While solving math word problems automatically has received considerable attention in the NLP community, few works have addressed probability word problems specifically. In this paper, we employ and analyse various neural models for answering such wo
rd problems. In a two-step approach, the problem text is first mapped to a formal representation in a declarative language using a sequence-to-sequence model, and then the resulting representation is executed using a probabilistic programming system to provide the answer. Our best performing model incorporates general-domain contextualised word representations that were finetuned using transfer learning on another in-domain dataset. We also apply end-to-end models to this task, which bring out the importance of the two-step approach in obtaining correct solutions to probability problems.
Much recent work in NLP has documented dataset artifacts, bias, and spurious correlations between input features and output labels. However, how to tell which features have spurious'' instead of legitimate correlations is typically left unspecified.
In this work we argue that for complex language understanding tasks, all simple feature correlations are spurious, and we formalize this notion into a class of problems which we call competency problems. For example, the word amazing'' on its own should not give information about a sentiment label independent of the context in which it appears, which could include negation, metaphor, sarcasm, etc. We theoretically analyze the difficulty of creating data for competency problems when human bias is taken into account, showing that realistic datasets will increasingly deviate from competency problems as dataset size increases. This analysis gives us a simple statistical test for dataset artifacts, which we use to show more subtle biases than were described in prior work, including demonstrating that models are inappropriately affected by these less extreme biases. Our theoretical treatment of this problem also allows us to analyze proposed solutions, such as making local edits to dataset instances, and to give recommendations for future data collection and model design efforts that target competency problems.
Many real-world problems require the combined application of multiple reasoning abilities---employing suitable abstractions, commonsense knowledge, and creative synthesis of problem-solving strategies. To help advance AI systems towards such capabili
ties, we propose a new reasoning challenge, namely Fermi Problems (FPs), which are questions whose answers can only be approximately estimated because their precise computation is either impractical or impossible. For example, How much would the sea level rise if all ice in the world melted?'' FPs are commonly used in quizzes and interviews to bring out and evaluate the creative reasoning abilities of humans. To do the same for AI systems, we present two datasets: 1) A collection of 1k real-world FPs sourced from quizzes and olympiads; and 2) a bank of 10k synthetic FPs of intermediate complexity to serve as a sandbox for the harder real-world challenge. In addition to question-answer pairs, the datasets contain detailed solutions in the form of an executable program and supporting facts, helping in supervision and evaluation of intermediate steps. We demonstrate that even extensively fine-tuned large-scale language models perform poorly on these datasets, on average making estimates that are off by two orders of magnitude. Our contribution is thus the crystallization of several unsolved AI problems into a single, new challenge that we hope will spur further advances in building systems that can reason.
Current neural math solvers learn to incorporate commonsense or domain knowledge by utilizing pre-specified constants or formulas. However, as these constants and formulas are mainly human-specified, the generalizability of the solvers is limited. In
this paper, we propose to explicitly retrieve the required knowledge from math problemdatasets. In this way, we can determinedly characterize the required knowledge andimprove the explainability of solvers. Our two algorithms take the problem text andthe solution equations as input. Then, they try to deduce the required commonsense and domain knowledge by integrating information from both parts. We construct two math datasets and show the effectiveness of our algorithms that they can retrieve the required knowledge for problem-solving.
This study deals with the most important problems related to the age of aging,
especially the social - psychological ones, which appear little by little as the age of man,
and from the increase in this segment on the one hand, and then seek to help
the elderly
and solve their problems on the other hand. This study deals with several aspects: First: the
concept of aging, its limits, its manifestations, second: the fertility that characterizes this
stage, the social problems of the elderly, the psychological problems of the elderly,
Problems of older persons. In conclusion, they made several proposals in order to
contribute to the goal of the study to focus attention on the elderly and to understand their
various problems in order to move towards solving them.
This research is a field study of the reality of small industrial
projects in the industrial area in Tartous. The researcher started a
theoretical presentation of the problems facing the small projects. It
was adopted in the field study to identify the basic problems and
the proposed solutions to the answers of a sample of the owners of
these projects.
This study aims to score psychological, academic and economic
problems faced by students with special needs in the Faculty of Arts at
the University of Damascus and to identify the differences in these
problems between the research samples. The sa
mple consisted of / 72/
students from the students of the Faculty of Arts at Damascus
University, was selected deliberate manner.
In this paper we offer a new interactive method for solving Multiobjective linear
programming problems. This method depends on forming the model for reducing the
relative deviations of objective functions from their ideal standard, and dealing with
the
unsatisfying deviations of objective functions by reacting with decision maker.
The results obtained from using this method were compared with many interactive
methods as (STEM Method[6] – Improvement STEM Method[7] – Matejas-peric
Method[8]). Numerical results indicate that the efficiency of purposed method comparing
with the obtained results by using that methods at initial solution point and the other
interactive points with decision maker.
The current research aims to identify the problems facing the
kindergarten where (buildings and equipment available where and
problems of professional and social parameters), the research
community of the public kindergartens parameters (Women's
Union-Teachers Association) in the city of Damascus, has been
withdrawn randomized them the sample, which amounted to (82)
teachers, and researcher used the following tools: a questionnaire
prepared by the researcher, has been used descriptive and analytical
approach so as to appropriateness of the nature of the search.
The research aims to introduce the Problems of teaching
Literature tor Arabic learners of other languages speakers from the
perspective of teachers. The research addresses the problems of
the texts in the courses of Arabic-teaching for general purposes.
