Generating visual explanations with natural language
نویسندگان
چکیده
Abstract We generate natural language explanations for a fine‐grained visual recognition task. Our fulfill two criteria. First, are class discriminative , meaning they mention attributes in an image which important to identify class. Second, relevant reflect the actual content of image. system, composed explanation sampler and phrase‐critic model, generates explanations. In addition, we demonstrate that our can help humans decide whether accept or reject AI decision.
منابع مشابه
Generating patient-specific interactive natural language explanations.
Patient compliance is a significant problem and is strongly correlated with the patients' understanding of their condition and prescribed treatment. Since doctors typically do not have large amounts of time to educate patients, and impersonal, voluminous patient handouts are largely ineffective, we propose the use of a sophisticated computer-based information system to generate tailored, intera...
متن کاملGenerating Natural Language Explanations for Decisions
We have implemented a model of decision making based on the goals and relationships of agents in the domain of Congressional roll call voting. The VOTE program simulates voting decisions of members of the United States House of Representatives on given bills. VOTE not only makes decisions, but also generates a natural language justiication for its decision that takes into account both the views...
متن کاملGenerating Visual Explanations
Clearly explaining a rationale for a classification decision to an end user can be as important as the decision itself. Existing approaches for deep visual recognition are generally opaque and do not output any justification text; contemporary vision-language models can describe image content but fail to take into account class-discriminative image aspects which justify visual predictions. We p...
متن کاملVisual Reasoning with Natural Language
Natural language provides a widely accessible and expressive interface for robotic agents. To understand language in complex environments, agents must reason about the full range of language inputs and their correspondence to the world. For example, consider the scenario and instruction in Figure 1. To execute the instruction, the robot must identify the top shelf, recognize the two stacks as s...
متن کاملInteractive Natural Language Explanations of Cyc Inferences
This paper describes the inference explanation capabilities of Cyc, a logical reasoning system that includes a huge “commonsense” knowledge base and an inference engine that supports both question answering and hypothesis generation. Cyc allows the user to compose queries by means of English templates, and tries to find answers via deductive reasoning. If deduction is fruitless Cyc resorts to a...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Applied AI letters
سال: 2021
ISSN: ['2689-5595']
DOI: https://doi.org/10.1002/ail2.55