Solving symbolic reasoning problems that require compositionality and
systematicity is considered one of the key ingredients of human intelligence.
However, symbolic reasoning is still a great challenge for deep learning
models, which often cannot generalize the reasoning pattern to
out-of-distribution test cases. In this work, we propose a hybrid system
capable of solving arithmetic problems that require compositional and
systematic reasoning over sequences of symbols. The model acquires such a skill
by learning appropriate substitution rules, which are applied iteratively to
the input string until the expression is completely resolved. We show that the
proposed system can accurately solve nested arithmetical expressions even when
trained only on a subset including the simplest cases, significantly
outperforming both a sequence-to-sequence model trained end-to-end and a
state-of-the-art large language model.

提出了一种混合系统，通过学习适当的替换规则并迭代应用这些规则到输入字符串，能够解决需要在符号序列上进行组合和系统推理的算术问题。

简单算术问题系统化泛化的混合系统

A Hybrid System for Systematic Generalization in Simple Arithmetic  Problems

Over a five-year period, computing methods for generating high-fidelity,
fictional depictions of people and events moved from exotic demonstrations by
computer science research teams into ongoing use as a tool of disinformation.
The methods, referred to with the portmanteau of "deepfakes," have been used to
create compelling audiovisual content. Here, I share challenges ahead with
malevolent uses of two classes of deepfakes that we can expect to come into
practice with costly implications for society: interactive and compositional
deepfakes. Interactive deepfakes have the capability to impersonate people with
realistic interactive behaviors, taking advantage of advances in multimodal
interaction. Compositional deepfakes leverage synthetic content in larger
disinformation plans that integrate sets of deepfakes over time with observed,
expected, and engineered world events to create persuasive synthetic histories.
Synthetic histories can be constructed manually but may one day be guided by
adversarial generative explanation (AGE) techniques. In the absence of
mitigations, interactive and compositional deepfakes threaten to move us closer
to a post-epistemic world, where fact cannot be distinguished from fiction. I
shall describe interactive and compositional deepfakes and reflect about
cautions and potential mitigations to defend against them.

该研究讨论了两种类型的 Deepfakes—— 互动式 Deepfakes 和组合式 Deepfakes，这两种 Deepfakes 的恶意使用将会对社会产生昂贵的影响，并探讨了可能的缓解措施。

交互式和组合式 Deepfake 的展望

On the Horizon: Interactive and Compositional Deepfakes

Existing studies on question answering on knowledge bases (KBQA) mainly
operate with the standard i.i.d assumption, i.e., training distribution over
questions is the same as the test distribution. However, i.i.d may be neither
reasonably achievable nor desirable on large-scale KBs because 1) true user
distribution is hard to capture and 2) randomly sample training examples from
the enormous space would be highly data-inefficient. Instead, we suggest that
KBQA models should have three levels of built-in generalization: i.i.d,
compositional, and zero-shot. To facilitate the development of KBQA models with
stronger generalization, we construct and release a new large-scale,
high-quality dataset with 64,331 questions, GrailQA, and provide evaluation
settings for all three levels of generalization. In addition, we propose a
novel BERT-based KBQA model. The combination of our dataset and model enables
us to thoroughly examine and demonstrate, for the first time, the key role of
pre-trained contextual embeddings like BERT in the generalization of KBQA.

本文研究在知识库问答（KBQA）中，为了增强模型的泛化能力，建议模型应具有三个内置泛化层面：i.i.d、组合和零样本，并提出一种新颖的基于 BERT 的 KBQA 模型，此外构建和发布一个高质量的数据集 GrailQA，为三个泛化层面提供评估设置。实验证明，预训练的上下文嵌入（如 BERT）在 KBQA 的泛化中起着重要的作用。

超越 I.I.D.: 基于知识库的问答的三个泛化层次

Beyond I.I.D.: Three Levels of Generalization for Question Answering on  Knowledge Bases

Recent years have witnessed an increasing interest in image-based
question-answering (QA) tasks. However, due to data limitations, there has been
much less work on video-based QA. In this paper, we present TVQA, a large-scale
video QA dataset based on 6 popular TV shows. TVQA consists of 152,545 QA pairs
from 21,793 clips, spanning over 460 hours of video. Questions are designed to
be compositional in nature, requiring systems to jointly localize relevant
moments within a clip, comprehend subtitle-based dialogue, and recognize
relevant visual concepts. We provide analyses of this new dataset as well as
several baselines and a multi-stream end-to-end trainable neural network
framework for the TVQA task. The dataset is publicly available at
this http URL

本文提出 TVQA，一个基于 6 个流行电视节目的大规模视频问答数据集，共计包含 152,545 对 QA 对，分布在 21,793 个片段中，共涵盖了 460 小时的视频。该数据集中的问题具有组合性质，需要系统联合定位剪辑中的相关片段，理解基于字幕的对话，并识别相关的视觉概念。作者提供了该数据集的分析以及几个基线模型和一个多流端到端可训练的神经网络框架。