Joint Constrained Learning for Event-Event Relation Extraction

Abstract

Understanding natural language involves recognizing how multiple event mentions structurally and temporally interact with each other.In this process, one can induce event complexes that organize multi-granular events with temporal order and membership relations interweaving among them. Due to the lack of jointly labeled data for these relational phenomena and the restriction on the structures they articulate, we propose a joint constrained learning framework for modeling event-event relations. Specifically, the framework enforces logical constraints within and across multiple temporal and subevent relations by converting these constraints into differentiable learning objectives. We show that our joint constrained learning approach effectively compensates for the lack of jointly labeled data, and outperforms SOTA methods on benchmarks for both temporal relation extraction and event hierarchy construction, replacing a commonly used but more expensive global inference process. We also present a promising case study showing the effectiveness of our approach in inducing event complexes on an external corpus. 1 * This work was done when the author was visiting the University of Pennsylvania.

Temporal Reasoning on Implicit Events from Distant Supervision

“…Table 3 shows the performance of our model and the baselines. We see that our model is consistently better than BaseLM, and at the same time, comparable to Wang et al (2020). Our model benefits more from input contexts, and only drops 4% in the OT-MS setting with minimal supervision (from 89.6 to 86.1), comparing to the 10% drop from T5-Large.…”

“…We report four results -OT-NS (original test, no story): train and test with only the sentences containing the trigger verbs; OT: train and test with the entire document (down-sampled to be below the maximum sequence length) as an auxiliary input; OT-MS (original test, minimal supervision): train with 1.2k (6%) training instances; PT (perturbed test): train with the complete training set and test on a perturbed test set from . In OT-NS, we also report a SOTA system from Wang et al (2020) under the same two-label 10 setting.…”

Constrained Multi-Task Learning for Event Coreference Resolution

“…Constrained learning in neural models. Another line of related work concerns the use of constraints in neural models (Li et al, 2019;Wang et al, 2020), where constraints are represented as first order logic formulas and compiled into the loss functions. These models are typically trained to minimize the weighted sum of task losses and constraint losses.…”

Is Killed More Significant than Fled? A Contextual Model for Salient Event Detection

“…The intuition is that the higher level and more abstract events are relatively more salient. We use the model from Wang et al (2020) to identify the parent-child relationship between every event pair. An event is called a child of another event if it is a subevent of the parent (e.g., "shooting" may be a subevent/child of an "attack" event).…”