ACL 2021 Papers

Identifying causal relations of events is an important task in natural language processing area. However, the task is very challenging, because event causality is usually expressed in diverse forms that often lack explicit causal clues. Existing methods cannot handle well the problem, especially in the condition of lacking training data. Nonetheless, humans can make a correct judgement based on their background knowledge, including descriptive knowledge and relational knowledge. Inspired by it, we propose a novel Latent Structure Induction Network (LSIN) to incorporate the external structural knowledge into this task. Specifically, to make use of the descriptive knowledge, we devise a Descriptive Graph Induction module to obtain and encode the graph-structured descriptive knowledge. To leverage the relational knowledge, we propose a Relational Graph Induction module which is able to automatically learn a reasoning structure for event causality reasoning. Experimental results on two widely used datasets indicate that our approach significantly outperforms previous state-of-the-art methods.

This paper studies a new problem setting of entity alignment for knowledge graphs (KGs). Since KGs possess different sets of entities, there could be entities that cannot find alignment across them, leading to the problem of dangling entities. As the first attempt to this problem, we construct a new dataset and design a multi-task learning framework for both entity alignment and dangling entity detection. The framework can opt to abstain from predicting alignment for the detected dangling entities. We propose three techniques for dangling entity detection that are based on the distribution of nearest-neighbor distances, i.e., nearest neighbor classification, marginal ranking and background ranking. After detecting and removing dangling entities, an incorporated entity alignment model in our framework can provide more robust alignment for remaining entities. Comprehensive experiments and analyses demonstrate the effectiveness of our framework. We further discover that the dangling entity detection module can, in turn, improve alignment learning and the final performance. The contributed resource is publicly available to foster further research.

This work presents Keep it Simple (KiS), a new approach to unsupervised text simplification which learns to balance a reward across three properties: fluency, salience and simplicity. We train the model with a novel algorithm to optimize the reward (k-SCST), in which the model proposes several candidate simplifications, computes each candidate’s reward, and encourages candidates that outperform the mean reward. Finally, we propose a realistic text comprehension task as an evaluation method for text simplification. When tested on the English news domain, the KiS model outperforms strong supervised baselines by more than 4 SARI points, and can help people complete a comprehension task an average of 18% faster while retaining accuracy, when compared to the original text.

The goal of database question answering is to enable natural language querying of real-life relational databases in diverse application domains. Recently, large-scale datasets such as Spider and WikiSQL facilitated novel modeling techniques for text-to-SQL parsing, improving zero-shot generalization to unseen databases. In this work, we examine the challenges that still prevent these techniques from practical deployment. First, we present KaggleDBQA, a new cross-domain evaluation dataset of real Web databases, with domain-specific data types, original formatting, and unrestricted questions. Second, we re-examine the choice of evaluation tasks for text-to-SQL parsers as applied in real-life settings. Finally, we augment our in-domain evaluation task with database documentation, a naturally occurring source of implicit domain knowledge. We show that KaggleDBQA presents a challenge to state-of-the-art zero-shot parsers but a more realistic evaluation setting and creative use of associated database documentation boosts their accuracy by over 13.2%, doubling their performance.

We present Knowledge Enhanced Multimodal BART (KM-BART), which is a Transformer-based sequence-to-sequence model capable of reasoning about commonsense knowledge from multimodal inputs of images and texts. We adapt the generative BART architecture (Lewis et al., 2020) to a multimodal model with visual and textual inputs. We further develop novel pretraining tasks to improve the model performance on the Visual Commonsense Generation (VCG) task. In particular, our pretraining task of Knowledge-based Commonsense Generation (KCG) boosts model performance on the VCG task by leveraging commonsense knowledge from a large language model pretrained on external commonsense knowledge graphs. To the best of our knowledge, we are the first to propose a dedicated task for improving model performance on the VCG task. Experimental results show that our model reaches state-of-the-art performance on the VCG task (Park et al., 2020) by applying these novel pretraining tasks.

In order to better understand the reason behind model behaviors (i.e., making predictions), most recent works have exploited generative models to provide complementary explanations. However, existing approaches in NLP mainly focus on “WHY A” rather than contrastive “WHY A NOT B”, which is shown to be able to better distinguish confusing candidates and improve data efficiency in other research fields. In this paper, we focus on generating contrastive explanations with counterfactual examples in NLI and propose a novel Knowledge-Aware Contrastive Explanation generation framework (KACE).Specifically, we first identify rationales (i.e., key phrases) from input sentences, and use them as key perturbations for generating counterfactual examples. After obtaining qualified counterfactual examples, we take them along with original examples and external knowledge as input, and employ a knowledge-aware generative pre-trained language model to generate contrastive explanations. Experimental results show that contrastive explanations are beneficial to fit the scenarios by clarifying the difference between the predicted answer and other possible wrong ones. Moreover, we train an NLI model enhanced with contrastive explanations and achieves an accuracy of 91.9% on SNLI, gaining improvements of 5.7% against ETPA (“Explain-Then-Predict-Attention”) and 0.6% against NILE (“WHY A”).

Structured information is an important knowledge source for automatic verification of factual claims. Nevertheless, the majority of existing research into this task has focused on textual data, and the few recent inquiries into structured data have been for the closed-domain setting where appropriate evidence for each claim is assumed to have already been retrieved. In this paper, we investigate verification over structured data in the open-domain setting, introducing a joint reranking-and-verification model which fuses evidence documents in the verification component. Our open-domain model achieves performance comparable to the closed-domain state-of-the-art on the TabFact dataset, and demonstrates performance gains from the inclusion of multiple tables as well as a significant improvement over a heuristic retrieval baseline.

This paper studies joint models for selecting correct answer sentences among the top k provided by answer sentence selection (AS2) modules, which are core components of retrieval-based Question Answering (QA) systems. Our work shows that a critical step to effectively exploiting an answer set regards modeling the interrelated information between pair of answers. For this purpose, we build a three-way multi-classifier, which decides if an answer supports, refutes, or is neutral with respect to another one. More specifically, our neural architecture integrates a state-of-the-art AS2 module with the multi-classifier, and a joint layer connecting all components. We tested our models on WikiQA, TREC-QA, and a real-world dataset. The results show that our models obtain the new state of the art in AS2.

Compared to the general news domain, information extraction (IE) from biomedical text requires much broader domain knowledge. However, many previous IE methods do not utilize any external knowledge during inference. Due to the exponential growth of biomedical publications, models that do not go beyond their fixed set of parameters will likely fall behind. Inspired by how humans look up relevant information to comprehend a scientific text, we present a novel framework that utilizes external knowledge for joint entity and relation extraction named KECI (Knowledge-Enhanced Collective Inference). Given an input text, KECI first constructs an initial span graph representing its initial understanding of the text. It then uses an entity linker to form a knowledge graph containing relevant background knowledge for the the entity mentions in the text. To make the final predictions, KECI fuses the initial span graph and the knowledge graph into a more refined graph using an attention mechanism. KECI takes a collective approach to link mention spans to entities by integrating global relational information into local representations using graph convolutional networks. Our experimental results show that the framework is highly effective, achieving new state-of-the-art results in two different benchmark datasets: BioRelEx (binding interaction detection) and ADE (adverse drug event extraction). For example, KECI achieves absolute improvements of 4.59% and 4.91% in F1 scores over the state-of-the-art on the BioRelEx entity and relation extraction tasks

The general format of natural language inference (NLI) makes it tempting to be used for zero-shot text classification by casting any target label into a sentence of hypothesis and verifying whether or not it could be entailed by the input, aiming at generic classification applicable on any specified label space. In this opinion piece, we point out a few overlooked issues that are yet to be discussed in this line of work. We observe huge variance across different classification datasets amongst standard BERT-based NLI models and surprisingly find that pre-trained BERT without any fine-tuning can yield competitive performance against BERT fine-tuned for NLI. With the concern that these models heavily rely on spurious lexical patterns for prediction, we also experiment with preliminary approaches for more robust NLI, but the results are in general negative. Our observations reveal implicit but challenging difficulties in entailment-based zero-shot text classification.

Sparse attention has been claimed to increase model interpretability under the assumption that it highlights influential inputs. Yet the attention distribution is typically over representations internal to the model rather than the inputs themselves, suggesting this assumption may not have merit. We build on the recent work exploring the interpretability of attention; we design a set of experiments to help us understand how sparsity affects our ability to use attention as an explainability tool. On three text classification tasks, we verify that only a weak relationship between inputs and co-indexed intermediate representations exists—under sparse attention and otherwise. Further, we do not find any plausible mappings from sparse attention distributions to a sparse set of influential inputs through other avenues. Rather, we observe in this setting that inducing sparsity may make it less plausible that attention can be used as a tool for understanding model behavior.

Existing software-based energy measurements of NLP models are not accurate because they do not consider the complex interactions between energy consumption and model execution. We present IrEne, an interpretable and extensible energy prediction system that accurately predicts the inference energy consumption of a wide range of Transformer-based NLP models. IrEne constructs a model tree graph that breaks down the NLP model into modules that are further broken down into low-level machine learning (ML) primitives. IrEne predicts the inference energy consumption of the ML primitives as a function of generalizable features and fine-grained runtime resource usage. IrEne then aggregates these low-level predictions recursively to predict the energy of each module and finally of the entire model. Experiments across multiple Transformer models show IrEne predicts inference energy consumption of transformer models with an error of under 7% compared to the ground truth. In contrast, existing energy models see an error of over 50%. We also show how IrEne can be used to conduct energy bottleneck analysis and to easily evaluate the energy impact of different architectural choices. We release the code and data at https://github.com/StonyBrookNLP/irene.

This work investigates the use of interactively updated label suggestions to improve upon the efficiency of gathering annotations on the task of opinion mining in German Covid-19 social media data. We develop guidelines to conduct a controlled annotation study with social science students and find that suggestions from a model trained on a small, expert-annotated dataset already lead to a substantial improvement – in terms of inter-annotator agreement (+.14 Fleiss’ κ) and annotation quality – compared to students that do not receive any label suggestions. We further find that label suggestions from interactively trained models do not lead to an improvement over suggestions from a static model. Nonetheless, our analysis of suggestion bias shows that annotators remain capable of reflecting upon the suggested label in general. Finally, we confirm the quality of the annotated data in transfer learning experiments between different annotator groups. To facilitate further research in opinion mining on social media data, we release our collected data consisting of 200 expert and 2,785 student annotations.

With the recent success of pre-trained models in NLP, a significant focus was put on interpreting their representations. One of the most prominent approaches is structural probing (Hewitt and Manning, 2019), where a linear projection of word embeddings is performed in order to approximate the topology of dependency structures. In this work, we introduce a new type of structural probing, where the linear projection is decomposed into 1. iso-morphic space rotation; 2. linear scaling that identifies and scales the most relevant dimensions. In addition to syntactic dependency, we evaluate our method on two novel tasks (lexical hypernymy and position in a sentence). We jointly train the probes for multiple tasks and experimentally show that lexical and syntactic information is separated in the representations. Moreover, the orthogonal constraint makes the Structural Probes less vulnerable to memorization.

Although pretrained language models can be fine-tuned to produce state-of-the-art results for a very wide range of language understanding tasks, the dynamics of this process are not well understood, especially in the low data regime. Why can we use relatively vanilla gradient descent algorithms (e.g., without strong regularization) to tune a model with hundreds of millions of parameters on datasets with only hundreds or thousands of labeled examples? In this paper, we argue that analyzing fine-tuning through the lens of intrinsic dimension provides us with empirical and theoretical intuitions to explain this remarkable phenomenon. We empirically show that common pre-trained models have a very low intrinsic dimension; in other words, there exists a low dimension reparameterization that is as effective for fine-tuning as the full parameter space. For example, by optimizing only 200 trainable parameters randomly projected back into the full space, we can tune a RoBERTa model to achieve 90% of the full parameter performance levels on MRPC. Furthermore, we empirically show that pre-training implicitly minimizes intrinsic dimension and, perhaps surprisingly, larger models tend to have lower intrinsic dimension after a fixed number of pre-training updates, at least in part explaining their extreme effectiveness. Lastly, we connect intrinsic dimensionality with low dimensional task representations and compression based generalization bounds to provide intrinsic-dimension-based generalization bounds that are independent of the full parameter count.

Natural Language Processing (NLP) systems learn harmful societal biases that cause them to amplify inequality as they are deployed in more and more situations. To guide efforts at debiasing these systems, the NLP community relies on a variety of metrics that quantify bias in models. Some of these metrics are intrinsic, measuring bias in word embedding spaces, and some are extrinsic, measuring bias in downstream tasks that the word embeddings enable. Do these intrinsic and extrinsic metrics correlate with each other? We compare intrinsic and extrinsic metrics across hundreds of trained models covering different tasks and experimental conditions. Our results show no reliable correlation between these metrics that holds in all scenarios across tasks and languages. We urge researchers working on debiasing to focus on extrinsic measures of bias, and to make using these measures more feasible via creation of new challenge sets and annotated test data. To aid this effort, we release code, a new intrinsic metric, and an annotated test set focused on gender bias in hate speech.

Entity Matching (EM) aims at recognizing entity records that denote the same real-world object. Neural EM models learn vector representation of entity descriptions and match entities end-to-end. Though robust, these methods require many annotated resources for training, and lack of interpretability. In this paper, we propose a novel EM framework that consists of Heterogeneous Information Fusion (HIF) and Key Attribute Tree (KAT) Induction to decouple feature representation from matching decision. Using self-supervised learning and mask mechanism in pre-trained language modeling, HIF learns the embeddings of noisy attribute values by inter-attribute attention with unlabeled data. Using a set of comparison features and a limited amount of annotated data, KAT Induction learns an efficient decision tree that can be interpreted by generating entity matching rules whose structure is advocated by domain experts. Experiments on 6 public datasets and 3 industrial datasets show that our method is highly efficient and outperforms SOTA EM models in most cases. We will release the codes upon acceptance.

Geometry problem solving has attracted much attention in the NLP community recently. The task is challenging as it requires abstract problem understanding and symbolic reasoning with axiomatic knowledge. However, current datasets are either small in scale or not publicly available. Thus, we construct a new large-scale benchmark, Geometry3K, consisting of 3,002 geometry problems with dense annotation in formal language. We further propose a novel geometry solving approach with formal language and symbolic reasoning, called Interpretable Geometry Problem Solver (Inter-GPS). Inter-GPS first parses the problem text and diagram into formal language automatically via rule-based text parsing and neural object detecting, respectively. Unlike implicit learning in existing methods, Inter-GPS incorporates theorem knowledge as conditional rules and performs symbolic reasoning step by step. Also, a theorem predictor is designed to infer the theorem application sequence fed to the symbolic solver for the more efficient and reasonable searching path. Extensive experiments on the Geometry3K and GEOS datasets demonstrate that Inter-GPS achieves significant improvements over existing methods. The project with code and data is available at https://lupantech.github.io/inter-gps.

Understanding privacy policies is crucial for users as it empowers them to learn about the information that matters to them. Sentences written in a privacy policy document explain privacy practices, and the constituent text spans convey further specific information about that practice. We refer to predicting the privacy practice explained in a sentence as intent classification and identifying the text spans sharing specific information as slot filling. In this work, we propose PolicyIE, an English corpus consisting of 5,250 intent and 11,788 slot annotations spanning 31 privacy policies of websites and mobile applications. PolicyIE corpus is a challenging real-world benchmark with limited labeled examples reflecting the cost of collecting large-scale annotations from domain experts. We present two alternative neural approaches as baselines, (1) intent classification and slot filling as a joint sequence tagging and (2) modeling them as a sequence-to-sequence (Seq2Seq) learning task. The experiment results show that both approaches perform comparably in intent classification, while the Seq2Seq method outperforms the sequence tagging approach in slot filling by a large margin. We perform a detailed error analysis to reveal the challenges of the proposed corpus.