A Timestep aware Sentence Embedding and Acme Coverage for Brief but Informative Title Generation
The title generation task that summarizes article content in recapitulatory words relies heavily on utilizing the corresponding key context. To generate a title with appropriate information in the content and avoid repetition, we propose a title generation framework with two complementary components in this paper. First, we propose a Timestep aware Sentence Embedding (TSE) mechanism, which updates the sentences’ representations by re-locating the critical words in the corresponding sentence for each decoding step. Then, we present an Acme Coverage (AC) mechanism to solve the repetition problem and preserve the remaining valuable keywords after each decoding step according to the final vocabulary distribution. We conduct comprehensive experiments on various title generation tasks with different backbones, the evaluation scores of ROUGE and METEOR in varying degrees are significantly outperforming most of the existing state-of-the-art approaches. The experimental results demonstrate the effectiveness and generality of our novel generation framework TSE-AC.
Code (1)
Tasks
SentenceSentence EmbeddingSentence-EmbeddingSimilar Papers 제목 키워드 기반
Instance-aware Image and Sentence Matching with Selective Multimodal LSTM
Effective image and sentence matching depends on how to well measure their global visual-semantic similarity. Based on the observation that such a global similarity arises from a complex aggregation of multiple local sim…
Semantic SimilaritySemantic Textual SimilaritySentenceEnabling Efficient and Flexible Interpretability of Data-driven Anomaly Detection in Industrial Processes with AcME-AD
While Machine Learning has become crucial for Industry 4.0, its opaque nature hinders trust and impedes the transformation of valuable insights into actionable decision, a challenge exacerbated in the evolving Industry 5…
Anomaly DetectionThe Disappearance of Timestep Embedding in Modern Time-Dependent Neural Networks
Dynamical systems are often time-varying, whose modeling requires a function that evolves with respect to time. Recent studies such as the neural ordinary differential equation proposed a time-dependent neural network, w…
Image GenerationLearning Cross-Modal Embeddings with Adversarial Networks for Cooking Recipes and Food Images
Food computing is playing an increasingly important role in human daily life, and has found tremendous applications in guiding human behavior towards smart food consumption and healthy lifestyle. An important task under …
Cross-Modal RetrievalNutritionRetrievalTranslation+1Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
As a fundamental backbone for video generation, diffusion models are challenged by low inference speed due to the sequential nature of denoising. Previous methods speed up the models by caching and reusing model outputs …
DenoisingVideo Generation