EMNLP 2020 论文列表

State of the art research for date-time entity extraction from text is task agnostic. Consequently, while the methods proposed in literature perform well for generic date-time extraction from texts, they don’t fare as well on task specific date-time entity extraction where only a subset of the date-time entities present in the text are pertinent to solving the task. Furthermore, some tasks require identifying negation constraints associated with the date-time entities to correctly reason over time. We showcase a novel model for extracting task-specific date-time entities along with their negation constraints. We show the efficacy of our method on the task of date-time understanding in the context of scheduling meetings for an email-based digital AI scheduling assistant. Our method achieves an absolute gain of 19% f-score points compared to baseline methods in detecting the date-time entities relevant to scheduling meetings and a 4% improvement over baseline methods for detecting negation constraints over date-time entities.

In recent years, there has been an increasing interest in the application of Artificial Intelligence – and especially Machine Learning – to the field of Sustainable Development (SD). However, until now, NLP has not been systematically applied in this context. In this paper, we show the high potential of NLP to enhance project sustainability. In particular, we focus on the case of community profiling in developing countries, where, in contrast to the developed world, a notable data gap exists. Here, NLP could help to address the cost and time barrier of structuring qualitative data that prohibits its widespread use and associated benefits. We propose the new extreme multi-class multi-label Automatic UserPerceived Value classification task. We release Stories2Insights, an expert-annotated dataset of interviews carried out in Uganda, we provide a detailed corpus analysis, and we implement a number of strong neural baselines to address the task. Experimental results show that the problem is challenging, and leaves considerable room for future research at the intersection of NLP and SD.

In the financial domain, risk modeling and profit generation heavily rely on the sophisticated and intricate stock movement prediction task. Stock forecasting is complex, given the stochastic dynamics and non-stationary behavior of the market. Stock movements are influenced by varied factors beyond the conventionally studied historical prices, such as social media and correlations among stocks. The rising ubiquity of online content and knowledge mandates an exploration of models that factor in such multimodal signals for accurate stock forecasting. We introduce an architecture that achieves a potent blend of chaotic temporal signals from financial data, social media, and inter-stock relationships via a graph neural network in a hierarchical temporal fashion. Through experiments on real-world S&P 500 index data and English tweets, we show the practical applicability of our model as a tool for investment decision making and trading.

wikiHow is a resource of how-to guidesthat describe the steps necessary to accomplish a goal. Guides in this resource are regularly edited by a community of users, who try to improve instructions in terms of style, clarity and correctness. In this work, we test whether the need for such edits can be predicted automatically. For this task, we extend an existing resource of textual edits with a complementary set of approx. 4 million sentences that remain unedited over time and report on the outcome of two revision modeling experiments.

Millions of people irrespective of socioeconomic and demographic backgrounds, depend on Wikipedia articles everyday for keeping themselves informed regarding popular as well as obscure topics. Articles have been categorized by editors into several quality classes, which indicate their reliability as encyclopedic content. This manual designation is an onerous task because it necessitates profound knowledge about encyclopedic language, as well navigating circuitous set of wiki guidelines. In this paper we propose Neural wikipedia Quality Monitor (NwQM), a novel deep learning model which accumulates signals from several key information sources such as article text, meta data and images to obtain improved Wikipedia article representation. We present comparison of our approach against a plethora of available solutions and show 8% improvement over state-of-the-art approaches with detailed ablation studies.

In recent years, the task of generating realistic short and long texts have made tremendous advancements. In particular, several recently proposed neural network-based language models have demonstrated their astonishing capabilities to generate texts that are challenging to distinguish from human-written texts with the naked eye. Despite many benefits and utilities of such neural methods, in some applications, being able to tell the “author” of a text in question becomes critically important. In this work, in the context of this Turing Test, we investigate the so-called authorship attribution problem in three versions: (1) given two texts T1 and T2, are both generated by the same method or not? (2) is the given text T written by a human or machine? (3) given a text T and k candidate neural methods, can we single out the method (among k alternatives) that generated T? Against one humanwritten and eight machine-generated texts (i.e., CTRL, GPT, GPT2, GROVER, XLM, XLNET, PPLM, FAIR), we empirically experiment with the performance of various models in three problems. By and large, we find that most generators still generate texts significantly different from human-written ones, thereby making three problems easier to solve. However, the qualities of texts generated by GPT2, GROVER, and FAIR are better, often confusing machine classifiers in solving three problems. All codes and datasets of our experiments are available at: https://bit.ly/ 302zWdz

Books are typically segmented into chapters and sections, representing coherent sub-narratives and topics. We investigate the task of predicting chapter boundaries, as a proxy for the general task of segmenting long texts. We build a Project Gutenberg chapter segmentation data set of 9,126 English novels, using a hybrid approach combining neural inference and rule matching to recognize chapter title headers in books, achieving an F1-score of 0.77 on this task. Using this annotated data as ground truth after removing structural cues, we present cut-based and neural methods for chapter segmentation, achieving a F1-score of 0.453 on the challenging task of exact break prediction over book-length documents. Finally, we reveal interesting historical trends in the chapter structure of novels.

The uncertainty measurement of classified results is especially important in areas requiring limited human resources for higher accuracy. For instance, data-driven algorithms diagnosing diseases need accurate uncertainty score to decide whether additional but limited quantity of experts are needed for rectification. However, few uncertainty models focus on improving the performance of text classification where human resources are involved. To achieve this, we aim at generating accurate uncertainty score by improving the confidence of winning scores. Thus, a model called MSD, which includes three independent components as “mix-up”, “self-ensembling”, “distinctiveness score”, is proposed to improve the accuracy of uncertainty score by reducing the effect of overconfidence of winning score and considering the impact of different categories of uncertainty simultaneously. MSD can be applied with different Deep Neural Networks. Extensive experiments with ablation setting are conducted on four real-world datasets, on which, competitive results are obtained.

Recent advances in weakly supervised learning enable training high-quality text classifiers by only providing a few user-provided seed words. Existing methods mainly use text data alone to generate pseudo-labels despite the fact that metadata information (e.g., author and timestamp) is widely available across various domains. Strong label indicators exist in the metadata and it has been long overlooked mainly due to the following challenges: (1) metadata is multi-typed, requiring systematic modeling of different types and their combinations, (2) metadata is noisy, some metadata entities (e.g., authors, venues) are more compelling label indicators than others. In this paper, we propose a novel framework, META, which goes beyond the existing paradigm and leverages metadata as an additional source of weak supervision. Specifically, we organize the text data and metadata together into a text-rich network and adopt network motifs to capture appropriate combinations of metadata. Based on seed words, we rank and filter motif instances to distill highly label-indicative ones as “seed motifs”, which provide additional weak supervision. Following a bootstrapping manner, we train the classifier and expand the seed words and seed motifs iteratively. Extensive experiments and case studies on real-world datasets demonstrate superior performance and significant advantages of leveraging metadata as weak supervision.

We present CoDEx, a set of knowledge graph completion datasets extracted from Wikidata and Wikipedia that improve upon existing knowledge graph completion benchmarks in scope and level of difficulty. In terms of scope, CoDEx comprises three knowledge graphs varying in size and structure, multilingual descriptions of entities and relations, and tens of thousands of hard negative triples that are plausible but verified to be false. To characterize CoDEx, we contribute thorough empirical analyses and benchmarking experiments. First, we analyze each CoDEx dataset in terms of logical relation patterns. Next, we report baseline link prediction and triple classification results on CoDEx for five extensively tuned embedding models. Finally, we differentiate CoDEx from the popular FB15K-237 knowledge graph completion dataset by showing that CoDEx covers more diverse and interpretable content, and is a more difficult link prediction benchmark. Data, code, and pretrained models are available at https://bit.ly/2EPbrJs.

Text classification is a fundamental problem in natural language processing. Recent studies applied graph neural network (GNN) techniques to capture global word co-occurrence in a corpus. However, previous works are not scalable to large-sized corpus and ignore the heterogeneity of the text graph. To address these problems, we introduce a novel Transformer based heterogeneous graph neural network, namely Text Graph Transformer (TG-Transformer). Our model learns effective node representations by capturing structure and heterogeneity from the text graph. We propose a mini-batch text graph sampling method that significantly reduces computing and memory costs to handle large-sized corpus. Extensive experiments have been conducted on several benchmark datasets, and the results demonstrate that TG-Transformer outperforms state-of-the-art approaches on text classification task.

Little is known about the trustworthiness of predictions made by knowledge graph embedding (KGE) models. In this paper we take initial steps toward this direction by investigating the calibration of KGE models, or the extent to which they output confidence scores that reflect the expected correctness of predicted knowledge graph triples. We first conduct an evaluation under the standard closed-world assumption (CWA), in which predicted triples not already in the knowledge graph are considered false, and show that existing calibration techniques are effective for KGE under this common but narrow assumption. Next, we introduce the more realistic but challenging open-world assumption (OWA), in which unobserved predictions are not considered true or false until ground-truth labels are obtained. Here, we show that existing calibration techniques are much less effective under the OWA than the CWA, and provide explanations for this discrepancy. Finally, to motivate the utility of calibration for KGE from a practitioner’s perspective, we conduct a unique case study of human-AI collaboration, showing that calibrated predictions can improve human performance in a knowledge graph completion task.

Entity set expansion and synonym discovery are two critical NLP tasks. Previous studies accomplish them separately, without exploring their interdependencies. In this work, we hypothesize that these two tasks are tightly coupled because two synonymous entities tend to have a similar likelihood of belonging to various semantic classes. This motivates us to design SynSetExpan, a novel framework that enables two tasks to mutually enhance each other. SynSetExpan uses a synonym discovery model to include popular entities’ infrequent synonyms into the set, which boosts the set expansion recall. Meanwhile, the set expansion model, being able to determine whether an entity belongs to a semantic class, can generate pseudo training data to fine-tune the synonym discovery model towards better accuracy. To facilitate the research on studying the interplays of these two tasks, we create the first large-scale Synonym-Enhanced Set Expansion (SE2) dataset via crowdsourcing. Extensive experiments on the SE2 dataset and previous benchmarks demonstrate the effectiveness of SynSetExpan for both entity set expansion and synonym discovery tasks.

Natural Language Inference (NLI) datasets contain annotation artefacts resulting in spurious correlations between the natural language utterances and their respective entailment classes. These artefacts are exploited by neural networks even when only considering the hypothesis and ignoring the premise, leading to unwanted biases. Belinkov et al. (2019b) proposed tackling this problem via adversarial training, but this can lead to learned sentence representations that still suffer from the same biases. We show that the bias can be reduced in the sentence representations by using an ensemble of adversaries, encouraging the model to jointly decrease the accuracy of these different adversaries while fitting the data. This approach produces more robust NLI models, outperforming previous de-biasing efforts when generalised to 12 other NLI datasets (Belinkov et al., 2019a; Mahabadi et al., 2020). In addition, we find that the optimal number of adversarial classifiers depends on the dimensionality of the sentence representations, with larger sentence representations being more difficult to de-bias while benefiting from using a greater number of adversaries.

Performance on the Winograd Schema Challenge (WSC), a respected English commonsense reasoning benchmark, recently rocketed from chance accuracy to 89% on the SuperGLUE leaderboard, with relatively little corroborating evidence of a correspondingly large improvement in reasoning ability. We hypothesize that much of this improvement comes from recent changes in task formalization—the combination of input specification, loss function, and reuse of pretrained parameters—by users of the dataset, rather than improvements in the pretrained model’s reasoning ability. We perform an ablation on two Winograd Schema datasets that interpolates between the formalizations used before and after this surge, and find (i) framing the task as multiple choice improves performance dramatically and (ii)several additional techniques, including the reuse of a pretrained language modeling head, can mitigate the model’s extreme sensitivity to hyperparameters. We urge future benchmark creators to impose additional structure to minimize the impact of formalization decisions on reported results.

We describe a method for developing broad-coverage semantic dependency parsers for languages for which no semantically annotated resource is available. We leverage a multitask learning framework coupled with annotation projection. We use syntactic parsing as the auxiliary task in our multitask setup. Our annotation projection experiments from English to Czech show that our multitask setup yields 3.1% (4.2%) improvement in labeled F1-score on in-domain (out-of-domain) test set compared to a single-task baseline.

Large annotated datasets in NLP are overwhelmingly in English. This is an obstacle to progress in other languages. Unfortunately, obtaining new annotated resources for each task in each language would be prohibitively expensive. At the same time, commercial machine translation systems are now robust. Can we leverage these systems to translate English-language datasets automatically? In this paper, we offer a positive response for natural language inference (NLI) in Turkish. We translated two large English NLI datasets into Turkish and had a team of experts validate their translation quality and fidelity to the original labels. Using these datasets, we address core issues of representation for Turkish NLI. We find that in-language embeddings are essential and that morphological parsing can be avoided where the training set is large. Finally, we show that models trained on our machine-translated datasets are successful on human-translated evaluation sets. We share all code, models, and data publicly.

Reasoning about conjuncts in conjunctive sentences is important for a deeper understanding of conjunctions in English and also how their usages and semantics differ from conjunctive and disjunctive boolean logic. Existing NLI stress tests do not consider non-boolean usages of conjunctions and use templates for testing such model knowledge. Hence, we introduce ConjNLI, a challenge stress-test for natural language inference over conjunctive sentences, where the premise differs from the hypothesis by conjuncts removed, added, or replaced. These sentences contain single and multiple instances of coordinating conjunctions (“and”, “or”, “but”, “nor”) with quantifiers, negations, and requiring diverse boolean and non-boolean inferences over conjuncts. We find that large-scale pre-trained language models like RoBERTa do not understand conjunctive semantics well and resort to shallow heuristics to make inferences over such sentences. As some initial solutions, we first present an iterative adversarial fine-tuning method that uses synthetically created training data based on boolean and non-boolean heuristics. We also propose a direct model advancement by making RoBERTa aware of predicate semantic roles. While we observe some performance gains, ConjNLI is still challenging for current methods, thus encouraging interesting future work for better understanding of conjunctions.

A standard way to address different NLP problems is by first constructing a problem-specific dataset, then building a model to fit this dataset. To build the ultimate artificial intelligence, we desire a single machine that can handle diverse new problems, for which task-specific annotations are limited. We bring up textual entailment as a unified solver for such NLP problems. However, current research of textual entailment has not spilled much ink on the following questions: (i) How well does a pretrained textual entailment system generalize across domains with only a handful of domain-specific examples? and (ii) When is it worth transforming an NLP task into textual entailment? We argue that the transforming is unnecessary if we can obtain rich annotations for this task. Textual entailment really matters particularly when the target NLP task has insufficient annotations. Universal NLP can be probably achieved through different routines. In this work, we introduce Universal Few-shot textual Entailment (UFO-Entail). We demonstrate that this framework enables a pretrained entailment model to work well on new entailment domains in a few-shot setting, and show its effectiveness as a unified solver for several downstream NLP tasks such as question answering and coreference resolution when the end-task annotations are limited.