Local-to-Global Causal Reasoning for Cross-Document Relation Extraction

Cross-document relation extraction(RE),as an extension of information extraction,requires integrating information from multiple documents retrieved from open domains with a large number of irrelevant or confusing noisy texts.Previous studies focus on the attention mechanism to construct the connection between different text features through semantic similarity.However,similarity-based methods cannot distinguish valid information from highly similar retrieved documents well.How to design an effective algorithm to implement aggregated reasoning in confusing information with similar features still remains an open issue.To address this problem,we design a novel local-toglobal causal reasoning(LGCR)network for cross-document RE,which enables efficient distinguishing,filtering and global reasoning on complex information from a causal perspective.Specifically,we propose a local causal estimation algorithm to estimate the causal effect,which is the first trial to use the causal reasoning independent of feature similarity to distinguish between confusing and valid information in cross-document RE.Furthermore,based on the causal effect,we propose a causality guided global reasoning algorithm to filter the confusing information and achieve global reasoning.Experimental results under the closed and the open settings of the large-scale dataset Cod RED demonstrate our LGCR network significantly outperforms the state-ofthe-art methods and validate the effectiveness of causal reasoning in confusing information processing.

An Analysis of the Causal Reasoning Deficiencies in English Majors' Argumentative Writing

The Syllabus for English Majors at Universities and Colleges(2000) makes it clear to further strengthen the English majors' critical thinking and logical reasoning ability.But how to effectively incorporate the cultivation of critical thinking skills into English majors' core courses,such as the writing courses,remains one of the most important tasks of teaching reform for English majors.The present study is aimed at having a systematic analysis on the causal reasoning deficiencies in English majors' argumentative writing.Furthermore,the reasons resulting in the causal reasoning deficiencies and the implications for the teaching of second language writing are explored.

Causal reasoning in typical computer vision tasks

Deep learning has revolutionized the field of artificial intelligence.Based on the statistical correlations uncovered by deep learning-based methods,computer vision tasks,such as autonomous driving and robotics,are growing rapidly.Despite being the basis of deep learning,such correlation strongly depends on the distribution of the original data and is susceptible to uncontrolled factors.Without the guidance of prior knowledge,statistical correlations alone cannot correctly reflect the essential causal relations and may even introduce spurious correlations.As a result,researchers are now trying to enhance deep learningbased methods with causal theory.Causal theory can model the intrinsic causal structure unaffected by data bias and effectively avoids spurious correlations.This paper aims to comprehensively review the existing causal methods in typical vision and visionlanguage tasks such as semantic segmentation,object detection,and image captioning.The advantages of causality and the approaches for building causal paradigms will be summarized.Future roadmaps are also proposed,including facilitating the development of causal theory and its application in other complex scenarios and systems.

Causal Reasoning Meets Visual Representation Learning: A Prospective Study

Visual representation learning is ubiquitous in various real-world applications,including visual comprehension,video understanding,multi-modal analysis,human-computer interaction,and urban computing.Due to the emergence of huge amounts of multimodal heterogeneous spatial/temporal/spatial-temporal data in the big data era,the lack of interpretability,robustness,and out-of-distribution generalization are becoming the challenges of the existing visual models.The majority of the existing methods tend to fit the original data/variable distributions and ignore the essential causal relations behind the multi-modal knowledge,which lacks unified guidance and analysis about why modern visual representation learning methods easily collapse into data bias and have limited generalization and cognitive abilities.Inspired by the strong inference ability of human-level agents,recent years have therefore witnessed great effort in developing causal reasoning paradigms to realize robust representation and model learning with good cognitive ability.In this paper,we conduct a comprehensive review of existing causal reasoning methods for visual representation learning,covering fundamental theories,models,and datasets.The limitations of current methods and datasets are also discussed.Moreover,we propose some prospective challenges,opportunities,and future research directions for benchmarking causal reasoning algorithms in visual representation learning.This paper aims to provide a comprehensive overview of this emerging field,attract attention,encourage discussions,bring to the forefront the urgency of developing novel causal reasoning methods,publicly available benchmarks,and consensus-building standards for reliable visual representation learning and related real-world applications more efficiently.

Causal Inference

Causal inference is a powerful modeling tool for explanatory analysis,which might enable current machine learning to become explainable.How to marry causal inference with machine learning to develop explainable artificial intelligence(XAI)algorithms is one of key steps toward to the artificial intelligence 2.0.With the aim of bringing knowledge of causal inference to scholars of machine learning and artificial intelligence,we invited researchers working on causal inference to write this survey from different aspects of causal inference.This survey includes the following sections:“Estimating average treatment effect:A brief review and beyond”from Dr.Kun Kuang,“Attribution problems in counterfactual inference”from Prof.Lian Li,“The Yule–Simpson paradox and the surrogate paradox”from Prof.Zhi Geng,“Causal potential theory”from Prof.Lei Xu,“Discovering causal information from observational data”from Prof.Kun Zhang,“Formal argumentation in causal reasoning and explanation”from Profs.Beishui Liao and Huaxin Huang,“Causal inference with complex experiments”from Prof.Peng Ding,“Instrumental variables and negative controls for observational studies”from Prof.Wang Miao,and“Causal inference with interference”from Dr.Zhichao Jiang.

Academic Freedom,Feminism and the Probabilistic Conception of Evidence

There is a current debate about the extent to which Academic Freedom should be permitted in our universities.On the one hand,we have traditionalists who maintain that Academic Freedom should be unrestricted:people who have the appropriate qualifications and accomplishments should be allowed to develop theories about how the world is,or ought to be,as they see fit.On the other hand,we have post-traditional philosophers who argue against this degree of Academic Freedom.I consider a conservative version of post-traditional philosophy that permits restrictions on Academic Freedom only if the following conditions are met,Condition 1:The dissemination of the results of a given research project R must cause significant harm to some people,especially to people from oppressed groups.Condition 2:Condition 1 must possess strong empirical support,and which accepts the following assumptions:(1)there is a world of objective facts that is,in principle,discoverable,(2)rational means are the means of discovering it and,(3)rational means requires strong empirical support.I define strong empirical support for an hypothesis h on evidence e in probabilistic terms,as a ratio of posterior to prior probabilities substantially exceeding 1.I now argue in favour of a research policy that accepts unrestricted Academic Freedom.My argument is that there is a formal and general quandary that arises within the standard theory of probability when we apply this account of empirical support to a set of possible causal hypotheses framed in such a way that the“reverse probabilities”,pr(e/h)are 1.I consider various possible ways to escape this quandary,none of which are without difficulties,concluding that a research policy allowing for unrestricted Academic Freedom is probably the best that we can hope for.