中文
相关论文

相关论文: Incremental Interpretation: Applications, Theory, …

200 篇论文

Artificial intelligence and machine learning algorithms have become ubiquitous. Although they offer a wide range of benefits, their adoption in decision-critical fields is limited by their lack of interpretability, particularly with textual…

机器学习 · 计算机科学 2023-01-27 Diego Antognini

Images depicting complex, dynamic scenes are challenging to parse automatically, requiring both high-level comprehension of the overall situation and fine-grained identification of participating entities and their interactions. Current…

计算机视觉与模式识别 · 计算机科学 2025-05-06 Shahaf Pruss , Morris Alper , Hadar Averbuch-Elor

Adding interpretability to multivariate methods creates a powerful synergy for exploring complex physical systems with higher order correlations while bringing about a degree of clarity in the underlying dynamics of the system.

高能物理 - 唯象学 · 物理学 2022-05-04 Christophe Grojean , Ayan Paul , Zhuoni Qian , Inga Strümke

We introduce a new application for inductive logic programming: learning the semantics of programming languages from example evaluations. In this short paper, we explored a simplified task in this domain using the Metagol meta-interpretive…

编程语言 · 计算机科学 2019-07-23 Sándor Bartha , James Cheney

While data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited. In this paper, we present a novel data augmentation method for…

计算与语言 · 计算机科学 2019-05-28 Jinhua Zhu , Fei Gao , Lijun Wu , Yingce Xia , Tao Qin , Wengang Zhou , Xueqi Cheng , Tie-Yan Liu

Methods and insights from statistical physics are finding an increasing variety of applications where one seeks to understand the emergent properties of a complex interacting system. One such area concerns the dynamics of language at a…

物理与社会 · 物理学 2015-11-13 Richard A. Blythe

Recent advances in machine learning, particularly deep learning, have enabled autonomous systems to perceive and comprehend objects and their environments in a perceptual subsymbolic manner. These systems can now perform object detection,…

人工智能 · 计算机科学 2023-09-13 Amr Gomaa , Michael Feld

Next-word predictions from autoregressive neural language models show remarkable sensitivity to syntax. This work evaluates the extent to which this behavior arises as a result of a learned ability to maintain implicit representations of…

计算与语言 · 计算机科学 2022-11-18 Tiwalayo Eisape , Vineet Gangireddy , Roger P. Levy , Yoon Kim

Slang is a predominant form of informal language making flexible and extended use of words that is notoriously hard for natural language processing systems to interpret. Existing approaches to slang interpretation tend to rely on context…

计算与语言 · 计算机科学 2022-05-03 Zhewei Sun , Richard Zemel , Yang Xu

Computer programs are often factored into pure components -- simple, total functions from inputs to outputs -- and components that may have side effects -- errors, changes to memory, parallel threads, abortion of the current loop, etc. We…

计算与语言 · 计算机科学 2025-04-02 Dylan Bumford , Simon Charlow

Given a specific discourse, which discourse properties trigger the use of metaphorical language, rather than using literal alternatives? For example, what drives people to say "grasp the meaning" rather than "understand the meaning" within…

计算与语言 · 计算机科学 2022-05-24 Prisca Piccirilli , Sabine Schulte im Walde

Representation is a core issue in artificial intelligence. Humans use discrete language to communicate and learn from each other, while machines use continuous features (like vector, matrix, or tensor in deep neural networks) to represent…

计算机视觉与模式识别 · 计算机科学 2022-01-17 Yuqi Wang , Xu-Yao Zhang , Cheng-Lin Liu , Zhaoxiang Zhang

Are the predictions of humans and language models affected by similar things? Research suggests that while comprehending language, humans make predictions about upcoming words, with more predictable words being processed more easily.…

计算与语言 · 计算机科学 2022-11-11 James A. Michaelov , Benjamin K. Bergen

Many explainable AI (XAI) techniques strive for interpretability by providing concise salient information, such as sparse linear factors. However, users either only see inaccurate global explanations, or highly-varying local explanations.…

人机交互 · 计算机科学 2024-04-11 Jessica Y. Bo , Pan Hao , Brian Y. Lim

One goal of Artificial Intelligence is to learn meaningful representations for natural language expressions, but what this entails is not always clear. A variety of new linguistic behaviours present themselves embodied as computers,…

人工智能 · 计算机科学 2024-12-12 Davide Nunes , Luis Antunes

Much of human communication depends on implication, conveying meaning beyond literal words to express a wider range of thoughts, intentions, and feelings. For models to better understand and facilitate human communication, they must be…

The era of Large Language Models (LLMs) presents a new opportunity for interpretability--agentic interpretability: a multi-turn conversation with an LLM wherein the LLM proactively assists human understanding by developing and leveraging a…

人工智能 · 计算机科学 2025-06-17 Been Kim , John Hewitt , Neel Nanda , Noah Fiedel , Oyvind Tafjord

Multi-agent robotic systems are increasingly operating in real-world environments in close proximity to humans, yet are largely controlled by policy models with inscrutable deep neural network representations. We introduce a method for…

机器学习 · 计算机科学 2023-02-24 Renos Zabounidis , Joseph Campbell , Simon Stepputtis , Dana Hughes , Katia Sycara

Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such…

机器学习 · 计算机科学 2022-02-25 Claire Glanois , Paul Weng , Matthieu Zimmer , Dong Li , Tianpei Yang , Jianye Hao , Wulong Liu

We describe a computational model of humans' ability to provide a detailed interpretation of components in a scene. Humans can identify in an image meaningful components almost everywhere, and identifying these components is an essential…

人工智能 · 计算机科学 2021-10-19 Guy Ben-Yosef , Liav Assif , Daniel Harari , Shimon Ullman