Temporal Common Sense Acquisition with Minimal Supervision
- URL: http://arxiv.org/abs/2005.04304v1
- Date: Fri, 8 May 2020 22:20:16 GMT
- Title: Temporal Common Sense Acquisition with Minimal Supervision
- Authors: Ben Zhou and Qiang Ning and Daniel Khashabi and Dan Roth
- Abstract summary: This work proposes a novel sequence modeling approach that exploits explicit and implicit mentions of temporal common sense.
Our method is shown to give quality predictions of various dimensions of temporal common sense.
It also produces representations of events for relevant tasks such as duration comparison, parent-child relations, event coreference and temporal QA.
- Score: 77.8308414884754
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Temporal common sense (e.g., duration and frequency of events) is crucial for
understanding natural language. However, its acquisition is challenging, partly
because such information is often not expressed explicitly in text, and human
annotation on such concepts is costly. This work proposes a novel sequence
modeling approach that exploits explicit and implicit mentions of temporal
common sense, extracted from a large corpus, to build TACOLM, a temporal common
sense language model. Our method is shown to give quality predictions of
various dimensions of temporal common sense (on UDST and a newly collected
dataset from RealNews). It also produces representations of events for relevant
tasks such as duration comparison, parent-child relations, event coreference
and temporal QA (on TimeBank, HiEVE and MCTACO) that are better than using the
standard BERT. Thus, it will be an important component of temporal NLP.
Related papers
- Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding [57.62275091656578]
We refer to the complex events composed of many news articles over an extended period as Temporal Complex Event (TCE)
This paper proposes a novel approach using Large Language Models (LLMs) to systematically extract and analyze the event chain within TCE.
arXiv Detail & Related papers (2024-06-04T16:42:17Z) - Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models [58.17315970207874]
We propose a zero-shot method for adapting generalisable visual-textual priors from arbitrary VLM to facilitate moment-text alignment.
Experiments conducted on three VMR benchmark datasets demonstrate the notable performance advantages of our zero-shot algorithm.
arXiv Detail & Related papers (2023-09-01T13:06:50Z) - An Overview Of Temporal Commonsense Reasoning and Acquisition [20.108317515225504]
Temporal commonsense reasoning refers to the ability to understand the typical temporal context of phrases, actions, and events.
Recent research on the performance of large language models suggests that they often take shortcuts in their reasoning and fall prey to simple linguistic traps.
arXiv Detail & Related papers (2023-07-28T01:30:15Z) - Generic Temporal Reasoning with Differential Analysis and Explanation [61.96034987217583]
We introduce a novel task named TODAY that bridges the gap with temporal differential analysis.
TODAY evaluates whether systems can correctly understand the effect of incremental changes.
We show that TODAY's supervision style and explanation annotations can be used in joint learning.
arXiv Detail & Related papers (2022-12-20T17:40:03Z) - ECOLA: Enhanced Temporal Knowledge Embeddings with Contextualized
Language Representations [35.51427298619691]
We study enhancing temporal knowledge embedding with textual data.
We propose Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations (ECOLA)
Experiments show that ECOLA significantly enhances temporal embedding models with up to 287% relative improvements regarding Hits@1 on the link prediction task.
arXiv Detail & Related papers (2022-03-17T20:08:25Z) - Extracting Temporal Event Relation with Syntactic-Guided Temporal Graph
Transformer [17.850316385809617]
We propose a new Temporal Graph Transformer network to explicitly find the connection between two events from a syntactic graph constructed from one or two continuous sentences.
Experiments on MATRES and TB-Dense datasets show that our approach significantly outperforms previous state-of-the-art methods on both end-to-end temporal relation extraction and temporal relation classification.
arXiv Detail & Related papers (2021-04-19T19:00:45Z) - Temporal Reasoning on Implicit Events from Distant Supervision [91.20159064951487]
We propose a novel temporal reasoning dataset that evaluates the degree to which systems understand implicit events.
We find that state-of-the-art models struggle when predicting temporal relationships between implicit and explicit events.
We propose a neuro-symbolic temporal reasoning model, SYMTIME, which exploits distant supervision signals from large-scale text and uses temporal rules to infer end times.
arXiv Detail & Related papers (2020-10-24T03:12:27Z) - Modeling Preconditions in Text with a Crowd-sourced Dataset [17.828175478279654]
This paper introduces PeKo, a crowd-sourced annotation of preconditions between event pairs in newswire.
We also introduce two challenge tasks aimed at modeling preconditions.
Evaluation on both tasks shows that modeling preconditions is challenging even for today's large language models.
arXiv Detail & Related papers (2020-10-06T01:52:34Z) - Paragraph-level Commonsense Transformers with Recurrent Memory [77.4133779538797]
We train a discourse-aware model that incorporates paragraph-level information to generate coherent commonsense inferences from narratives.
Our results show that PARA-COMET outperforms the sentence-level baselines, particularly in generating inferences that are both coherent and novel.
arXiv Detail & Related papers (2020-10-04T05:24:12Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.