A fundamental goal of scientific research is to learn about causal relationships. However, despite its critical role in the life and social sciences, causality has not had the same importance in Natural Language Processing (NLP), which has traditionally placed more emphasis on predictive tasks. This distinction is beginning to fade, with an emerging area of interdisciplinary research at the convergence of causal inference and language processing. Still, research on causality in NLP remains scattered across domains without unified definitions, benchmark datasets and clear articulations of the remaining challenges. In this survey, we consolidate research across academic areas and situate it in the broader NLP landscape. We introduce the statistical challenge of estimating causal effects, encompassing settings where text is used as an outcome, treatment, or as a means to address confounding. In addition, we explore potential uses of causal inference to improve the performance, robustness, fairness, and interpretability of NLP models. We thus provide a unified overview of causal inference for the computational linguistics community.

15
下载
关闭预览

相关内容

Processing 是一门开源编程语言和与之配套的集成开发环境(IDE)的名称。Processing 在电子艺术和视觉设计社区被用来教授编程基础,并运用于大量的新媒体和互动艺术作品中。

Neural network models have achieved state-of-the-art performances in a wide range of natural language processing (NLP) tasks. However, a long-standing criticism against neural network models is the lack of interpretability, which not only reduces the reliability of neural NLP systems but also limits the scope of their applications in areas where interpretability is essential (e.g., health care applications). In response, the increasing interest in interpreting neural NLP models has spurred a diverse array of interpretation methods over recent years. In this survey, we provide a comprehensive review of various interpretation methods for neural models in NLP. We first stretch out a high-level taxonomy for interpretation methods in NLP, i.e., training-based approaches, test-based approaches, and hybrid approaches. Next, we describe sub-categories in each category in detail, e.g., influence-function based methods, KNN-based methods, attention-based models, saliency-based methods, perturbation-based methods, etc. We point out deficiencies of current methods and suggest some avenues for future research.

0
0
下载
预览

Naturality of long-term information structure -- coherence -- remains a challenge in language generation. Large language models have insufficiently learned such structure, as their long-form generations differ from natural text in measures of coherence. To alleviate this divergence, we propose coherence boosting, an inference procedure that increases the effect of distant context on next-token prediction. We show the benefits of coherence boosting with pretrained models by distributional analyses of generated ordinary text and dialog responses. We also find that coherence boosting with state-of-the-art models for various zero-shot NLP tasks yields performance gains with no additional training.

0
0
下载
预览

Many modern applications seek to understand the relationship between an outcome variable $Y$ and a covariate $X$ in the presence of a (possibly high-dimensional) confounding variable $Z$. Although much attention has been paid to testing whether $Y$ depends on $X$ given $Z$, in this paper we seek to go beyond testing by inferring the strength of that dependence. We first define our estimand, the minimum mean squared error (mMSE) gap, which quantifies the conditional relationship between $Y$ and $X$ in a way that is deterministic, model-free, interpretable, and sensitive to nonlinearities and interactions. We then propose a new inferential approach called floodgate that can leverage any working regression function chosen by the user (allowing, e.g., it to be fitted by a state-of-the-art machine learning algorithm or be derived from qualitative domain knowledge) to construct asymptotic confidence bounds, and we apply it to the mMSE gap. In addition to proving floodgate's asymptotic validity, we rigorously quantify its accuracy (distance from confidence bound to estimand) and robustness. We then show we can apply the same floodgate principle to a different measure of variable importance when $Y$ is binary. Finally, we demonstrate floodgate's performance in a series of simulations and apply it to data from the UK Biobank to infer the strengths of dependence of platelet count on various groups of genetic mutations.

0
0
下载
预览

We address the problem of causal effect estimation in the presence of unobserved confounding, but where proxies for the latent confounder(s) are observed. We propose two kernel-based methods for nonlinear causal effect estimation in this setting: (a) a two-stage regression approach, and (b) a maximum moment restriction approach. We focus on the proximal causal learning setting, but our methods can be used to solve a wider class of inverse problems characterised by a Fredholm integral equation. In particular, we provide a unifying view of two-stage and moment restriction approaches for solving this problem in a nonlinear setting. We provide consistency guarantees for each algorithm, and we demonstrate these approaches achieve competitive results on synthetic data and data simulating a real-world task. In particular, our approach outperforms earlier methods that are not suited to leveraging proxy variables.

0
0
下载
预览

Human mental processes allow for qualitative reasoning about causality in terms of mechanistic relations of the variables of interest, which we argue are naturally described by structural causal model (SCM). Since interpretations are being derived from mental models, the same applies for SCM. By defining a metric space on SCM, we provide a theoretical perspective on the comparison of mental models and thereby conclude that interpretations can be used for guiding a learning system towards true causality. To this effect, we present a theoretical analysis from first principles that results in a human-readable interpretation scheme consistent with the provided causality that we name structural causal interpretations (SCI). Going further, we prove that any existing neural induction method (NIM) is in fact interpretable. Our first experiment (E1) assesses the quality of such NIM-based SCI. In (E2) we observe evidence for our conjecture on improved sample-efficiency for SCI-based learning. After conducting a small user study, in (E3) we observe superiority in human-based over NIM-based SCI in support of our initial hypothesis.

0
0
下载
预览

Several queries and scores have recently been proposed to explain individual predictions over ML models. Given the need for flexible, reliable, and easy-to-apply interpretability methods for ML models, we foresee the need for developing declarative languages to naturally specify different explainability queries. We do this in a principled way by rooting such a language in a logic, called FOIL, that allows for expressing many simple but important explainability queries, and might serve as a core for more expressive interpretability languages. We study the computational complexity of FOIL queries over two classes of ML models often deemed to be easily interpretable: decision trees and OBDDs. Since the number of possible inputs for an ML model is exponential in its dimension, the tractability of the FOIL evaluation problem is delicate but can be achieved by either restricting the structure of the models or the fragment of FOIL being evaluated. We also present a prototype implementation of FOIL wrapped in a high-level declarative language and perform experiments showing that such a language can be used in practice.

0
6
下载
预览

In the era of deep learning, modeling for most NLP tasks has converged to several mainstream paradigms. For example, we usually adopt the sequence labeling paradigm to solve a bundle of tasks such as POS-tagging, NER, Chunking, and adopt the classification paradigm to solve tasks like sentiment analysis. With the rapid progress of pre-trained language models, recent years have observed a rising trend of Paradigm Shift, which is solving one NLP task by reformulating it as another one. Paradigm shift has achieved great success on many tasks, becoming a promising way to improve model performance. Moreover, some of these paradigms have shown great potential to unify a large number of NLP tasks, making it possible to build a single model to handle diverse tasks. In this paper, we review such phenomenon of paradigm shifts in recent years, highlighting several paradigms that have the potential to solve different NLP tasks.

0
16
下载
预览

Causal inference is a critical research topic across many domains, such as statistics, computer science, education, public policy and economics, for decades. Nowadays, estimating causal effect from observational data has become an appealing research direction owing to the large amount of available data and low budget requirement, compared with randomized controlled trials. Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up. In this survey, we provide a comprehensive review of causal inference methods under the potential outcome framework, one of the well known causal inference framework. The methods are divided into two categories depending on whether they require all three assumptions of the potential outcome framework or not. For each category, both the traditional statistical methods and the recent machine learning enhanced methods are discussed and compared. The plausible applications of these methods are also presented, including the applications in advertising, recommendation, medicine and so on. Moreover, the commonly used benchmark datasets as well as the open-source codes are also summarized, which facilitate researchers and practitioners to explore, evaluate and apply the causal inference methods.

0
78
下载
预览

Natural Language Inference (NLI) is fundamental to many Natural Language Processing (NLP) applications including semantic search and question answering. The NLI problem has gained significant attention thanks to the release of large scale, challenging datasets. Present approaches to the problem largely focus on learning-based methods that use only textual information in order to classify whether a given premise entails, contradicts, or is neutral with respect to a given hypothesis. Surprisingly, the use of methods based on structured knowledge -- a central topic in artificial intelligence -- has not received much attention vis-a-vis the NLI problem. While there are many open knowledge bases that contain various types of reasoning information, their use for NLI has not been well explored. To address this, we present a combination of techniques that harness knowledge graphs to improve performance on the NLI problem in the science questions domain. We present the results of applying our techniques on text, graph, and text-to-graph based models, and discuss implications for the use of external knowledge in solving the NLI problem. Our model achieves the new state-of-the-art performance on the NLI problem over the SciTail science questions dataset.

0
3
下载
预览

This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input. A survey of NLG is timely in view of the changes that the field has undergone over the past decade or so, especially in relation to new (usually data-driven) methods, as well as new applications of NLG technology. This survey therefore aims to (a) give an up-to-date synthesis of research on the core tasks in NLG and the architectures adopted in which such tasks are organised; (b) highlight a number of relatively recent research topics that have arisen partly as a result of growing synergies between NLG and other areas of artificial intelligence; (c) draw attention to the challenges in NLG evaluation, relating them to similar challenges faced in other areas of Natural Language Processing, with an emphasis on different evaluation methods and the relationships between them.

1
5
下载
预览
小贴士
相关论文
Xiaofei Sun,Diyi Yang,Xiaoya Li,Tianwei Zhang,Yuxian Meng,Qiu Han,Guoyin Wang,Eduard Hovy,Jiwei Li
0+阅读 · 10月20日
Nikolay Malkin,Zhen Wang,Nebojsa Jojic
0+阅读 · 10月15日
Lu Zhang,Lucas Janson
0+阅读 · 10月15日
Afsaneh Mastouri,Yuchen Zhu,Limor Gultchin,Anna Korba,Ricardo Silva,Matt J. Kusner,Arthur Gretton,Krikamol Muandet
0+阅读 · 10月9日
Matej Zečević,Devendra Singh Dhami,Constantin A. Rothkopf,Kristian Kersting
0+阅读 · 10月5日
Marcelo Arenas,Daniel Baez,Pablo Barceló,Jorge Pérez,Bernardo Subercaseaux
6+阅读 · 10月5日
Tianxiang Sun,Xiangyang Liu,Xipeng Qiu,Xuanjing Huang
16+阅读 · 9月26日
Liuyi Yao,Zhixuan Chu,Sheng Li,Yaliang Li,Jing Gao,Aidong Zhang
78+阅读 · 2020年2月5日
Improving Natural Language Inference Using External Knowledge in the Science Questions Domain
Xiaoyan Wang,Pavan Kapanipathi,Ryan Musa,Mo Yu,Kartik Talamadupula,Ibrahim Abdelaziz,Maria Chang,Achille Fokoue,Bassem Makni,Nicholas Mattei,Michael Witbrock
3+阅读 · 2018年9月15日
相关资讯
【资源】问答阅读理解资源列表
专知
3+阅读 · 2020年7月25日
Call for Participation: Shared Tasks in NLPCC 2019
中国计算机学会
5+阅读 · 2019年3月22日
人工智能 | NIPS 2019等国际会议信息8条
Call4Papers
6+阅读 · 2019年3月21日
A Technical Overview of AI & ML in 2018 & Trends for 2019
待字闺中
10+阅读 · 2018年12月24日
人工智能 | 国际会议信息10条
Call4Papers
5+阅读 · 2018年12月18日
Disentangled的假设的探讨
CreateAMind
7+阅读 · 2018年12月10日
计算机类 | 期刊专刊截稿信息9条
Call4Papers
4+阅读 · 2018年1月26日
【论文】变分推断(Variational inference)的总结
机器学习研究会
24+阅读 · 2017年11月16日
Top