Event detection has long been troubled by the trigger curse: overfitting the trigger will harm the generalization ability while underfitting it will hurt the detection performance. This problem is even more severe in few-shot scenario. In this paper,
we identify and solve the trigger curse problem in few-shot event detection (FSED) from a causal view. By formulating FSED with a structural causal model (SCM), we found that the trigger is a confounder of the context and the result, which makes previous FSED methods much easier to overfit triggers. To resolve this problem, we propose to intervene on the context via backdoor adjustment during training. Experiments show that our method significantly improves the FSED on both ACE05 and MAVEN datasets.
Reading order detection is the cornerstone to understanding visually-rich documents (e.g., receipts and forms). Unfortunately, no existing work took advantage of advanced deep learning models because it is too laborious to annotate a large enough dat
aset. We observe that the reading order of WORD documents is embedded in their XML metadata; meanwhile, it is easy to convert WORD documents to PDFs or images. Therefore, in an automated manner, we construct ReadingBank, a benchmark dataset that contains reading order, text, and layout information for 500,000 document images covering a wide spectrum of document types. This first-ever large-scale dataset unleashes the power of deep neural networks for reading order detection. Specifically, our proposed LayoutReader captures the text and layout information for reading order prediction using the seq2seq model. It performs almost perfectly in reading order detection and significantly improves both open-source and commercial OCR engines in ordering text lines in their results in our experiments. The dataset and models are publicly available at https://aka.ms/layoutreader.
Social media is an essential tool to share information about crisis events, such as natural disasters. Event Detection aims at extracting information in the form of an event, but considers each event in isolation, without combining information across
sentences or events. Many posts in Crisis NLP contain repetitive or complementary information which needs to be aggregated (e.g., the number of trapped people and their location) for disaster response. Although previous approaches in Crisis NLP aggregate information across posts, they only use shallow representations of the content (e.g., keywords), which cannot adequately represent the semantics of a crisis event and its sub-events. In this work, we propose a novel framework to extract critical sub-events from a large-scale crisis event by combining important information across relevant tweets. Our framework first converts all the tweets from a crisis event into a temporally-ordered set of graphs. Then it extracts sub-graphs that represent semantic relationships connecting verbs and nouns in 3 to 6 node sub-graphs. It does this by learning edge weights via Dynamic Graph Convolutional Networks (DGCNs) and extracting smaller, relevant sub-graphs. Our experiments show that our extracted structures (1) are semantically meaningful sub-events and (2) contain information important for the large crisis-event. Furthermore, we show that our approach significantly outperforms event detection baselines, highlighting the importance of aggregating information across tweets for our task.
Slow emerging topic detection is a task between event detection, where we aggregate behaviors of different words on short period of time, and language evolution, where we monitor their long term evolution. In this work, we tackle the problem of early
detection of slowly emerging new topics. To this end, we gather evidence of weak signals at the word level. We propose to monitor the behavior of words representation in an embedding space and use one of its geometrical properties to characterize the emergence of topics. As evaluation is typically hard for this kind of task, we present a framework for quantitative evaluation and show positive results that outperform state-of-the-art methods. Our method is evaluated on two public datasets of press and scientific articles.
Large-Scale Multi-Label Text Classification (LMTC) includes tasks with hierarchical label spaces, such as automatic assignment of ICD-9 codes to discharge summaries. Performance of models in prior art is evaluated with standard precision, recall, and
F1 measures without regard for the rich hierarchical structure. In this work we argue for hierarchical evaluation of the predictions of neural LMTC models. With the example of the ICD-9 ontology we describe a structural issue in the representation of the structured label space in prior art, and propose an alternative representation based on the depth of the ontology. We propose a set of metrics for hierarchical evaluation using the depth-based representation. We compare the evaluation scores from the proposed metrics with previously used metrics on prior art LMTC models for ICD-9 coding in MIMIC-III. We also propose further avenues of research involving the proposed ontological representation.
Existing text-based personality detection research mostly relies on data-driven approaches to implicitly capture personality cues in online posts, lacking the guidance of psychological knowledge. Psychological questionnaire, which contains a series o
f dedicated questions highly related to personality traits, plays a critical role in self-report personality assessment. We argue that the posts created by a user contain critical contents that could help answer the questions in a questionnaire, resulting in an assessment of his personality by linking the texts and the questionnaire. To this end, we propose a new model named Psychological Questionnaire enhanced Network (PQ-Net) to guide personality detection by tracking critical information in texts with a questionnaire. Specifically, PQ-Net contains two streams: a context stream to encode each piece of text into a contextual text representation, and a questionnaire stream to capture relevant information in the contextual text representation to generate potential answer representations for a questionnaire. The potential answer representations are used to enhance the contextual text representation and to benefit personality prediction. Experimental results on two datasets demonstrate the superiority of PQ-Net in capturing useful cues from the posts for personality detection.
This paper proposes to study a fine-grained semantic novelty detection task, which can be illustrated with the following example. It is normal that a person walks a dog in the park, but if someone says A man is walking a chicken in the park'', it is
novel. Given a set of natural language descriptions of normal scenes, we want to identify descriptions of novel scenes. We are not aware of any existing work that solves the problem. Although existing novelty or anomaly detection algorithms are applicable, since they are usually topic-based, they perform poorly on our fine-grained semantic novelty detection task. This paper proposes an effective model (called GAT-MA) to solve the problem and also contributes a new dataset. Experimental evaluation shows that GAT-MA outperforms 11 baselines by large margins.
Stance detection (SD) entails classifying the sentiment of a text towards a given target, and is a relevant sub-task for opinion mining and social media analysis. Recent works have explored knowledge infusion supplementing the linguistic competence a
nd latent knowledge of large pre-trained language models with structured knowledge graphs (KGs), yet few works have applied such methods to the SD task. In this work, we first perform stance-relevant knowledge probing on Transformers-based pre-trained models in a zero-shot setting, showing these models' latent real-world knowledge about SD targets and their sensitivity to context. We then train and evaluate new knowledge-enriched stance detection models on two Twitter stance datasets, achieving state-of-the-art performance on both.
Stance detection determines whether the author of a text is in favor of, against or neutral to a specific target and provides valuable insights into important events such as legalization of abortion. Despite significant progress on this task, one of
the remaining challenges is the scarcity of annotations. Besides, most previous works focused on a hard-label training in which meaningful similarities among categories are discarded during training. To address these challenges, first, we evaluate a multi-target and a multi-dataset training settings by training one model on each dataset and datasets of different domains, respectively. We show that models can learn more universal representations with respect to targets in these settings. Second, we investigate the knowledge distillation in stance detection and observe that transferring knowledge from a teacher model to a student model can be beneficial in our proposed training settings. Moreover, we propose an Adaptive Knowledge Distillation (AKD) method that applies instance-specific temperature scaling to the teacher and student predictions. Results show that the multi-dataset model performs best on all datasets and it can be further improved by the proposed AKD, outperforming the state-of-the-art by a large margin. We publicly release our code.
As NLP systems become better at detecting opinions and beliefs from text, it is important to ensure not only that models are accurate but also that they arrive at their predictions in ways that align with human reasoning. In this work, we present a m
ethod for imparting human-like rationalization to a stance detection model using crowdsourced annotations on a small fraction of the training data. We show that in a data-scarce setting, our approach can improve the reasoning of a state-of-the-art classifier---particularly for inputs containing challenging phenomena such as sarcasm---at no cost in predictive performance. Furthermore, we demonstrate that attention weights surpass a leading attribution method in providing faithful explanations of our model's predictions, thus serving as a computationally cheap and reliable source of attributions for our model.
