Several applications, such as text-to-SQL and computational fact checking, exploit the relationship between relational data and natural language text. However, state of the art solutions simply fail in managing "data-ambiguity", i.e., the case when there are multiple interpretations of the relationship between text and data. Given the ambiguity in language, text can be mapped to different subsets of data, but existing training corpora only have examples in which every sentence/question is annotated precisely w.r.t. the relation. This unrealistic assumption leaves the target applications unable to handle ambiguous cases. To tackle this problem, we present an end-to-end solution that, given a table D, generates examples that consist of text, annotated with its data evidence, with factual ambiguities w.r.t. D. We formulate the problem of profiling relational tables to identify row and attribute data ambiguity. For the latter, we propose a deep learning method that identifies every pair of data ambiguous attributes and a label that describes both columns. Such metadata is then used to generate examples with data ambiguities for any input table. To enable scalability, we finally introduce a SQL approach that can generate millions of examples in seconds. We show the high accuracy of our solution in profiling relational tables and report on how our automatically generated examples lead to drastic quality improvements in two fact-checking applications, including a website with thousands of users, and in a text-to-SQL system.

Abstract In the last few years, the natural language processing community has witnessed advances in neural representations of free texts with transformer-based language models (LMs). Given the importance of knowledge available in tabular data, recent research efforts extend LMs by developing neural representations for structured data. In this article, we present a survey that analyzes these efforts. We first abstract the different systems according to a traditional machine learning pipeline in terms of training data, input representation, model training, and supported downstream tasks. For each aspect, we characterize and compare the proposed solutions. Finally, we discuss future work directions.

Fact-checking is one of the effective solutions in fighting online misinformation. However, traditional fact-checking is a process requiring scarce expert human resources, and thus does not scale well on social media because of the continuous flow of new content to be checked. Methods based on crowdsourcing have been proposed to tackle this challenge, as they can scale with a smaller cost, but, while they have shown to be feasible, have always been studied in controlled environments. In this work, we study the first large-scale effort of crowdsourced fact-checking deployed in practice, started by Twitter with the Birdwatch program. Our analysis shows that crowdsourcing may be an effective fact-checking strategy in some settings, even comparable to results obtained by human experts, but does not lead to consistent, actionable results in others. We processed 11.9k tweets verified by the Birdwatch program and report empirical evidence of i) differences in how the crowd and experts select content to be fact-checked, ii) how the crowd and the experts retrieve different resources to fact-check, and iii) the edge the crowd shows in fact-checking scalability and efficiency as compared to expert checkers.

Applications such as computational fact checking and data-to-text generation exploit the relationship between relational data and natural language text. Despite promising results in these areas, state of the art solutions simply fail in managing "data-ambiguity", i.e., the case when there are multiple interpretations of the relationship between the textual sentence and the relational data. To tackle this problem, we introduce Pythia, a system that, given a relational table D, generates textual sentences that contain factual ambiguities w.r.t. the data in D. Such sentences can then be used to train target applications in handling data-ambiguity. In this demonstration, we first show how our system generates data ambiguous sentences for a given table in an unsupervised fashion by data profiling and query generation. We then demonstrate how two existing applications benefit from Pythia's generated sentences, improving the state-of-the-art results. The audience will interact with Pythia by changing input parameters in an interactive fashion, including the upload of their own dataset to see what data ambiguous sentences are generated for it.

While pre-trained language models (PLMs) are the go-to solution to tackle many natural language processing problems, they are still very limited in their ability to capture and to use common-sense knowledge.In fact, even if information is available in the form of approximate (soft) logical rules, it is not clear how to transfer it to a PLM in order to improve its performance for deductive reasoning tasks.Here, we aim to bridge this gap by teaching PLMs how to reason with soft Horn rules.We introduce a classification task where, given facts and soft rules, the PLM should return a prediction with a probability for a given hypothesis.We release the first dataset for this task, and we propose a revised loss function that enables the PLM to learn how to predict precise probabilities for the task.Our evaluation results show that the resulting fine-tuned models achieve very high performance, even on logical rules that were unseen at training.Moreover, we demonstrate that logical notions expressed by the rules are transferred to the finetuned model, yielding state-of-the-art results on external datasets.

We present a generic method to compute the factual accuracy of a generated data summary with minimal user effort.We look at the problem as a fact-checking task to verify the numerical claims in the text.The verification algorithm assumes that the data used to generate the text is available.In this paper, we describe how the proposed solution has been used to identify incorrect claims about basketball textual summaries in the context of the Accuracy Shared Task at INLG 2021.

We demonstrate Scrutinizer, a system that supports human fact checkers in translating text claims into SQL queries on an associated database. Scrutinizer coordinates teams of human fact checkers and reduces their verification time by proposing queries or query fragments over relevant data. Those proposals are based on claim text classifiers, that gradually improve during the verification of multiple claims. In addition, Scrutinizer uses tentative execution of query candidates to narrow down the set of alternatives. The verification process is controlled by a cost-based optimizer that plans effective question sequences to verify specific claims, and prioritizes claims for verification. In this demonstration, we first show how our system can assist users in verifying statistical claims. We then let users come up with new, unseen claims and show how the system effectively learns new queries with little user feedback.