COMET-M: Reasoning about Multiple Events in Complex Sentences

• URL: http://arxiv.org/abs/2305.14617v2
• Date: Mon, 23 Oct 2023 06:49:57 GMT
• Title: COMET-M: Reasoning about Multiple Events in Complex Sentences
• Authors: Sahithya Ravi, Raymond Ng, Vered Shwartz
• Abstract summary: We propose COMET-M (Multi-Event), an event-centric commonsense model capable of generating commonsense inferences for a target event within a complex sentence. COMET-M builds upon COMET, which excels at generating event-centric inferences for simple sentences, but struggles with the complexity of multi-event sentences prevalent in natural text.
• Score: 14.644677930985816
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding the speaker's intended meaning often involves drawing commonsense inferences to reason about what is not stated explicitly. In multi-event sentences, it requires understanding the relationships between events based on contextual knowledge. We propose COMET-M (Multi-Event), an event-centric commonsense model capable of generating commonsense inferences for a target event within a complex sentence. COMET-M builds upon COMET (Bosselut et al., 2019), which excels at generating event-centric inferences for simple sentences, but struggles with the complexity of multi-event sentences prevalent in natural text. To overcome this limitation, we curate a multi-event inference dataset of 35K human-written inferences. We trained COMET-M on the human-written inferences and also created baselines using automatically labeled examples. Experimental results demonstrate the significant performance improvement of COMET-M over COMET in generating multi-event inferences. Moreover, COMET-M successfully produces distinct inferences for each target event, taking the complete context into consideration. COMET-M holds promise for downstream tasks involving natural text such as coreference resolution, dialogue, and story understanding.

Related papers

• Synergetic Event Understanding: A Collaborative Approach to Cross-Document Event Coreference Resolution with Large Language Models [41.524192769406945]
  Cross-document event coreference resolution (CDECR) involves clustering event mentions across multiple documents that refer to the same real-world events. Existing approaches utilize fine-tuning of small language models (SLMs) to address the compatibility among the contexts of event mentions. We propose a collaborative approach for CDECR, leveraging the capabilities of both a universally capable LLM and a task-specific SLM.
  arXiv  Detail & Related papers  (2024-06-04T09:35:47Z)
• EVIT: Event-Oriented Instruction Tuning for Event Reasoning [18.012724531672813]
  Event reasoning aims to infer events according to certain relations and predict future events. Large language models (LLMs) have made significant advancements in event reasoning owing to their wealth of knowledge and reasoning capabilities. However, smaller instruction-tuned models currently in use do not consistently demonstrate exceptional proficiency in managing these tasks.
  arXiv  Detail & Related papers  (2024-04-18T08:14:53Z)
• Towards Event Extraction from Speech with Contextual Clues [61.164413398231254]
  We introduce the Speech Event Extraction (SpeechEE) task and construct three synthetic training sets and one human-spoken test set. Compared to event extraction from text, SpeechEE poses greater challenges mainly due to complex speech signals that are continuous and have no word boundaries. Our method brings significant improvements on all datasets, achieving a maximum F1 gain of 10.7%.
  arXiv  Detail & Related papers  (2024-01-27T11:07:19Z)
• MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation [104.6065882758648]
  MAVEN-Arg is the first all-in-one dataset supporting event detection, event argument extraction, and event relation extraction. As an EAE benchmark, MAVEN-Arg offers three main advantages: (1) a comprehensive schema covering 162 event types and 612 argument roles, all with expert-written definitions and examples; (2) a large data scale, containing 98,591 events and 290,613 arguments obtained with laborious human annotation; and (3) the exhaustive annotation supporting all task variants of EAE.
  arXiv  Detail & Related papers  (2023-11-15T16:52:14Z)
• Rich Event Modeling for Script Event Prediction [60.67635412135682]
  We propose the Rich Event Prediction (REP) framework for script event prediction. REP contains an event extractor to extract such information from texts. The core component of the predictor is a transformer-based event encoder to flexibly deal with an arbitrary number of arguments.
  arXiv  Detail & Related papers  (2022-12-16T05:17:59Z)
• Multiview Contextual Commonsense Inference: A New Dataset and Task [40.566530682082714]
  CICEROv2 is a dataset consisting of 8,351 instances from 2,379 dialogues. It contains multiple human-written answers for each contextual commonsense inference question. We show that the inferences in CICEROv2 are more semantically diverse than other contextual commonsense inference datasets.
  arXiv  Detail & Related papers  (2022-10-06T13:08:41Z)
• EA$^2$E: Improving Consistency with Event Awareness for Document-Level Argument Extraction [52.43978926985928]
  We introduce the Event-Aware Argument Extraction (EA$2$E) model with augmented context for training and inference. Experiment results on WIKIEVENTS and ACE2005 datasets demonstrate the effectiveness of EA$2$E.
  arXiv  Detail & Related papers  (2022-05-30T04:33:51Z)
• ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning [49.795767003586235]
  We introduce ESTER, a comprehensive machine reading comprehension 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%, 57.8%, and 76.3% for event-based F1, token based F1 and HIT@1 scores respectively.
  arXiv  Detail & Related papers  (2021-04-16T19:59:26Z)
• 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.