abstraction, conditioning on the NMT model’s own previous hidden states. Experiments show that hierarchical attention significantly improves the BLEU score over a strong NMT baseline with the state-of-the-art in context-aware methods, and that both the encoder and decoder benefit from context in complementary ways.

Neural language models are a critical component of state-of-the-art systems for machine translation, summarization, audio transcription, and other tasks. These language models are almost universally autoregressive in nature, generating sentences one token at a time from left to right. This paper studies the influence of token generation order on model quality via a novel two-pass language model that produces partially-filled sentence “templates” and then fills in missing tokens. We compare various strategies for structuring these two passes and observe a surprisingly large variation in model quality. We find the most effective strategy generates function words in the first pass followed by content words in the second. We believe these experimental results justify a more extensive investigation of the generation order for neural language models.

Recent state-of-the-art neural language models share the representations of words given by the input and output mappings. We propose a simple modification to these architectures that decouples the hidden state from the word embedding prediction. Our architecture leads to comparable or better results compared to previous tied models and models without tying, with a much smaller number of parameters. We also extend our proposal to word2vec models, showing that tying is appropriate for general word prediction tasks.

Recurrent neural network language models (RNNLMs) are the current standard-bearer for statistical language modeling. However, RNNLMs only estimate probabilities for complete sequences of text, whereas some applications require context-independent phrase probabilities instead. In this paper, we study how to compute an RNNLM’s em marginal probability: the probability that the model assigns to a short sequence of text when the preceding context is not known. We introduce a simple method of altering the RNNLM training to make the model more accurate at marginal estimation. Our experiments demonstrate that the technique is effective compared to baselines including the traditional RNNLM probability and an importance sampling approach. Finally, we show how we can use the marginal estimation to improve an RNNLM by training the marginals to match n-gram probabilities from a larger corpus.

Chinese pinyin input method engine (IME) converts pinyin into character so that Chinese characters can be conveniently inputted into computer through common keyboard. IMEs work relying on its core component, pinyin-to-character conversion (P2C). Usually Chinese IMEs simply predict a list of character sequences for user choice only according to user pinyin input at each turn. However, Chinese inputting is a multi-turn online procedure, which can be supposed to be exploited for further user experience promoting. This paper thus for the first time introduces a sequence-to-sequence model with gated-attention mechanism for the core task in IMEs. The proposed neural P2C model is learned by encoding previous input utterance as extra context to enable our IME capable of predicting character sequence with incomplete pinyin input. Our model is evaluated in different benchmark datasets showing great user experience improvement compared to traditional models, which demonstrates the first engineering practice of building Chinese aided IME.

Graphemes of most languages encode pronunciation, though some are more explicit than others. Languages like Spanish have a straightforward mapping between its graphemes and phonemes, while this mapping is more convoluted for languages like English. Spoken languages such as Cantonese present even more challenges in pronunciation modeling: (1) they do not have a standard written form, (2) the closest graphemic origins are logographic Han characters, of which only a subset of these logographic characters implicitly encodes pronunciation. In this work, we propose a multimodal approach to predict the pronunciation of Cantonese logographic characters, using neural networks with a geometric representation of logographs and pronunciation of cognates in historically related languages. The proposed framework improves performance by 18.1% and 25.0% respective to unimodal and multimodal baselines.

In natural language processing, a lot of the tasks are successfully solved with recurrent neural networks, but such models have a huge number of parameters. The majority of these parameters are often concentrated in the embedding layer, which size grows proportionally to the vocabulary length. We propose a Bayesian sparsification technique for RNNs which allows compressing the RNN dozens or hundreds of times without time-consuming hyperparameters tuning. We also generalize the model for vocabulary sparsification to filter out unnecessary words and compress the RNN even further. We show that the choice of the kept words is interpretable.

Several recent papers investigate Active Learning (AL) for mitigating the data dependence of deep learning for natural language processing. However, the applicability of AL to real-world problems remains an open question. While in supervised learning, practitioners can try many different methods, evaluating each against a validation set before selecting a model, AL affords no such luxury. Over the course of one AL run, an agent annotates its dataset exhausting its labeling budget. Thus, given a new task, we have no opportunity to compare models and acquisition functions. This paper provides a large-scale empirical study of deep active learning, addressing multiple tasks and, for each, multiple datasets, multiple models, and a full suite of acquisition functions. We find that across all settings, Bayesian active learning by disagreement, using uncertainty estimates provided either by Dropout or Bayes-by-Backprop significantly improves over i.i.d. baselines and usually outperforms classic uncertainty sampling.

Multi-head attention is appealing for the ability to jointly attend to information from different representation subspaces at different positions. In this work, we introduce a disagreement regularization to explicitly encourage the diversity among multiple attention heads. Specifically, we propose three types of disagreement regularization, which respectively encourage the subspace, the attended positions, and the output representation associated with each attention head to be different from other heads. Experimental results on widely-used WMT14 English-German and WMT17 Chinese-English translation tasks demonstrate the effectiveness and universality of the proposed approach.

Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations to correctly classified examples which can cause the model to misclassify. In the image domain, these perturbations can often be made virtually indistinguishable to human perception, causing humans and state-of-the-art models to disagree. However, in the natural language domain, small perturbations are clearly perceptible, and the replacement of a single word can drastically alter the semantics of the document. Given these challenges, we use a black-box population-based optimization algorithm to generate semantically and syntactically similar adversarial examples that fool well-trained sentiment analysis and textual entailment models with success rates of 97% and 70%, respectively. We additionally demonstrate that 92.3% of the successful sentiment analysis adversarial examples are classified to their original label by 20 human annotators, and that the examples are perceptibly quite similar. Finally, we discuss an attempt to use adversarial training as a defense, but fail to yield improvement, demonstrating the strength and diversity of our adversarial examples. We hope our findings encourage researchers to pursue improving the robustness of DNNs in the natural language domain.

The Paradigm Cell Filling Problem in morphology asks to complete word inflection tables from partial ones. We implement novel neural models for this task, evaluating them on 18 data sets in 8 languages, showing performance that is comparable with previous work with far less training data. We also publish a new dataset for this task and code implementing the system described in this paper.

We employ imitation learning to train a neural transition-based string transducer for morphological tasks such as inflection generation and lemmatization. Previous approaches to training this type of model either rely on an external character aligner for the production of gold action sequences, which results in a suboptimal model due to the unwarranted dependence on a single gold action sequence despite spurious ambiguity, or require warm starting with an MLE model. Our approach only requires a simple expert policy, eliminating the need for a character aligner or warm start. It also addresses familiar MLE training biases and leads to strong and state-of-the-art performance on several benchmarks.

Neural sequence-to-sequence models have proven very effective for machine translation, but at the expense of model interpretability. To shed more light into the role played by linguistic structure in the process of neural machine translation, we perform a fine-grained analysis of how various source-side morphological features are captured at different levels of the NMT encoder while varying the target language. Differently from previous work, we find no correlation between the accuracy of source morphology encoding and translation quality. We do find that morphological features are only captured in context and only to the extent that they are directly transferable to the target words.

This paper presents a simple framework for characterizing morphological complexity and how it encodes syntactic information. In particular, we propose a new measure of morpho-syntactic complexity in terms of governor-dependent preferential attachment that explains parsing performance. Through experiments on dependency parsing with data from Universal Dependencies (UD), we show that representations derived from morphological attributes deliver important parsing performance improvements over standard word form embeddings when trained on the same datasets. We also show that the new morpho-syntactic complexity measure is predictive of the gains provided by using morphological attributes over plain forms on parsing scores, making it a tool to distinguish languages using morphology as a syntactic marker from others.

Pre-trained word embeddings and language model have been shown useful in a lot of tasks. However, both of them cannot directly capture word connections in a sentence, which is important for dependency parsing given its goal is to establish dependency relations between words. In this paper, we propose to implicitly capture word connections from unlabeled data by a word ordering model with self-attention mechanism. Experiments show that these implicit word connections do improve our parsing model. Furthermore, by combining with a pre-trained language model, our model gets state-of-the-art performance on the English PTB dataset, achieving 96.35% UAS and 95.25% LAS.

Conventional wisdom is that hand-crafted features are redundant for deep learning models, as they already learn adequate representations of text automatically from corpora. In this work, we test this claim by proposing a new method for exploiting handcrafted features as part of a novel hybrid learning approach, incorporating a feature auto-encoder loss component. We evaluate on the task of named entity recognition (NER), where we show that including manual features for part-of-speech, word shapes and gazetteers can improve the performance of a neural CRF model. We obtain a F 1 of 91.89 for the CoNLL-2003 English shared task, which significantly outperforms a collection of highly competitive baseline models. We also present an ablation study showing the importance of auto-encoding, over using features as either inputs or outputs alone, and moreover, show including the autoencoder components reduces training requirements to 60%, while retaining the same predictive accuracy.