ACL 2019 Papers

As Natural Language Processing (NLP) and Machine Learning (ML) tools rise in popularity, it becomes increasingly vital to recognize the role they play in shaping societal biases and stereotypes. Although NLP models have shown success in modeling various applications, they propagate and may even amplify gender bias found in text corpora. While the study of bias in artificial intelligence is not new, methods to mitigate gender bias in NLP are relatively nascent. In this paper, we review contemporary studies on recognizing and mitigating gender bias in NLP. We discuss gender bias based on four forms of representation bias and analyze methods recognizing gender bias. Furthermore, we discuss the advantages and drawbacks of existing gender debiasing methods. Finally, we discuss future studies for recognizing and mitigating gender bias in NLP.

For unsegmented languages such as Japanese and Chinese, tokenization of a sentence has a significant impact on the performance of text classification. Sentences are usually segmented with words or subwords by a morphological analyzer or byte pair encoding and then encoded with word (or subword) representations for neural networks. However, segmentation is potentially ambiguous, and it is unclear whether the segmented tokens achieve the best performance for the target task. In this paper, we propose a method to simultaneously learn tokenization and text classification to address these problems. Our model incorporates a language model for unsupervised tokenization into a text classifier and then trains both models simultaneously. To make the model robust against infrequent tokens, we sampled segmentation for each sentence stochastically during training, which resulted in improved performance of text classification. We conducted experiments on sentiment analysis as a text classification task and show that our method achieves better performance than previous methods.

Training neural sequence-to-sequence models with simple token-level log-likelihood is now a standard approach to historical text normalization, albeit often outperformed by phrase-based models. Policy gradient training enables direct optimization for exact matches, and while the small datasets in historical text normalization are prohibitive of from-scratch reinforcement learning, we show that policy gradient fine-tuning leads to significant improvements across the board. Policy gradient training, in particular, leads to more accurate normalizations for long or unseen words.

We incorporate morphological supervision into character language models (CLMs) via multitasking and show that this addition improves bits-per-character (BPC) performance across 24 languages, even when the morphology data and language modeling data are disjoint. Analyzing the CLMs shows that inflected words benefit more from explicitly modeling morphology than uninflected words, and that morphological supervision improves performance even as the amount of language modeling data grows. We then transfer morphological supervision across languages to improve performance in the low-resource setting.

To ascertain the importance of phonetic information in the form of phonological distinctive features for the purpose of segment-level phonotactic acquisition, we compare the performance of two recurrent neural network models of phonotactic learning: one that has access to distinctive features at the start of the learning process, and one that does not. Though the predictions of both models are significantly correlated with human judgments of non-words, the feature-naive model significantly outperforms the feature-aware one in terms of probability assigned to a held-out test set of English words, suggesting that distinctive features are not obligatory for learning phonotactic patterns at the segment level.

Pinyin-to-character (P2C) conversion is the core component of pinyin-based Chinese input method engine (IME). However, the conversion is seriously compromised by the ambiguities of Chinese characters corresponding to pinyin as well as the predefined fixed vocabularies. To alleviate such inconveniences, we propose a neural P2C conversion model augmented by an online updated vocabulary with a sampling mechanism to support open vocabulary learning during IME working. Our experiments show that the proposed method outperforms commercial IMEs and state-of-the-art traditional models on standard corpus and true inputting history dataset in terms of multiple metrics and thus the online updated vocabulary indeed helps our IME effectively follows user inputting behavior.

A lot of work has been done in the field of image compression via machine learning, but not much attention has been given to the compression of natural language. Compressing text into lossless representations while making features easily retrievable is not a trivial task, yet has huge benefits. Most methods designed to produce feature rich sentence embeddings focus solely on performing well on downstream tasks and are unable to properly reconstruct the original sequence from the learned embedding. In this work, we propose a near lossless method for encoding long sequences of texts as well as all of their sub-sequences into feature rich representations. We test our method on sentiment analysis and show good performance across all sub-sentence and sentence embeddings.

There has been an increased interest in multimodal language processing including multimodal dialog, question answering, sentiment analysis, and speech recognition. However, naturally occurring multimodal data is often imperfect as a result of imperfect modalities, missing entries or noise corruption. To address these concerns, we present a regularization method based on tensor rank minimization. Our method is based on the observation that high-dimensional multimodal time series data often exhibit correlations across time and modalities which leads to low-rank tensor representations. However, the presence of noise or incomplete values breaks these correlations and results in tensor representations of higher rank. We design a model to learn such tensor representations and effectively regularize their rank. Experiments on multimodal language data show that our model achieves good results across various levels of imperfection.

Transfer learning is effective for improving the performance of tasks that are related, and Multi-task learning (MTL) and Cross-lingual learning (CLL) are important instances. This paper argues that hard-parameter sharing, of hard-coding layers shared across different tasks or languages, cannot generalize well, when sharing with a loosely related task. Such case, which we call sparse transfer, might actually hurt performance, a phenomenon known as negative transfer. Our contribution is using adversarial training across tasks, to “soft-code” shared and private spaces, to avoid the shared space gets too sparse. In CLL, our proposed architecture considers another challenge of dealing with low-quality input.

Obstacles hindering the development of capsule networks for challenging NLP applications include poor scalability to large output spaces and less reliable routing processes. In this paper, we introduce: (i) an agreement score to evaluate the performance of routing processes at instance-level; (ii) an adaptive optimizer to enhance the reliability of routing; (iii) capsule compression and partial routing to improve the scalability of capsule networks. We validate our approach on two NLP tasks, namely: multi-label text classification and question answering. Experimental results show that our approach considerably improves over strong competitors on both tasks. In addition, we gain the best results in low-resource settings with few training instances.

Recurrent networks have achieved great success on various sequential tasks with the assistance of complex recurrent units, but suffer from severe computational inefficiency due to weak parallelization. One direction to alleviate this issue is to shift heavy computations outside the recurrence. In this paper, we propose a lightweight recurrent network, or LRN. LRN uses input and forget gates to handle long-range dependencies as well as gradient vanishing and explosion, with all parameter related calculations factored outside the recurrence. The recurrence in LRN only manipulates the weight assigned to each token, tightly connecting LRN with self-attention networks. We apply LRN as a drop-in replacement of existing recurrent units in several neural sequential models. Extensive experiments on six NLP tasks show that LRN yields the best running efficiency with little or no loss in model performance.

Many common character-level, string-to-string transduction tasks, e.g., grapheme-to-phoneme conversion and morphological inflection, consist almost exclusively of monotonic transduction. Neural sequence-to-sequence models with soft attention, non-monotonic models, outperform popular monotonic models. In this work, we ask the following question: Is monotonicity really a helpful inductive bias in these tasks? We develop a hard attention sequence-to-sequence model that enforces strict monotonicity and learns alignment jointly. With the help of dynamic programming, we are able to compute the exact marginalization over all alignments. Our models achieve state-of-the-art performance on morphological inflection. Furthermore, we find strong performance on two other character-level transduction tasks. Code is available at https://github.com/shijie-wu/neural-transducer.

This work examines the robustness of self-attentive neural networks against adversarial input perturbations. Specifically, we investigate the attention and feature extraction mechanisms of state-of-the-art recurrent neural networks and self-attentive architectures for sentiment analysis, entailment and machine translation under adversarial attacks. We also propose a novel attack algorithm for generating more natural adversarial examples that could mislead neural models but not humans. Experimental results show that, compared to recurrent neural models, self-attentive models are more robust against adversarial perturbation. In addition, we provide theoretical explanations for their superior robustness to support our claims.

Sequence-to-sequence models are a powerful workhorse of NLP. Most variants employ a softmax transformation in both their attention mechanism and output layer, leading to dense alignments and strictly positive output probabilities. This density is wasteful, making models less interpretable and assigning probability mass to many implausible outputs. In this paper, we propose sparse sequence-to-sequence models, rooted in a new family of \alpha-entmax transformations, which includes softmax and sparsemax as particular cases, and is sparse for any \alpha > 1. We provide fast algorithms to evaluate these transformations and their gradients, which scale well for large vocabulary sizes. Our models are able to produce sparse alignments and to assign nonzero probability to a short list of plausible outputs, sometimes rendering beam search exact. Experiments on morphological inflection and machine translation reveal consistent gains over dense models.

Many state-of-the-art neural models for NLP are heavily parameterized and thus memory inefficient. This paper proposes a series of lightweight and memory efficient neural architectures for a potpourri of natural language processing (NLP) tasks. To this end, our models exploit computation using Quaternion algebra and hypercomplex spaces, enabling not only expressive inter-component interactions but also significantly (75%) reduced parameter size due to lesser degrees of freedom in the Hamilton product. We propose Quaternion variants of models, giving rise to new architectures such as the Quaternion attention Model and Quaternion Transformer. Extensive experiments on a battery of NLP tasks demonstrates the utility of proposed Quaternion-inspired models, enabling up to 75% reduction in parameter size without significant loss in performance.

Common language models typically predict the next word given the context. In this work, we propose a method that improves language modeling by learning to align the given context and the following phrase. The model does not require any linguistic annotation of phrase segmentation. Instead, we define syntactic heights and phrase segmentation rules, enabling the model to automatically induce phrases, recognize their task-specific heads, and generate phrase embeddings in an unsupervised learning manner. Our method can easily be applied to language models with different network architectures since an independent module is used for phrase induction and context-phrase alignment, and no change is required in the underlying language modeling network. Experiments have shown that our model outperformed several strong baseline models on different data sets. We achieved a new state-of-the-art performance of 17.4 perplexity on the Wikitext-103 dataset. Additionally, visualizing the outputs of the phrase induction module showed that our model is able to learn approximate phrase-level structural knowledge without any annotation.

In this paper, we study the problem of hybrid language modeling, that is using models which can predict both characters and larger units such as character ngrams or words. Using such models, multiple potential segmentations usually exist for a given string, for example one using words and one using characters only. Thus, the probability of a string is the sum of the probabilities of all the possible segmentations. Here, we show how it is possible to marginalize over the segmentations efficiently, in order to compute the true probability of a sequence. We apply our technique on three datasets, comprising seven languages, showing improvements over a strong character level language model.

Highly regularized LSTMs achieve impressive results on several benchmark datasets in language modeling. We propose a new regularization method based on decoding the last token in the context using the predicted distribution of the next token. This biases the model towards retaining more contextual information, in turn improving its ability to predict the next token. With negligible overhead in the number of parameters and training time, our Past Decode Regularization (PDR) method improves perplexity on the Penn Treebank dataset by up to 1.8 points and by up to 2.3 points on the WikiText-2 dataset, over strong regularized baselines using a single softmax. With a mixture-of-softmax model, we show gains of up to 1.0 perplexity points on these datasets. In addition, our method achieves 1.169 bits-per-character on the Penn Treebank Character dataset for character level language modeling.

Gazetteers were shown to be useful resources for named entity recognition (NER). Many existing approaches to incorporating gazetteers into machine learning based NER systems rely on manually defined selection strategies or handcrafted templates, which may not always lead to optimal effectiveness, especially when multiple gazetteers are involved. This is especially the case for the task of Chinese NER, where the words are not naturally tokenized, leading to additional ambiguities. To automatically learn how to incorporate multiple gazetteers into an NER system, we propose a novel approach based on graph neural networks with a multi-digraph structure that captures the information that the gazetteers offer. Experiments on various datasets show that our model is effective in incorporating rich gazetteer information while resolving ambiguities, outperforming previous approaches.