We present the TAPAS contribution to the Shared Task on Statement
Verification and Evidence Finding with Tables (SemEval 2021 Task 9, Wang et al.
(2021)). SEM TAB FACT Task A is a classification task of recognizing if a
statement is entailed, neutral or refuted by the content of a given table. We
adopt the binary TAPAS model of Eisenschlos et al. (2020) to this task. We
learn two binary classification models: A first model to predict if a statement
is neutral or non-neutral and a second one to predict if it is entailed or
refuted. As the shared task training set contains only entailed or refuted
examples, we generate artificial neutral examples to train the first model.
Both models are pre-trained using a MASKLM objective, intermediate
counter-factual and synthetic data (Eisenschlos et al., 2020) and TABFACT (Chen
et al., 2020), a large table entailment dataset. We find that the artificial
neutral examples are somewhat effective at training the first model, achieving
68.03 test F1 versus the 60.47 of a majority baseline. For the second stage, we
find that the pre-training on the intermediate data and TABFACT improves the
results over MASKLM pre-training (68.03 vs 57.01).

本文介绍了 TAPAS 在语句验证和证据查找领域的贡献，该任务需要识别给定表的内容是否支持、中立或反驳一个陈述，使用 Eisenschlos 等人的二进制 TAPAS 模型。

SemEval-2021 任务 9 中的 TAPAS: 使用中间预训练对表格进行推理

TAPAS at SemEval-2021 Task 9: Reasoning over tables with intermediate  pre-training

We present a simple methods to leverage the table content for the BERT-based
model to solve the text-to-SQL problem. Based on the observation that some of
the table content match some words in question string and some of the table
header also match some words in question string, we encode two addition feature
vector for the deep model. Our methods also benefit the model inference in
testing time as the tables are almost the same in training and testing time. We
test our model on the WikiSQL dataset and outperform the BERT-based baseline by
3.7% in logic form and 3.7% in execution accuracy and achieve state-of-the-art.

本文提出了一种简单的方法，利用表格内容为基于 BERT 的模型解决文本到 SQL 的问题。通过观察表格内容与问题中的一些单词匹配以及表格标题也与问题中的一些单词匹配，我们为深度模型编码了两个额外的特征向量。我们在 WikiSQL 数据集上进行了测试，并在逻辑形式和执行准确性方面比 BERT 基线提高了 3.7％，成为业内领先者。