ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning

04/16/2021
by   Rujun Han, et al.
9

Stories and narratives are composed based on a variety of events. Understanding how these events are semantically related to each other is the essence of reading comprehension. Recent event-centric reading comprehension datasets focus on either event arguments or event temporal commonsense. Although these tasks evaluate machines' ability of narrative understanding, human like reading comprehension requires the capability to process event-based semantics beyond arguments and temporal commonsense. For example, to understand causality between events, we need to infer motivations or purposes; to understand event hierarchy, we need to parse the composition of events. To facilitate these tasks, we introduce ESTER, a comprehensive machine reading comprehension (MRC) dataset for Event Semantic Relation Reasoning. We study five most commonly used event semantic relations and formulate them as question answering tasks. Experimental results show that the current SOTA systems achieve 60.5 scores respectively, which are significantly below human performances.

READ FULL TEXT
research
08/27/2020

Relation/Entity-Centric Reading Comprehension

Constructing a machine that understands human language is one of the mos...
research
06/25/2023

Sentence-level Event Detection without Triggers via Prompt Learning and Machine Reading Comprehension

The traditional way of sentence-level event detection involves two impor...
research
08/20/2022

Trigger-free Event Detection via Derangement Reading Comprehension

Event detection (ED), aiming to detect events from texts and categorize ...
research
12/30/2020

DEER: A Data Efficient Language Model for Event Temporal Reasoning

Pretrained language models (LMs) such as BERT, RoBERTa, and ELECTRA are ...
research
10/21/2020

Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction

We study the problem of event extraction from text data, which requires ...
research
12/03/2019

Reading the Manual: Event Extraction as Definition Comprehension

We propose a novel approach to event extraction that supplies models wit...
research
10/23/2019

Relation Module for Non-answerable Prediction on Question Answering

Machine reading comprehension(MRC) has attracted significant amounts of ...

Please sign up or login with your details

Forgot password? Click here to reset