Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPlan Explanations that Exploit a Cognitive Spatial Model
تفسيرات خطة تستغل نموذجا مكثفا معرفيا
75
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
من الناحية المثالية، يشارك الأشخاص الذين ينقلون معا في الفضاء الداخلي المعقد نموذجا عقليا يسهل التفسير.تقارير الورقة هذه عن نظام تحكم روبوت يعتمد طراز العالم المعرفي على التمويل المكاني الذي يعمم على بياناته الإدراكية.بالنظر إلى وجود هدف، يقوم نظام التحكم في صياغة خطط متعددة، ولكل منها متري ذات صلة بالنماذج، وينشط بينها.نتيجة لذلك، يمكن أن توفر لغة طبيعية مفهومة بسهولة حول نوايا الروبوت والثقة، وتوليد تفسيرات متنوعة ومتعاكة تشير إلى النموذج المكاني المكتسب.النتائج التجريبية في البيئات الكبيرة المعقدة توضح قدرة الروبوت على توفير تفسيرات سهلة الاستخدام في اللغة الطبيعية.
Ideally, people who navigate together in a complex indoor space share a mental model that facilitates explanation. This paper reports on a robot control system whose cognitive world model is based on spatial affordances that generalize over its perceptual data. Given a target, the control system formulates multiple plans, each with a model-relevant metric, and selects among them. As a result, it can provide readily understandable natural language about the robot's intentions and confidence, and generate diverse, contrastive explanations that reference the acquired spatial model. Empirical results in large, complex environments demonstrate the robot's ability to provide human-friendly explanations in natural language.
References used
https://aclanthology.org/
rate research
Read More
Contrastive explanations clarify why an event occurred in contrast to another. They are inherently intuitive to humans to both produce and comprehend. We propose a method to produce contrastive explanations in the latent space, via a projection of th
e input representation, such that only the features that differentiate two potential decisions are captured. Our modification allows model behavior to consider only contrastive reasoning, and uncover which aspects of the input are useful for and against particular decisions. Our contrastive explanations can additionally answer for which label, and against which alternative label, is a given input feature useful. We produce contrastive explanations via both high-level abstract concept attribution and low-level input token/span attribution for two NLP classification benchmarks. Our findings demonstrate the ability of label-contrastive explanations to provide fine-grained interpretability of model decisions.
In this paper, we explore the construction of natural language explanations for news claims, with the goal of assisting fact-checking and news evaluation applications. We experiment with two methods: (1) an extractive method based on Biased TextRank
-- a resource-effective unsupervised graph-based algorithm for content extraction; and (2) an abstractive method based on the GPT-2 language model. We perform comparative evaluations on two misinformation datasets in the political and health news domains, and find that the extractive method shows the most promise.
This research discusses the problem of drinking water shortage and
distribution instability in Salamyeh city due to the current crisis.
Salamyeh city dependents on Orontes River as a source for drinking
water through Hama water supply facility, wh
ich sufferes repeated
sabbotage attacks. As a result, an emergency measure was implemented
by depending on local water sources within the city, which are deep wells
that produce water of sulphuric nature.Three desalination plants were
provided to treat local sulphuric water producing suitable safe water, but
these plants production is way less than the city needs.
Given the diversity of the candidates and complexity of job requirements, and since interviewing is an inherently subjective process, it is an important task to ensure consistent, uniform, efficient and objective interviews that result in high qualit
y recruitment. We propose an interview assistant system to automatically, and in an objective manner, select an optimal set of technical questions (from question banks) personalized for a candidate. This set can help a human interviewer to plan for an upcoming interview of that candidate. We formalize the problem of selecting a set of questions as an integer linear programming problem and use standard solvers to get a solution. We use knowledge graph as background knowledge in this formulation, and derive our objective functions and constraints from it. We use candidate's resume to personalize the selection of questions. We propose an intrinsic evaluation to compare a set of suggested questions with actually asked questions. We also use expert interviewers to comparatively evaluate our approach with a set of reasonable baselines.
Recent developments in neural networks have led to the advance in data-to-text generation. However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications. In this study, w
e propose a novel Plan-then-Generate (PlanGen) framework to improve the controllability of neural data-to-text models. Extensive experiments and analyses are conducted on two benchmark datasets, ToTTo and WebNLG. The results show that our model is able to control both the intra-sentence and inter-sentence structure of the generated output. Furthermore, empirical comparisons against previous state-of-the-art methods show that our model improves the generation quality as well as the output diversity as judged by human and automatic evaluations.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
