EMNLP 2021 论文列表

We propose a novel framework to train models to classify acceptability of responses generated by natural language generation (NLG) models, improving upon existing sentence transformation and model-based approaches. An NLG response is considered acceptable if it is both semantically correct and grammatical. We don’t make use of any human references making the classifiers suitable for runtime deployment. Training data for the classifiers is obtained using a 2-stage approach of first generating synthetic data using a combination of existing and new model-based approaches followed by a novel validation framework to filter and sort the synthetic data into acceptable and unacceptable classes. Our 2-stage approach adapts to a wide range of data representations and does not require additional data beyond what the NLG models are trained on. It is also independent of the underlying NLG model architecture, and is able to generate more realistic samples close to the distribution of the NLG model-generated responses. We present results on 5 datasets (WebNLG, Cleaned E2E, ViGGO, Alarm, and Weather) with varying data representations. We compare our framework with existing techniques that involve synthetic data generation using simple sentence transformations and/or model-based techniques, and show that building acceptability classifiers using data that resembles the generation model outputs followed by a validation framework outperforms the existing techniques, achieving state-of-the-art results. We also show that our techniques can be used in few-shot settings using self-training.

Commonsense is defined as the knowledge on which everyone agrees. However, certain types of commonsense knowledge are correlated with culture and geographic locations and they are only shared locally. For example, the scenes of wedding ceremonies vary across regions due to different customs influenced by historical and religious factors. Such regional characteristics, however, are generally omitted in prior work. In this paper, we construct a Geo-Diverse Visual Commonsense Reasoning dataset (GD-VCR) to test vision-and-language models’ ability to understand cultural and geo-location-specific commonsense. In particular, we study two state-of-the-art Vision-and-Language models, VisualBERT and ViLBERT trained on VCR, a standard benchmark with images primarily from Western regions. We then evaluate how well the trained models can generalize to answering the questions in GD-VCR. We find that the performance of both models for non-Western regions including East Asia, South Asia, and Africa is significantly lower than that for Western region. We analyze the reasons behind the performance disparity and find that the performance gap is larger on QA pairs that: 1) are concerned with culture-related scenarios, e.g., weddings, religious activities, and festivals; 2) require high-level geo-diverse commonsense reasoning rather than low-order perception and recognition. Dataset and code are released at https://github.com/WadeYin9712/GD-VCR.

There is a growing consensus that surface form alone does not enable models to learn meaning and gain language understanding. This warrants an interest in hybrid systems that combine the strengths of neural and symbolic methods. We favour triadic systems consisting of neural networks, knowledge bases, and inference engines. The network provides perception, that is, the interface between the system and its environment. The knowledge base provides explicit memory and thus immediate access to established facts. Finally, inference capabilities are provided by the inference engine which reflects on the perception, supported by memory, to reason and discover new facts. In this work, we probe six popular language models for semantic relations and outline a future line of research to study how the constituent subsystems can be jointly realised and integrated.

Zero-shot cross-domain slot filling alleviates the data dependence in the case of data scarcity in the target domain, which has aroused extensive research. However, as most of the existing methods do not achieve effective knowledge transfer to the target domain, they just fit the distribution of the seen slot and show poor performance on unseen slot in the target domain. To solve this, we propose a novel approach based on prototypical contrastive learning with a dynamic label confusion strategy for zero-shot slot filling. The prototypical contrastive learning aims to reconstruct the semantic constraints of labels, and we introduce the label confusion strategy to establish the label dependence between the source domains and the target domain on-the-fly. Experimental results show that our model achieves significant improvement on the unseen slots, while also set new state-of-the-arts on slot filling task.

A fundamental component to the success of modern representation learning is the ease of performing various vector operations. Recently, objects with more geometric structure (eg. distributions, complex or hyperbolic vectors, or regions such as cones, disks, or boxes) have been explored for their alternative inductive biases and additional representational capacity. In this work, we introduce Box Embeddings, a Python library that enables researchers to easily apply and extend probabilistic box embeddings. Fundamental geometric operations on boxes are implemented in a numerically stable way, as are modern approaches to training boxes which mitigate gradient sparsity. The library is fully open source, and compatible with both PyTorch and TensorFlow, which allows existing neural network layers to be replaced with or transformed into boxes easily. In this work, we present the implementation details of the fundamental components of the library, and the concepts required to use box representations alongside existing neural network architectures.

Recent multilingual pre-trained language models have achieved remarkable zero-shot performance, where the model is only finetuned on one source language and directly evaluated on target languages. In this work, we propose a self-learning framework that further utilizes unlabeled data of target languages, combined with uncertainty estimation in the process to select high-quality silver labels. Three different uncertainties are adapted and analyzed specifically for the cross lingual transfer: Language Heteroscedastic/Homoscedastic Uncertainty (LEU/LOU), Evidential Uncertainty (EVI). We evaluate our framework with uncertainties on two cross-lingual tasks including Named Entity Recognition (NER) and Natural Language Inference (NLI) covering 40 languages in total, which outperforms the baselines significantly by 10 F1 for NER on average and 2.5 accuracy for NLI.

Word embedding is essential for neural network models for various natural language processing tasks. Since the word embedding usually has a considerable size, in order to deploy a neural network model having it on edge devices, it should be effectively compressed. There was a study for proposing a block-wise low-rank approximation method for word embedding, called GroupReduce. Even if their structure is effective, the properties behind the concept of the block-wise word embedding compression were not sufficiently explored. Motivated by this, we improve GroupReduce in terms of word weighting and structuring. For word weighting, we propose a simple yet effective method inspired by the term frequency-inverse document frequency method and a novel differentiable method. Based on them, we construct a discriminative word embedding compression algorithm. In the experiments, we demonstrate that the proposed algorithm more effectively finds word weights than competitors in most cases. In addition, we show that the proposed algorithm can act like a framework through successful cooperation with quantization.

Pre-training has improved model accuracy for both classification and generation tasks at the cost of introducing much larger and slower models. Pruning methods have proven to be an effective way of reducing model size, whereas distillation methods are proven for speeding up inference. We introduce a block pruning approach targeting both small and fast models. Our approach extends structured methods by considering blocks of any size and integrates this structure into the movement pruning paradigm for fine-tuning. We find that this approach learns to prune out full components of the underlying model, such as attention heads. Experiments consider classification and generation tasks, yielding among other results a pruned model that is a 2.4x faster, 74% smaller BERT on SQuAD v1, with a 1% drop on F1, competitive both with distilled models in speed and pruned models in size.

Biomedical Concept Normalization (BCN) is widely used in biomedical text processing as a fundamental module. Owing to numerous surface variants of biomedical concepts, BCN still remains challenging and unsolved. In this paper, we exploit biomedical concept hypernyms to facilitate BCN. We propose Biomedical Concept Normalizer with Hypernyms (BCNH), a novel framework that adopts list-wise training to make use of both hypernyms and synonyms, and also employs norm constraint on the representation of hypernym-hyponym entity pairs. The experimental results show that BCNH outperforms the previous state-of-the-art model on the NCBI dataset.

Emotion cause extraction (ECE) aims to extract the causes behind the certain emotion in text. Some works related to the ECE task have been published and attracted lots of attention in recent years. However, these methods neglect two major issues: 1) pay few attentions to the effect of document-level context information on ECE, and 2) lack of sufficient exploration for how to effectively use the annotated emotion clause. For the first issue, we propose a bidirectional hierarchical attention network (BHA) corresponding to the specified candidate cause clause to capture the document-level context in a structured and dynamic manner. For the second issue, we design an emotional filtering module (EF) for each layer of the graph attention network, which calculates a gate score based on the emotion clause to filter the irrelevant information. Combining the BHA and EF, the EF-BHA can dynamically aggregate the contextual information from two directions and filters irrelevant information. The experimental results demonstrate that EF-BHA achieves the competitive performances on two public datasets in different languages (Chinese and English). Moreover, we quantify the effect of context on emotion cause extraction and provide the visualization of the interactions between candidate cause clauses and contexts.

An important task in NLP applications such as sentence simplification is the ability to take a long, complex sentence and split it into shorter sentences, rephrasing as necessary. We introduce a novel dataset and a new model for this ‘split and rephrase’ task. Our BiSECT training data consists of 1 million long English sentences paired with shorter, meaning-equivalent English sentences. We obtain these by extracting 1-2 sentence alignments in bilingual parallel corpora and then using machine translation to convert both sides of the corpus into the same language. BiSECT contains higher quality training examples than the previous Split and Rephrase corpora, with sentence splits that require more significant modifications. We categorize examples in our corpus and use these categories in a novel model that allows us to target specific regions of the input sentence to be split and edited. Moreover, we show that models trained on BiSECT can perform a wider variety of split operations and improve upon previous state-of-the-art approaches in automatic and human evaluations.

Knowledge graph embeddings (KGEs) compactly encode multi-relational knowledge graphs (KGs). Existing KGE models rely on geometric operations to model relational patterns. Euclidean (circular) rotation is useful for modeling patterns such as symmetry, but cannot represent hierarchical semantics. In contrast, hyperbolic models are effective at modeling hierarchical relations, but do not perform as well on patterns on which circular rotation excels. It is crucial for KGE models to unify multiple geometric transformations so as to fully cover the multifarious relations in KGs. To do so, we propose BiQUE, a novel model that employs biquaternions to integrate multiple geometric transformations, viz., scaling, translation, Euclidean rotation, and hyperbolic rotation. BiQUE makes the best trade-offs among geometric operators during training, picking the best one (or their best combination) for each relation. Experiments on five datasets show BiQUE’s effectiveness.

As large-scale, pre-trained language models achieve human-level and superhuman accuracy on existing language understanding tasks, statistical bias in benchmark data and probing studies have recently called into question their true capabilities. For a more informative evaluation than accuracy on text classification tasks can offer, we propose evaluating systems through a novel measure of prediction coherence. We apply our framework to two existing language understanding benchmarks with different properties to demonstrate its versatility. Our experimental results show that this evaluation framework, although simple in ideas and implementation, is a quick, effective, and versatile measure to provide insight into the coherence of machines’ predictions.

Multi-label document classification, associating one document instance with a set of relevant labels, is attracting more and more research attention. Existing methods explore the incorporation of information beyond text, such as document metadata or label structure. These approaches however either simply utilize the semantic information of metadata or employ the predefined parent-child label hierarchy, ignoring the heterogeneous graphical structures of metadata and labels, which we believe are crucial for accurate multi-label document classification. Therefore, in this paper, we propose a novel neural network based approach for multi-label document classification, in which two heterogeneous graphs are constructed and learned using heterogeneous graph transformers. One is metadata heterogeneous graph, which models various types of metadata and their topological relations. The other is label heterogeneous graph, which is constructed based on both the labels’ hierarchy and their statistical dependencies. Experimental results on two benchmark datasets show the proposed approach outperforms several state-of-the-art baselines.

Meta-learning algorithms such as MAML, Reptile, and FOMAML have led to improved performance of several neural models. The primary difference between standard gradient descent and these meta-learning approaches is that they contain as a small component the gradient for maximizing dot-product between gradients of batches, leading to improved generalization. Previous work has shown that aligned gradients are related to generalization, and have also used the Reptile algorithm in a single-task setting to improve generalization. Inspired by these approaches for a single task setting, this paper proposes to use the finite differences first-order algorithm to calculate this gradient from dot-product of gradients, allowing explicit control on the weightage of this component relative to standard gradients. We use this gradient as a regularization technique, leading to more aligned gradients between different batches. By using the finite differences approximation, our approach does not suffer from O(nˆ2) memory usage of naively calculating the Hessian and can be easily applied to large models with large batch sizes. Our approach achieves state-of-the-art performance on the Gigaword dataset, and shows performance improvements on several datasets such as SQuAD-v2.0, Quasar-T, NewsQA and all the SuperGLUE datasets, with a range of models such as BERT, RoBERTa and ELECTRA. Our method also outperforms previous approaches of Reptile and FOMAML when used as a regularization technique, in both single and multi-task settings. Our method is model agnostic, and introduces no extra trainable weights.

Recent studies on compression of pretrained language models (e.g., BERT) usually use preserved accuracy as the metric for evaluation. In this paper, we propose two new metrics, label loyalty and probability loyalty that measure how closely a compressed model (i.e., student) mimics the original model (i.e., teacher). We also explore the effect of compression with regard to robustness under adversarial attacks. We benchmark quantization, pruning, knowledge distillation and progressive module replacing with loyalty and robustness. By combining multiple compression techniques, we provide a practical strategy to achieve better accuracy, loyalty and robustness.

In this paper, we present a new method for training a writing improvement model adapted to the writer’s first language (L1) that goes beyond grammatical error correction (GEC). Without using annotated training data, we rely solely on pre-trained language models fine-tuned with parallel corpora of reference translation aligned with machine translation. We evaluate our model with corpora of academic papers written in English by L1 Portuguese and L1 Spanish scholars and a reference corpus of expert academic English. We show that our model is able to address specific L1-influenced writing and more complex linguistic phenomena than existing methods, outperforming what a state-of-the-art GEC system can achieve in this regard. Our code and data are open to other researchers.

Quality Estimation (QE) plays an essential role in applications of Machine Translation (MT). Traditionally, a QE system accepts the original source text and translation from a black-box MT system as input. Recently, a few studies indicate that as a by-product of translation, QE benefits from the model and training data’s information of the MT system where the translations come from, and it is called the “glass-box QE”. In this paper, we extend the definition of “glass-box QE” generally to uncertainty quantification with both “black-box” and “glass-box” approaches and design several features deduced from them to blaze a new trial in improving QE’s performance. We propose a framework to fuse the feature engineering of uncertainty quantification into a pre-trained cross-lingual language model to predict the translation quality. Experiment results show that our method achieves state-of-the-art performances on the datasets of WMT 2020 QE shared task.

Sparse Mixture-of-Experts (MoE) has been a successful approach for scaling multilingual translation models to billions of parameters without a proportional increase in training computation. However, MoE models are prohibitively large and practitioners often resort to methods such as distillation for serving. In this work, we investigate routing strategies at different granularity (token, sentence, task) in MoE models to bypass distillation. Experiments on WMT and a web-scale dataset suggest that task-level routing (task-MoE) enables us to extract smaller, ready-to-deploy sub-networks from large sparse models. On WMT, our task-MoE with 32 experts (533M parameters) outperforms the best performing token-level MoE model (token-MoE) by +1.0 BLEU on average across 30 language pairs. The peak inference throughput is also improved by a factor of 1.9x when we route by tasks instead of tokens. While distilling a token-MoE to a smaller dense model preserves only 32% of the BLEU gains, our sub-network task-MoE, by design, preserves all the gains with the same inference cost as the distilled student model. Finally, when scaling up to 200 language pairs, our 128-expert task-MoE (13B parameters) performs competitively with a token-level counterpart, while improving the peak inference throughput by a factor of 2.6x.