ACL 2021 Papers

The importance of parameter selection in supervised learning is well known. However, due to the many parameter combinations, an incomplete or an insufficient procedure is often applied. This situation may cause misleading or confusing conclusions. In this opinion paper, through an intriguing example we point out that the seriousness goes beyond what is generally recognized. In the topic of multilabel classification for medical code prediction, one influential paper conducted a proper parameter selection on a set, but when moving to a subset of frequently occurring labels, the authors used the same parameters without a separate tuning. The set of frequent labels became a popular benchmark in subsequent studies, which kept pushing the state of the art. However, we discovered that most of the results in these studies cannot surpass the approach in the original paper if a parameter tuning had been conducted at the time. Thus it is unclear how much progress the subsequent developments have actually brought. The lesson clearly indicates that without enough attention on parameter selection, the research progress in our field can be uncertain or even illusive.

Distance based knowledge graph embedding methods show promising results on link prediction task, on which two topics have been widely studied: one is the ability to handle complex relations, such as N-to-1, 1-to-N and N-to-N, the other is to encode various relation patterns, such as symmetry/antisymmetry. However, the existing methods fail to solve these two problems at the same time, which leads to unsatisfactory results. To mitigate this problem, we propose PairRE, a model with paired vectors for each relation representation. The paired vectors enable an adaptive adjustment of the margin in loss function to fit for different complex relations. Besides, PairRE is capable of encoding three important relation patterns, symmetry/antisymmetry, inverse and composition. Given simple constraints on relation representations, PairRE can encode subrelation further. Experiments on link prediction benchmarks demonstrate the proposed key capabilities of PairRE. Moreover, We set a new state-of-the-art on two knowledge graph datasets of the challenging Open Graph Benchmark.

Recent research considers few-shot intent detection as a meta-learning problem: the model is learning to learn from a consecutive set of small tasks named episodes. In this work, we propose ProtAugment, a meta-learning algorithm for short texts classification (the intent detection task). ProtAugment is a novel extension of Prototypical Networks, that limits overfitting on the bias introduced by the few-shots classification objective at each episode. It relies on diverse paraphrasing: a conditional language model is first fine-tuned for paraphrasing, and diversity is later introduced at the decoding stage at each meta-learning episode. The diverse paraphrasing is unsupervised as it is applied to unlabelled data, and then fueled to the Prototypical Network training objective as a consistency loss. ProtAugment is the state-of-the-art method for intent detection meta-learning, at no extra labeling efforts and without the need to fine-tune a conditional language model on a given application domain.

Joint extraction of entities and relations from unstructured texts is a crucial task in information extraction. Recent methods achieve considerable performance but still suffer from some inherent limitations, such as redundancy of relation prediction, poor generalization of span-based extraction and inefficiency. In this paper, we decompose this task into three subtasks, Relation Judgement, Entity Extraction and Subject-object Alignment from a novel perspective and then propose a joint relational triple extraction framework based on Potential Relation and Global Correspondence (PRGC). Specifically, we design a component to predict potential relations, which constrains the following entity extraction to the predicted relation subset rather than all relations; then a relation-specific sequence tagging component is applied to handle the overlapping problem between subjects and objects; finally, a global correspondence component is designed to align the subject and object into a triple with low-complexity. Extensive experiments show that PRGC achieves state-of-the-art performance on public benchmarks with higher efficiency and delivers consistent performance gain on complex scenarios of overlapping triples. The source code has been submitted as the supplementary material and will be made publicly available after the blind review.

Large pre-trained language generation models such as GPT-2 have demonstrated their effectiveness as language priors by reaching state-of-the-art results in various language generation tasks. However, the performance of pre-trained models on task-oriented dialog tasks is still under-explored. We propose a Pre-trainedRole Alternating Language model (PRAL), explicitly designed for task-oriented conversational systems. We design several techniques: start position randomization, knowledge distillation, and history discount to improve pre-training performance. In addition, we introduce a high-quality large-scale task-oriented dialog pre-training dataset by post-prossessing13 dialog datasets. We effectively adapt PRALon three downstream tasks. The results show that PRAL outperforms or is on par with state-of-the-art models.

Personalized news recommendation methods are widely used in online news services. These methods usually recommend news based on the matching between news content and user interest inferred from historical behaviors. However, these methods usually have difficulties in making accurate recommendations to cold-start users, and tend to recommend similar news with those users have read. In general, popular news usually contain important information and can attract users with different interests. Besides, they are usually diverse in content and topic. Thus, in this paper we propose to incorporate news popularity information to alleviate the cold-start and diversity problems for personalized news recommendation. In our method, the ranking score for recommending a candidate news to a target user is the combination of a personalized matching score and a news popularity score. The former is used to capture the personalized user interest in news. The latter is used to measure time-aware popularity of candidate news, which is predicted based on news content, recency, and real-time CTR using a unified framework. Besides, we propose a popularity-aware user encoder to eliminate the popularity bias in user behaviors for accurate interest modeling. Experiments on two real-world datasets show our method can effectively improve the accuracy and diversity for news recommendation.

The multimodality problem has become a major challenge of existing non-autoregressive generation (NAG) systems. A common solution often resorts to sequence-level knowledge distillation by rebuilding the training dataset through autoregressive generation (hereinafter known as “teacher AG”). The success of such methods may largely depend on a latent assumption, i.e., the teacher AG is superior to the NAG model. However, in this work, we experimentally reveal that this assumption does not always hold for the text generation tasks like text summarization and story ending generation. To provide a feasible solution to the multimodality problem of NAG, we propose incorporating linguistic structure (Part-of-Speech sequence in particular) into NAG inference instead of relying on teacher AG. More specifically, the proposed POS-constrained Parallel Decoding (POSPD) method aims at providing a specific POS sequence to constrain the NAG model during decoding. Our experiments demonstrate that POSPD consistently improves NAG models on four text generation tasks to a greater extent compared to knowledge distillation. This observation validates the necessity of exploring the alternatives for sequence-level knowledge distillation.

Chinese spelling correction (CSC) is a task to detect and correct spelling errors in texts. CSC is essentially a linguistic problem, thus the ability of language understanding is crucial to this task. In this paper, we propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) for CSC, which jointly learns how to understand language and correct spelling errors. To this end, PLOME masks the chosen tokens with similar characters according to a confusion set rather than the fixed token “[MASK]” as in BERT. Besides character prediction, PLOME also introduces pronunciation prediction to learn the misspelled knowledge on phonic level. Moreover, phonological and visual similarity knowledge is important to this task. PLOME utilizes GRU networks to model such knowledge based on characters’ phonics and strokes. Experiments are conducted on widely used benchmarks. Our method achieves superior performance against state-of-the-art approaches by a remarkable margin. We release the source code and pre-trained model for further use by the community (https://github.com/liushulinle/PLOME).

We propose PIGLeT: a model that learns physical commonsense knowledge through interaction, and then uses this knowledge to ground language. We factorize PIGLeT into a physical dynamics model, and a separate language model. Our dynamics model learns not just what objects are but also what they do: glass cups break when thrown, plastic ones don’t. We then use it as the interface to our language model, giving us a unified model of linguistic form and grounded meaning. PIGLeT can read a sentence, simulate neurally what might happen next, and then communicate that result through a literal symbolic representation, or natural language. Experimental results show that our model effectively learns world dynamics, along with how to communicate them. It is able to correctly forecast what happens next given an English sentence over 80% of the time, outperforming a 100x larger, text-to-text approach by over 10%. Likewise, its natural language summaries of physical interactions are also judged by humans as more accurate than LM alternatives. We present comprehensive analysis showing room for future work.

Chinese Spelling Check (CSC) is a challenging task due to the complex characteristics of Chinese characters. Statistics reveal that most Chinese spelling errors belong to phonological or visual errors. However, previous methods rarely utilize phonological and morphological knowledge of Chinese characters or heavily rely on external resources to model their similarities. To address the above issues, we propose a novel end-to-end trainable model called PHMOSpell, which promotes the performance of CSC with multi-modal information. Specifically, we derive pinyin and glyph representations for Chinese characters from audio and visual modalities respectively, which are integrated into a pre-trained language model by a well-designed adaptive gating mechanism. To verify its effectiveness, we conduct comprehensive experiments and ablation tests. Experimental results on three shared benchmarks demonstrate that our model consistently outperforms previous state-of-the-art models.

In this paper, we formulate the personalized news headline generation problem whose goal is to output a user-specific title based on both a user’s reading interests and a candidate news body to be exposed to her. To build up a benchmark for this problem, we publicize a large-scale dataset named PENS (PErsonalized News headlineS). The training set is collected from user impressions logs of Microsoft News, and the test set is manually created by hundreds of native speakers to enable a fair testbed for evaluating models in an offline mode. We propose a generic framework as a preparatory solution to our problem. At its heart, user preference is learned by leveraging the user behavioral data, and three kinds of user preference injections are proposed to personalize a text generator and establish personalized headlines. We investigate our dataset by implementing several state-of-the-art user modeling methods in our framework to demonstrate a benchmark score for the proposed dataset. The dataset is available at https://msnews.github.io/pens.html.

The product reviews summarization task aims to automatically produce a short summary for a set of reviews of a given product. Such summaries are expected to aggregate a range of different opinions in a concise, coherent and informative manner. This challenging task gives rise to two shortcomings in existing work. First, summarizers tend to favor generic content that appears in reviews for many different products, resulting in template-like, less informative summaries. Second, as reviewers often disagree on the pros and cons of a given product, summarizers sometimes yield inconsistent, self-contradicting summaries. We propose the PASS system (Perturb-and-Select Summarizer) that employs a large pre-trained Transformer-based model (T5 in our case), which follows a few-shot fine-tuning scheme. A key component of the PASS system relies on applying systematic perturbations to the model’s input during inference, which allows it to generate multiple different summaries per product. We develop a method for ranking these summaries according to desired criteria, coherence in our case, enabling our system to almost entirely avoid the problem of self-contradiction. We compare our system against strong baselines on publicly available datasets, and show that it produces summaries which are more informative, diverse and coherent.

Out-of-distribution (OOD) intent detection is of practical importance in task-oriented dialogue systems. Since the distribution of outlier utterances is arbitrary and unknown in the training stage, existing methods commonly rely on strong assumptions on data distribution such as mixture of Gaussians to make inference, resulting in either complex multi-step training procedures or hand-crafted rules such as confidence threshold selection for outlier detection.In this paper, we propose a simple yet effective method to train an OOD intent classifier in a fully end-to-end manner by simulating the test scenario in training, which requires no assumption on data distribution and no additional post-processing or threshold setting. Specifically, we construct a set of pseudo outliers in the training stage, by generating synthetic outliers using inliner features via self-supervision and sampling OOD sentences from easily available open-domain datasets. The pseudo outliers are used to train a discriminative classifier that can be directly applied to and generalize well on the test task. We evaluate our method extensively on four benchmark dialogue datasets and observe significant improvements over state-of-the-art approaches.The source code has been made available at \url{https://github.com/liam0949/DCLOOS}.

It is a common belief that training deep transformers from scratch requires large datasets. Consequently, for small datasets, people usually use shallow and simple additional layers on top of pre-trained models during fine-tuning. This work shows that this does not always need to be the case: with proper initialization and optimization, the benefits of very deep transformers can carry over to challenging tasks with small datasets, including Text-to-SQL semantic parsing and logical reading comprehension. In particular, we successfully train 48 layers of transformers, comprising 24 fine-tuned layers from pre-trained RoBERTa and 24 relation-aware layers trained from scratch. With fewer training steps and no task-specific pre-training, we obtain the state of the art performance on the challenging cross-domain Text-to-SQL parsing benchmark Spider. We achieve this by deriving a novel Data dependent Transformer Fixed-update initialization scheme (DT-Fixup), inspired by the prior T-Fixup work. Further error analysis shows that increasing depth can help improve generalization on small datasets for hard cases that require reasoning and structural understanding.

Automatic metrics are essential for developing natural language generation (NLG) models, particularly for open-ended language generation tasks such as story generation. However, existing automatic metrics are observed to correlate poorly with human evaluation. The lack of standardized benchmark datasets makes it difficult to fully evaluate the capabilities of a metric and fairly compare different metrics. Therefore, we propose OpenMEVA, a benchmark for evaluating open-ended story generation metrics. OpenMEVA provides a comprehensive test suite to assess the capabilities of metrics, including (a) the correlation with human judgments, (b) the generalization to different model outputs and datasets, (c) the ability to judge story coherence, and (d) the robustness to perturbations. To this end, OpenMEVA includes both manually annotated stories and auto-constructed test examples. We evaluate existing metrics on OpenMEVA and observe that they have poor correlation with human judgments, fail to recognize discourse-level incoherence, and lack inferential knowledge (e.g., causal order between events), the generalization ability and robustness. Our study presents insights for developing NLG models and metrics in further research.

Recent studies on neural networks with pre-trained weights (i.e., BERT) have mainly focused on a low-dimensional subspace, where the embedding vectors computed from input words (or their contexts) are located. In this work, we propose a new approach, called OoMMix, to finding and regularizing the remainder of the space, referred to as out-of-manifold, which cannot be accessed through the words. Specifically, we synthesize the out-of-manifold embeddings based on two embeddings obtained from actually-observed words, to utilize them for fine-tuning the network. A discriminator is trained to detect whether an input embedding is located inside the manifold or not, and simultaneously, a generator is optimized to produce new embeddings that can be easily identified as out-of-manifold by the discriminator. These two modules successfully collaborate in a unified and end-to-end manner for regularizing the out-of-manifold. Our extensive evaluation on various text classification benchmarks demonstrates the effectiveness of our approach, as well as its good compatibility with existing data augmentation techniques which aim to enhance the manifold.

SOTA coreference resolution produces increasingly impressive scores on the OntoNotes benchmark. However lack of comparable data following the same scheme for more genres makes it difficult to evaluate generalizability to open domain data. This paper provides a dataset and comprehensive evaluation showing that the latest neural LM based end-to-end systems degrade very substantially out of domain. We make an OntoNotes-like coreference dataset called OntoGUM publicly available, converted from GUM, an English corpus covering 12 genres, using deterministic rules, which we evaluate. Thanks to the rich syntactic and discourse annotations in GUM, we are able to create the largest human-annotated coreference corpus following the OntoNotes guidelines, and the first to be evaluated for consistency with the OntoNotes scheme. Out-of-domain evaluation across 12 genres shows nearly 15-20% degradation for both deterministic and deep learning systems, indicating a lack of generalizability or covert overfitting in existing coreference resolution models.

Event Detection (ED) aims to identify event trigger words from a given text and classify it into an event type. Most current methods to ED rely heavily on training instances, and almost ignore the correlation of event types. Hence, they tend to suffer from data scarcity and fail to handle new unseen event types. To address these problems, we formulate ED as a process of event ontology population: linking event instances to pre-defined event types in event ontology, and propose a novel ED framework entitled OntoED with ontology embedding. We enrich event ontology with linkages among event types, and further induce more event-event correlations. Based on the event ontology, OntoED can leverage and propagate correlation knowledge, particularly from data-rich to data-poor event types. Furthermore, OntoED can be applied to new unseen event types, by establishing linkages to existing ones. Experiments indicate that OntoED is more predominant and robust than previous approaches to ED, especially in data-scarce scenarios.

In Machine Translation, assessing the quality of a large amount of automatic translations can be challenging. Automatic metrics are not reliable when it comes to high performing systems. In addition, resorting to human evaluators can be expensive, especially when evaluating multiple systems. To overcome the latter challenge, we propose a novel application of online learning that, given an ensemble of Machine Translation systems, dynamically converges to the best systems, by taking advantage of the human feedback available. Our experiments on WMT’19 datasets show that our online approach quickly converges to the top-3 ranked systems for the language pairs considered, despite the lack of human feedback for many translations.