Causal reasoning aims to predict the future scenarios that may be caused by the observed actions. However, existing causal reasoning methods deal with causalities on the word level. In this paper, we propose a novel event-level causal reasoning metho
d and demonstrate its use in the task of effect generation. In particular, we structuralize the observed cause-effect event pairs into an event causality network, which describes causality dependencies. Given an input cause sentence, a causal subgraph is retrieved from the event causality network and is encoded with the graph attention mechanism, in order to support better reasoning of the potential effects. The most probable effect event is then selected from the causal subgraph and is used as guidance to generate an effect sentence. Experiments show that our method generates more reasonable effect sentences than various well-designed competitors.
In this study, we propose a self-supervised learning method that distils representations of word meaning in context from a pre-trained masked language model. Word representations are the basis for context-aware lexical semantics and unsupervised sema
ntic textual similarity (STS) estimation. A previous study transforms contextualised representations employing static word embeddings to weaken excessive effects of contextual information. In contrast, the proposed method derives representations of word meaning in context while preserving useful context information intact. Specifically, our method learns to combine outputs of different hidden layers using self-attention through self-supervised learning with an automatically generated training corpus. To evaluate the performance of the proposed approach, we performed comparative experiments using a range of benchmark tasks. The results confirm that our representations exhibited a competitive performance compared to that of the state-of-the-art method transforming contextualised representations for the context-aware lexical semantic tasks and outperformed it for STS estimation.
We consider the problem of using observational data to estimate the causal effects of linguistic properties. For example, does writing a complaint politely lead to a faster response time? How much will a positive product review increase sales? This p
aper addresses two technical challenges related to the problem before developing a practical method. First, we formalize the causal quantity of interest as the effect of a writer's intent, and establish the assumptions necessary to identify this from observational data. Second, in practice, we only have access to noisy proxies for the linguistic properties of interest---e.g., predictions from classifiers and lexicons. We propose an estimator for this setting and prove that its bias is bounded when we perform an adjustment for the text. Based on these results, we introduce TextCause, an algorithm for estimating causal effects of linguistic properties. The method leverages (1) distant supervision to improve the quality of noisy proxies, and (2) a pre-trained language model (BERT) to adjust for the text. We show that the proposed method outperforms related approaches when estimating the effect of Amazon review sentiment on semi-simulated sales figures. Finally, we present an applied case study investigating the effects of complaint politeness on bureaucratic response times.
Due to its great power in modeling non-Euclidean data like graphs or manifolds, deep learning on graph techniques (i.e., Graph Neural Networks (GNNs)) have opened a new door to solving challenging graph-related NLP problems. There has seen a surge of
interests in applying deep learning on graph techniques to NLP, and has achieved considerable success in many NLP tasks, ranging from classification tasks like sentence classification, semantic role labeling and relation extraction, to generation tasks like machine translation, question generation and summarization. Despite these successes, deep learning on graphs for NLP still face many challenges, including automatically transforming original text sequence data into highly graph-structured data, and effectively modeling complex data that involves mapping between graph-based inputs and other highly structured output data such as sequences, trees, and graph data with multi-types in both nodes and edges. This tutorial will cover relevant and interesting topics on applying deep learning on graph techniques to NLP, including automatic graph construction for NLP, graph representation learning for NLP, advanced GNN based models (e.g., graph2seq, graph2tree, and graph2graph) for NLP, and the applications of GNNs in various NLP tasks (e.g., machine translation, natural language generation, information extraction and semantic parsing). In addition, hands-on demonstration sessions will be included to help the audience gain practical experience on applying GNNs to solve challenging NLP problems using our recently developed open source library -- Graph4NLP, the first library for researchers and practitioners for easy use of GNNs for various NLP tasks.
Deep neural networks have constantly pushed the state-of-the-art performance in natural language processing and are considered as the de-facto modeling approach in solving complex NLP tasks such as machine translation, summarization and question-answ
ering. Despite the proven efficacy of deep neural networks at-large, their opaqueness is a major cause of concern. In this tutorial, we will present research work on interpreting fine-grained components of a neural network model from two perspectives, i) fine-grained interpretation, and ii) causation analysis. The former is a class of methods to analyze neurons with respect to a desired language concept or a task. The latter studies the role of neurons and input features in explaining the decisions made by the model. We will also discuss how interpretation methods and causation analysis can connect towards better interpretability of model prediction. Finally, we will walk you through various toolkits that facilitate fine-grained interpretation and causation analysis of neural models.
Causal inference is the process of capturing cause-effect relationship among variables. Most existing works focus on dealing with structured data, while mining causal relationship among factors from unstructured data, like text, has been less examine
d, but is of great importance, especially in the legal domain. In this paper, we propose a novel Graph-based Causal Inference (GCI) framework, which builds causal graphs from fact descriptions without much human involvement and enables causal inference to facilitate legal practitioners to make proper decisions. We evaluate the framework on a challenging similar charge disambiguation task. Experimental results show that GCI can capture the nuance from fact descriptions among multiple confusing charges and provide explainable discrimination, especially in few-shot settings. We also observe that the causal knowledge contained in GCI can be effectively injected into powerful neural networks for better performance and interpretability.
We study the problem of Event Causality Identification (ECI) to detect causal relation between event mention pairs in text. Although deep learning models have recently shown state-of-the-art performance for ECI, they are limited to the intra-sentence
setting where event mention pairs are presented in the same sentences. This work addresses this issue by developing a novel deep learning model for document-level ECI (DECI) to accept inter-sentence event mention pairs. As such, we propose a graph-based model that constructs interaction graphs to capture relevant connections between important objects for DECI in input documents. Such interaction graphs are then consumed by graph convolutional networks to learn document context-augmented representations for causality prediction between events. Various information sources are introduced to enrich the interaction graphs for DECI, featuring discourse, syntax, and semantic information. Our extensive experiments show that the proposed model achieves state-of-the-art performance on two benchmark datasets.
Abstract Recent improvements in the predictive quality of natural language processing systems are often dependent on a substantial increase in the number of model parameters. This has led to various attempts of compressing such models, but existing m
ethods have not considered the differences in the predictive power of various model components or in the generalizability of the compressed models. To understand the connection between model compression and out-of-distribution generalization, we define the task of compressing language representation models such that they perform best in a domain adaptation setting. We choose to address this problem from a causal perspective, attempting to estimate the average treatment effect (ATE) of a model component, such as a single layer, on the model's predictions. Our proposed ATE-guided Model Compression scheme (AMoC), generates many model candidates, differing by the model components that were removed. Then, we select the best candidate through a stepwise regression model that utilizes the ATE to predict the expected performance on the target domain. AMoC outperforms strong baselines on dozens of domain pairs across three text classification and sequence tagging tasks.1
The principle of causality is considered one of the most important philosophical and
scientific principles that played a seminal role in developing scientific and epistemic
research. This started with the commencement of philosophical thought. Sinc
e then the
early philosophers attempted to look for the first causes that formed the universe and the
real reasons that led to the phenomena and incidents happeningin it , Hence, the principle
of causality helped to present a general comprehensive viewpoint about the universe. This
viewpoint says that nature always undergoes fixed rules, phenomena becomes regular
according to a certain system and that the hierarchy of these phenomena is linked with
systems that have laws and certain causal liaisons .
With the advancement of science and knowledge, it has become clear to scientists
and thinkers that mind does not conclude laws save through a number of principles, one of
which is the principle of causality. Thus, scientific experiment shows that phenomena are
related to each other as the causesare related to the effects. This is explained through the
principle of causality by which it is possible to derive conclusions of the general laws that
rule the relationships between correlated phenomena , As a result of the causal theory,
many philosophical and scientific concepts that are strongly related to the principle of
causality emerged. Such concepts were that of necessity, inevitability and indeterminism
which in its turn led to the emergence of many philosophical doctrines and scientific
movements that contributed greatly to the scientific and epistemic sphere through the
theories and problematic questions they posed and probed.
This study aimed to test the relationship between the components of economic freedom and
political freedoms in (6) Arab countries of the (MENA) Group during the period 2006-2015, based
firstly on studying and reviewing the intellectual trends and t
he empirical studies on this
relationship. and secondly on a Econometric study based on (Panel Data), and an estimation of the
parameters of the model after the tests of data stability using the (FEM) model which was chosen
according to the (F-Statistique) value of the (Wald) test.
