Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are missing some of this information. In this paper, we study the problem of annotating table columns (i.e., predicting column types and the relationships between columns) using only information from the table itself. We develop a multi-task learning framework (called Doduo) based on pre-trained language models, which takes the entire table as input and predicts column types/relations using a single model. Experimental results show that Doduo establishes new state-of-the-art performance on two benchmarks for the column type prediction and column relation prediction tasks with up to 4.0% and 11.9% improvements, respectively. We report that Doduo can already outperform the previous state-of-the-art performance with a minimal number of tokens, only 8 tokens per column. We release a toolbox (https://github.com/megagonlabs/doduo) and confirm the effectiveness of Doduo on a real-world data science problem through a case study.

The Web is a major resource of both factual and subjective information. While there are significant efforts to organize factual information into knowledge bases, there is much less work on organizing opinions, which are abundant in subjective data, into a structured format.

Abstract We present the Quantized Transformer (QT), an unsupervised system for extractive opinion summarization. QT is inspired by Vector- Quantized Variational Autoencoders, which we repurpose for popularity-driven summarization. It uses a clustering interpretation of the quantized space and a novel extraction algorithm to discover popular opinions among hundreds of reviews, a significant step towards opinion summarization of practical scope. In addition, QT enables controllable summarization without further training, by utilizing properties of the quantized space to extract aspect-specific summaries. We also make publicly available Space, a large-scale evaluation benchmark for opinion summarizers, comprising general and aspect-specific summaries for 50 hotels. Experiments demonstrate the promise of our approach, which is validated by human studies where judges showed clear preference for our method over competitive baselines.

We present Emu, a system that semantically enhances multilingual sentence embeddings. Our framework fine-tunes pre-trained multilingual sentence embeddings using two main components: a semantic classifier and a language discriminator. The semantic classifier improves the semantic similarity of related sentences, whereas the language discriminator enhances the multilinguality of the embeddings via multilingual adversarial training. Our experimental results based on several language pairs show that our specialized embeddings outperform the state-of-the-art multilingual sentence embedding model on the task of cross-lingual intent classification using only monolingual labeled data.

We present OPINIONDIGEST, an abstractive opinion summarization framework, which does not rely on gold-standard summaries for training.The framework uses an Aspect-based Sentiment Analysis model to extract opinion phrases from reviews, and trains a Transformer model to reconstruct the original reviews from these extractions.At summarization time, we merge extractions from multiple reviews and select the most popular ones.The selected opinions are used as input to the trained Transformer model, which verbalizes them into an opinion summary.OPINIONDIGEST can also generate customized summaries, tailored to specific user needs, by filtering the selected opinions according to their aspect and/or sentiment.Automatic evaluation on YELP data shows that our framework outperforms competitive baselines.Human studies on two corpora verify that OPINIONDIGEST produces informative summaries and shows promising customization capabilities 1 .

We present Ditto, a novel entity matching system based on pre-trained Transformer-based language models. We fine-tune and cast EM as a sequence-pair classification problem to leverage such models with a simple architecture. Our experiments show that a straight-forward application of language models such as BERT, DistilBERT, or RoBERTa pre-trained on large text corpora already significantly improves the matching quality and outperforms previous state-of-the-art (SOTA), by up to 29% of F1 score on benchmark datasets. We also developed three optimization techniques to further improve Ditto's matching capability. Ditto allows domain knowledge to be injected by highlighting important pieces of input information that may be of interest when making matching decisions. Ditto also summarizes strings that are too long so that only the essential information is retained and used for EM. Finally, Ditto adapts a SOTA technique on data augmentation for text to EM to augment the training data with (difficult) examples. This way, Ditto is forced to learn "harder" to improve the model's matching capability. The optimizations we developed further boost the performance of Ditto by up to 9.8%. Perhaps more surprisingly, we establish that Ditto can achieve the previous SOTA results with at most half the number of labeled data. Finally, we demonstrate Ditto's effectiveness on a real-world large-scale EM task. On matching two company datasets consisting of 789K and 412K records, Ditto achieves a high F1 score of 96.5%.

Understanding what makes people happy is a central topic in psychology. Prior work has mostly focused on developing self-reporting assessment tools for individuals and relies on experts to analyze the periodic reported assessments. One of the goals of the analysis is to understand what actions are necessary to encourage modifications in the behaviors of the individuals to improve their overall well-being. In this paper, we outline a complementary approach; on the assumption that the user journals her happy moments as short texts, a system can analyze these texts and propose sustainable suggestions for the user that may lead to an overall improvement in her well-being. We prototype one necessary component of such a system, the Happiness Entailment Recognition (HER)module, which takes as input a short text describing an event, a candidate suggestion, and outputs a determination about whether the suggestion is more likely to be good for this user based on the event described. This component is implemented as a neural network model with two encoders, one for the user input and one for the candidate actionable suggestion, with additional layers to capture psychologically significant features in the happy moment and suggestion. Our model achieves an AU-ROC of 0.831 and outperforms our baseline as well as the current state-of-the-art Textual Entailment model from AllenNLP by more than 48% of improvements, confirming the uniqueness and complexity of the HER task.

Participants in cryptocurrency markets are in constant communication with each other about the latest coins and news releases. Do these conversations build hype through the contagiousness of excitement, help the community process information, or play some other role? Using a novel dataset from a major cryptocurrency forum, we conduct an exploratory study of the characteristics of online discussion around cryptocurrencies. Through a regression analysis, we find that coins with more information available and higher levels of technical innovation are associated with higher quality discussion. People who talk about "serious" coins tend to participate in discussion displaying signatures of collective intelligence and information processing, while people who talk about "less serious" coins tend to display signatures of hype and naïvety. Interviews with experienced forum members also confirm these quantitative findings. These results highlight the varied roles of discussion in the cryptocurrency ecosystem and suggest that discussion of serious coins may be oriented towards earnest, perhaps more accurate, attempts at discovering which coins are likely to succeed.

K oko is a declarative information extraction system that incorporates advances in natural language processing techniques in its extraction language. K oko 's extraction language supports simultaneous specification of conditions over the surface syntax and on the structure of the dependency parse tree of sentences, thereby allowing for more refined extractions. Furthermore, the K oko extraction language allows for aggregating evidence from an input document and supports conditions that are tolerant of linguistic variation of expressing concepts. In this demo, we outline the design of K oko , a system for extracting information and understanding the results of the extraction. K oko provides an interactive interface that allows participants to write queries, understand the input and results of the queries. In particular, the user can customize the input text, visualize the input text's dependency parse trees, and understand the correspondences between query components, dependency tree nodes, text tokens, and the computation and associated scores that led to an extraction.

The understanding and modeling of human purchase behavior in city environment can have important implications in the study of urban economy and in the design and organization of cities. In this article, we study human purchase behavior at the community level and argue that people who live in different communities but work at close-by locations could act as “social bridges” between the respective communities and that they are correlated with similarity in community purchase behavior. We provide empirical evidence by studying millions of credit card transaction records for tens of thousands of individuals in a city environment during a period of three months. More specifically, we show that the number of social bridges between communities is a much stronger indicator of similarity in their purchase behavior than traditionally considered factors such as income and sociodemographic variables. Our findings also suggest that such an effect varies across different merchant categories, that the presence of female customers in social bridges is a stronger indicator compared to that of their male counterparts, and that there seems to be a geographical constraint for this effect, all of which may have implications in the studies of urban economy and data-driven urban planning.

Driver behavior affects traffic safety, fuel/energy consumption and gas emissions. The purpose of driver behavior profiling is to understand and have a positive influence on driver behavior. Driver behavior profiling tasks usually involve an automated collection of driving data and the application of computer models to classify what characterizes the aggressiveness of drivers. Different sensors and classification methods have been employed for this task, although low-cost solutions, high performance and collaborative sensing remain open questions for research. This paper makes an investigation with different Recurrent Neural Networks (RNN), aiming to classify driving events employing data collected by smartphone accelerometers. The results show that specific configurations of RNN upon accelerometer data provide high accuracy results, being a step towards the development of safer transportation systems.

Depression is a prevailing issue and is an increasing problem in many people's lives. Without observable diagnostic criteria, the signs of depression may go unnoticed, resulting in high demand for detecting depression in advance automatically. This paper tackles the challenging problem of forecasting severely depressed moods based on self-reported histories. Despite the large amount of research on understanding individual moods including depression, anxiety, and stress based on behavioral logs collected by pervasive computing devices such as smartphones, forecasting depressed moods is still an open question. This paper develops a recurrent neural network algorithm that incorporates categorical embedding layers for forecasting depression. We collected large-scale records from 2,382 self-declared depressed people to conduct the experiment. Experimental results show that our method forecast the severely depressed mood of a user based on self-reported histories, with higher accuracy than SVM. The results also showed that the long-term historical information of a user improves the accuracy of forecasting depressed mood.

Automatic check-in, which is to identify a user's visited points of interest (POIs) from his or her trajectories, is still an open problem because of positioning errors and the high POI density in small areas. In this study, we propose a probabilistic visited-POI identification method. The method uses a new hierarchical Bayesian model for identifying the latent visited-POI label of stay points, which are automatically extracted from trajectories. This model learns from labeled and unlabeled stay point data (i.e., semi-supervised learning) and takes into account personal preferences, stay locations including positioning errors, stay times for each category, and prior knowledge about typical user preferences and stay times. Experimental results with real user trajectories and POIs of Foursquare demonstrated that our method achieved statistically significant improvements in precision at 1 and recall at 3 over the nearest neighbor method and a conventional method that uses a supervised learning-to-rank algorithm.