Joint Reasoning for Temporal and Causal Relations

By Qiang Ning, Zhili Feng, Hao Wu, Dan Roth. 2018

173 citations recorded by the source corpus.

Understanding temporal and causal relations between events is a fundamental natural language understanding task. Because a cause must occur earlier than its effect, temporal and causal relations are closely related and one relation often dictates the value of the other. However, limited attention has been paid to studying these two relations jointly. This paper presents a joint inference framework for them using constrained conditional models (CCMs). Specifically, we formulate the joint problem as an integer linear programming (ILP) problem, enforcing constraints that are inherent in the nature of time and causality. We show that the joint inference framework results in statistically significant improvement in the extraction of both temporal and causal relations from text.

Subfields: Artificial Intelligence, Computer Networks and Communications, Information Extraction, Causal Inference & Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Nanyun Peng
2. Rujun Han
3. Dan Roth
4. Daniel Khashabi
5. Qiang Ning
6. Xiang Ren
7. Ben Zhou
8. Aram Galstyan

In Computer Networks and Communications

1. Nanyun Peng
2. Rujun Han
3. Qiang Ning
4. Aram Galstyan
5. Tat-seng Chua
6. Dan Roth
7. Daniel Khashabi
8. Yangqiu Song

In Information Extraction

1. Nanyun Peng
2. Rujun Han
3. Qiang Ning
4. Daniel Khashabi
5. Angela Yao
6. Tat-seng Chua
7. Dan Roth
8. Yangqiu Song

In Causal Inference & Discovery

1. Nanyun Peng
2. Rujun Han
3. Qiang Ning
4. Aram Galstyan
5. Tat-seng Chua

Citations in the corpus

• NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (2021, background): “Finally, we note that QA on causal and temporal events have long been studied in text comprehension [12, 34].”
• “Going on a vacation” takes longer than “Going for a walk”: A Study of Temporal Commonsense Understanding (2019, background): “…work has investigated some of these aspects, either explicitly or implicitly (e.g., duration (Gusev et al., 2011; Williams, 2012) and ordering (Chklovski and Pantel, 2004; Ning et al., 2018b)), but none of them have defined or studied all aspects of temporal commonsense in a unified framework.”
• Contextualized Word Embeddings Enhanced Event Temporal Relation Extraction for Story Understanding (2019, background): “Despite multiple productive research threads on temporal and causal relation modeling among events (Chambers et al., 2014; Ning et al., 2018a; Meng and Rumshisky, 2018) and event relation annotation for story understanding (Mostafazadeh et al.”
• Temporal Common Sense Acquisition with Minimal Supervision (2020, background): “…on the extraction and normalization of temporal expressions (Str¨otgen and Gertz, 2010; An-geli et al., 2012; Lee et al., 2014; Vashishtha et al., 2019), temporal relation extraction (Ning et al., 2017, 2018c; Vashishtha et al., 2019), and time-line construction (Leeuwenberg and Moens, 2018).”
• Partial Or Complete, That’s The Question (2019, unknown): “Following CogComp-Time (Ning et al., 2018d), we choose the same features and sparse-averaged perceptron algorithm as the L EARN component and ILP as I NFERENCE for SSPAN.”
• Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction (2019, methodology): “Recent data construction efforts such as MATRES (Ning et al., 2018a) further enhance the data quality by using a multi-axis annotation scheme and adopting a startpoint of events to improve inter-annotator agreements.”
• Guided Generation of Cause and Effect (2020, unknown): “…generation [Ammanabrolu et al. , 2019; Tang et al. , 2019; Clark et al. , 2018; Hu et al. , 2019b], Sentential Causal Resource # CE Pairs TCR [Ning et al. , 2018] 172 SemEval-2007 Task4 [Girju et al. , 2007] 220 Causal-TimeBank [Mirza et al. , 2014] 318 CaTeRS [Mostafazadeh et al. , 2016]…”
• Deep Structured Neural Network for Event Temporal Relation Extraction (2019, methodology): “This constraint specifies that if event i causes event j, then i has to occur before j. Note that this constraint only has 91.9% accuracy in TCR data (Ning et al., 2018a), but it can help improve model performance based on our experiments.”
• Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction (2020, unknown): “To cope with the class-imbalance problem and the small dataset issues, recent research efforts adopt hard constraint -enhanced deep learning methods and leverage pre-trained language models (Ning et al., 2018c; Han et al., 2019b) and are able to establish reasonable baselines for the task.”
• ASER: A Large-scale Eventuality Knowledge Graph (2019, background): “Such correlation between temporal and causal relations is also observed in [27].”