Narrative-UFET: Narrative Generation for Ultra-Fine Entity Typing

• URL: http://arxiv.org/abs/2606.27598v1
• Date: Thu, 25 Jun 2026 23:04:05 GMT
• Title: Narrative-UFET: Narrative Generation for Ultra-Fine Entity Typing
• Abstract summary: We present Narrative-UFET, a controlled extension of ultra-fine entity typing.<n>Each entity mention is paired with an automatically generated short, coherent narrative.<n>We show that narrative context yields consistent improvements on long-tail types over sentence-level baselines.
• Score: 5.212422366231854
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ultra-fine entity typing (UFET) assigns highly specific types to entity mentions, but current approaches struggle with types in the long tail. We hypothesize that a key limitation is the reliance on sentence-level context, since disambiguating evidence is often spread across multiple sentences. Testing this has been difficult because all existing UFET resources are sentence-level. We present Narrative-UFET, a controlled extension of UFET in which each entity mention is paired with an automatically generated short, coherent narrative. Synthesizing narratives lets us isolate the effect of specific discourse properties. We experiment with two paired variants: one in which the entity's type is held constant across the narrative (Maintain) and one in which it shifts (Change). We show that narrative context yields consistent improvements on long-tail types over sentence-level baselines, with the Change variant providing the stronger signal. A comparison against naturally occurring contexts shows that synthetic narratives yield stronger gains, indicating that controlled discourse construction can surface signals that real text leaves implicit. Substantial room for improvement remains, suggesting open directions in both discourse modeling and narrative construction.

Related papers

• NOAH: Benchmarking Narrative Prior driven Hallucination and Omission in Video Large Language Models [8.6767620170781]
  Video large language models (Video LLMs) have recently achieved strong performance on tasks such as captioning, summarization, and question answering.<n>Many models and training methods explicitly encourage continuity across events to enhance narrative coherence.<n>We identify this bias, which we call narrative prior, as a key driver of two errors: hallucinations, where non-existent events are introduced or existing ones are misinterpreted, and omissions, where factual events are suppressed because they are misaligned with surrounding context.
  arXiv  Detail & Related papers  (2025-11-09T17:41:11Z)
• Narrative Shift Detection: A Hybrid Approach of Dynamic Topic Models and Large Language Models [0.4649452333875421]
  We propose a combination of the language understanding capabilities of Large Language Models with the large scale applicability of topic models to dynamically model narrative shifts across time.<n>We employ our pipeline on a corpus of The Wall Street Journal news paper articles from 2009 to 2023.
  arXiv  Detail & Related papers  (2025-06-25T09:25:15Z)
• DiscoSum: Discourse-aware News Summarization [79.4884227574627]
  We introduce a novel approach to integrating discourse structure into summarization processes.<n>We present a novel summarization dataset where news articles are summarized multiple times in different ways across different social media platforms.<n>We develop a novel news discourse schema to describe summarization structures and a novel algorithm, DiscoSum, which employs beam search technique for structure-aware summarization.
  arXiv  Detail & Related papers  (2025-06-07T22:00:30Z)
• Neural models for Factual Inconsistency Classification with Explanations [17.214921274113284]
  We leverage existing work in linguistics to define five types of factual inconsistencies. We train neural models to predict inconsistency type with explanations, given a (claim, context) sentence pair. Our proposed methods provide a weighted F1 of 87% for inconsistency type classification across the five classes.
  arXiv  Detail & Related papers  (2023-06-15T06:06:50Z)
• Generating Coherent Narratives by Learning Dynamic and Discrete Entity States with a Contrastive Framework [68.1678127433077]
  We extend the Transformer model to dynamically conduct entity state updates and sentence realization for narrative generation. Experiments on two narrative datasets show that our model can generate more coherent and diverse narratives than strong baselines.
  arXiv  Detail & Related papers  (2022-08-08T09:02:19Z)
• Contextualized Semantic Distance between Highly Overlapped Texts [85.1541170468617]
  Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation. This paper aims to address the issue with a mask-and-predict strategy. We take the words in the longest common sequence as neighboring words and use masked language modeling (MLM) to predict the distributions on their positions. Experiments on Semantic Textual Similarity show NDD to be more sensitive to various semantic differences, especially on highly overlapped paired texts.
  arXiv  Detail & Related papers  (2021-10-04T03:59:15Z)
• Narrative Incoherence Detection [76.43894977558811]
  We propose the task of narrative incoherence detection as a new arena for inter-sentential semantic understanding. Given a multi-sentence narrative, decide whether there exist any semantic discrepancies in the narrative flow.
  arXiv  Detail & Related papers  (2020-12-21T07:18:08Z)
• 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)
• Temporal Embeddings and Transformer Models for Narrative Text Understanding [72.88083067388155]
  We present two approaches to narrative text understanding for character relationship modelling. The temporal evolution of these relations is described by dynamic word embeddings, that are designed to learn semantic changes over time. A supervised learning approach based on the state-of-the-art transformer model BERT is used instead to detect static relations between characters.
  arXiv  Detail & Related papers  (2020-03-19T14:23:12Z)

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.