Monitoring geometrical properties of word embeddings for detecting the emergence of new topics

• URL: http://arxiv.org/abs/2111.03496v1
• Date: Fri, 5 Nov 2021 13:31:56 GMT
• Title: Monitoring geometrical properties of word embeddings for detecting the emergence of new topics
• Abstract summary: We tackle the problem of early detection of slowly emerging new topics. We propose to monitor the behavior of words representation in an embedding space. We show positive results that outperform state-of-the-art methods on two public datasets of press and scientific articles.
• Score: 2.4411595994266797
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Slow emerging topic detection is a task between event detection, where we aggregate behaviors of different words on short period of time, and language evolution, where we monitor their long term evolution. In this work, we tackle the problem of early detection of slowly emerging new topics. To this end, we gather evidence of weak signals at the word level. We propose to monitor the behavior of words representation in an embedding space and use one of its geometrical properties to characterize the emergence of topics. As evaluation is typically hard for this kind of task, we present a framework for quantitative evaluation. We show positive results that outperform state-of-the-art methods on two public datasets of press and scientific articles.

Related papers

• From Noise to Signal: When Outliers Seed New Topics [0.4977593448452647]
  Outliers in dynamic topic modeling are typically treated as noise, yet we show that some can serve as early signals of emerging topics.<n>We introduce a temporal taxonomy of news-document trajectories that defines how documents relate to topic formation over time.
  arXiv  Detail & Related papers  (2026-03-18T23:54:18Z)
• BERTrend: Neural Topic Modeling for Emerging Trends Detection [0.0]
  BERTrend is a novel method for monitoring emerging trends in large, evolving text corpora. It uses neural topic modeling in an online setting to accurately detect and track meaningful weak signals. The method can also be used for retrospective analysis of past events.
  arXiv  Detail & Related papers  (2024-11-08T19:31:19Z)
• Double Mixture: Towards Continual Event Detection from Speech [60.33088725100812]
  Speech event detection is crucial for multimedia retrieval, involving the tagging of both semantic and acoustic events. This paper tackles two primary challenges in speech event detection: the continual integration of new events without forgetting previous ones, and the disentanglement of semantic from acoustic events. We propose a novel method, 'Double Mixture,' which merges speech expertise with robust memory mechanisms to enhance adaptability and prevent forgetting.
  arXiv  Detail & Related papers  (2024-04-20T06:32:00Z)
• Graph-based Clustering for Detecting Semantic Change Across Time and Languages [10.058655884092094]
  We propose a graph-based clustering approach to capture nuanced changes in both high- and low-frequency word senses across time and languages. Our approach substantially surpasses previous approaches in the SemEval 2020 binary classification task across four languages.
  arXiv  Detail & Related papers  (2024-02-01T21:27:19Z)
• 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)
• A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future [6.4105103117533755]
  A taxonomy is first developed to organize different tasks and methodologies. The proposed taxonomy is universal across different tasks, covering object detection, semantic/instance/panoptic segmentation, 3D and video understanding.
  arXiv  Detail & Related papers  (2023-07-18T12:52:49Z)
• Topics in the Haystack: Extracting and Evaluating Topics beyond Coherence [0.0]
  We propose a method that incorporates a deeper understanding of both sentence and document themes. This allows our model to detect latent topics that may include uncommon words or neologisms. We present correlation coefficients with human identification of intruder words and achieve near-human level results at the word-intrusion task.
  arXiv  Detail & Related papers  (2023-03-30T12:24:25Z)
• Spatio-temporal predictive tasks for abnormal event detection in videos [60.02503434201552]
  We propose new constrained pretext tasks to learn object level normality patterns. Our approach consists in learning a mapping between down-scaled visual queries and their corresponding normal appearance and motion characteristics. Experiments on several benchmark datasets demonstrate the effectiveness of our approach to localize and track anomalies.
  arXiv  Detail & Related papers  (2022-10-27T19:45:12Z)
• Fine-Grained Visual Entailment [51.66881737644983]
  We propose an extension of this task, where the goal is to predict the logical relationship of fine-grained knowledge elements within a piece of text to an image. Unlike prior work, our method is inherently explainable and makes logical predictions at different levels of granularity. We evaluate our method on a new dataset of manually annotated knowledge elements and show that our method achieves 68.18% accuracy at this challenging task.
  arXiv  Detail & Related papers  (2022-03-29T16:09:38Z)
• UCPhrase: Unsupervised Context-aware Quality Phrase Tagging [63.86606855524567]
  UCPhrase is a novel unsupervised context-aware quality phrase tagger. We induce high-quality phrase spans as silver labels from consistently co-occurring word sequences. We show that our design is superior to state-of-the-art pre-trained, unsupervised, and distantly supervised methods.
  arXiv  Detail & Related papers  (2021-05-28T19:44:24Z)
• Disambiguatory Signals are Stronger in Word-initial Positions [48.18148856974974]
  We point out the confounds in existing methods for comparing the informativeness of segments early in the word versus later in the word. We find evidence across hundreds of languages that indeed there is a cross-linguistic tendency to front-load information in words.
  arXiv  Detail & Related papers  (2021-02-03T18:19:16Z)
• Be More with Less: Hypergraph Attention Networks for Inductive Text Classification [56.98218530073927]
  Graph neural networks (GNNs) have received increasing attention in the research community and demonstrated their promising results on this canonical task. Despite the success, their performance could be largely jeopardized in practice since they are unable to capture high-order interaction between words. We propose a principled model -- hypergraph attention networks (HyperGAT) which can obtain more expressive power with less computational consumption for text representation learning.
  arXiv  Detail & Related papers  (2020-11-01T00:21:59Z)

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.