Losing My Composure: Predicting Compositionality Over Time

• URL: http://arxiv.org/abs/2607.11667v1
• Date: Mon, 13 Jul 2026 15:11:58 GMT
• Title: Losing My Composure: Predicting Compositionality Over Time
• Abstract summary: We introduce the Compositionality Trend Prediction task, which is evaluated against a novel dataset of in-context compositionality ratings.<n>Per-decade compositionality ratings allow us to investigate empirically untested hypotheses of generalized trends in compositionality over time.<n>Contrary to the decisive tendency posited in the literature, we find only a small negative trend in compositionality over time in our target compounds.
• Score: 6.53319284661275
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We explore the phenomenon of semantic change of German and English noun compounds, with the objective of investigating and modeling gradual changes of meanings and degrees of compositionality in the past and over time. To do so, we introduce the Compositionality Trend Prediction task, which is evaluated against a novel dataset of in-context compositionality ratings sampled across several decades of diachronic corpora for 23 German and 26 English target compounds, uniquely providing per-decade ratings and corresponding trends over time. These per-decade compositionality ratings allow us to investigate empirically untested hypotheses of generalized trends in compositionality over time, such as the idea that compounds should become less compositional (less transparent) over time. Beyond our empirical observations from the diachronic compositionality annotations, we perform experiments with semantic vector representations of varying complexity, as well as several temporal granularities for training these representations on diachronic data, resulting in about 100 models of each representation type, each covering a different 1--5 decade slice of a diachronic corpus. Contrary to the decisive tendency posited in the literature, we find only a small negative trend in compositionality over time in our target compounds. In our computational experiments, we find that using models trained on narrow time slices of diachronic data (single decades, or incrementally expanding temporal windows) align better with the per-decade compositionality ratings than those trained on an entire half-century window, the latter setting being an analog for the prevalent modeling approach of training representations on an entire half of a corpus' data. Additionally, we find static representations to be competitive with contextual representations in the Compositionality Trend Prediction task.

Related papers

• Learning visual representations for compositional analysis of artworks and photographs [40.190936097282275]
  We compare two parallel paradigms for composition analysis: a human-inspired method grounded in perceptual grouping, and fine-tuned foundation models enabled by recent large-scale compositional datasets.<n>With frozen encoders, the human-inspired method achieves competitive performance while remaining interpretable.<n>When sufficient data enables fine-tuning, large self-supervised models outperform significantly, but at the cost of interpretability and cross-domain generalization.
  arXiv  Detail & Related papers  (2026-08-06T15:11:24Z)
• Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces [26.947702126448203]
  The Platonic Representation Hypothesis posits that learned representations from models trained on different modalities converge to a shared latent structure of the world.<n>We first examine this in a trimodal setting and find that independently pretrained time series, vision, and language encoders exhibit near-orthogonal geometry in the absence of explicit coupling.<n>We then apply post-hoc alignment by training projection heads over frozen encoders using contrastive learning, and analyze the resulting representations with respect to geometry, scaling behavior, and dependence on information density and input modality characteristics.
  arXiv  Detail & Related papers  (2026-02-22T22:39:37Z)
• Compositional Generalisation for Explainable Hate Speech Detection [52.41588643566991]
  Hate speech detection is key to online content moderation, but current models struggle to generalise beyond their training data.<n>We show that even when models are trained with more fine-grained, span-level annotations, they struggle to disentangle the meaning of these labels from the surrounding context.<n>We investigate whether training on a dataset where expressions occur with equal frequency across all contexts can improve generalisation.
  arXiv  Detail & Related papers  (2025-06-04T13:07:36Z)
• Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding [143.5927158318524]
  Temporal grounding is the task of locating a specific segment from an untrimmed video according to a query sentence. We introduce a new Compositional Temporal Grounding task and construct two new dataset splits. We argue that the inherent structured semantics inside the videos and language is the crucial factor to achieve compositional generalization.
  arXiv  Detail & Related papers  (2023-01-22T08:02:23Z)
• Visual Comparison of Language Model Adaptation [55.92129223662381]
  adapters are lightweight alternatives for model adaptation. In this paper, we discuss several design and alternatives for interactive, comparative visual explanation methods. We show that, for instance, an adapter trained on the language debiasing task according to context-0 embeddings introduces a new type of bias.
  arXiv  Detail & Related papers  (2022-08-17T09:25:28Z)
• Assaying Out-Of-Distribution Generalization in Transfer Learning [103.57862972967273]
  We take a unified view of previous work, highlighting message discrepancies that we address empirically. We fine-tune over 31k networks, from nine different architectures in the many- and few-shot setting.
  arXiv  Detail & Related papers  (2022-07-19T12:52:33Z)
• Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning [92.07643510310766]
  Temporal grounding in videos aims to localize one target video segment that semantically corresponds to a given query sentence. We introduce a new Compositional Temporal Grounding task and construct two new dataset splits. We empirically find that they fail to generalize to queries with novel combinations of seen words. We propose a variational cross-graph reasoning framework that explicitly decomposes video and language into multiple structured hierarchies.
  arXiv  Detail & Related papers  (2022-03-24T12:55:23Z)
• Opinions are Made to be Changed: Temporally Adaptive Stance Classification [9.061088449712859]
  We introduce two novel large-scale, longitudinal stance datasets. We evaluate the performance persistence of stance classifiers over time and demonstrate how it decays as the temporal gap between training and testing data increases. We propose and compare several approaches to embedding adaptation and find that the Incremental Temporal Alignment (ITA) model leads to the best results in reducing performance drop over time.
  arXiv  Detail & Related papers  (2021-08-27T19:47:31Z)
• Denoise and Contrast for Category Agnostic Shape Completion [48.66519783934386]
  We present a deep learning model that exploits the power of self-supervision to perform 3D point cloud completion. A denoising pretext task provides the network with the needed local cues, decoupled from the high-level semantics. contrastive learning maximizes the agreement between variants of the same shape with different missing portions.
  arXiv  Detail & Related papers  (2021-03-30T20:33:24Z)

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.