Where's the Learning in Representation Learning for Compositional Semantics and the Case of Thematic Fit

• URL: http://arxiv.org/abs/2208.04749v1
• Date: Tue, 9 Aug 2022 12:37:46 GMT
• Title: Where's the Learning in Representation Learning for Compositional Semantics and the Case of Thematic Fit
• Authors: Mughilan Muthupari, Samrat Halder, Asad Sayeed, Yuval Marton
• Abstract summary: We observe that for certain NLP tasks, such as semantic role prediction or thematic fit estimation, random embeddings perform as well as pretrained embeddings. We find nuanced answers, depending on the task and its relation to the training objective.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Observing that for certain NLP tasks, such as semantic role prediction or thematic fit estimation, random embeddings perform as well as pretrained embeddings, we explore what settings allow for this and examine where most of the learning is encoded: the word embeddings, the semantic role embeddings, or ``the network''. We find nuanced answers, depending on the task and its relation to the training objective. We examine these representation learning aspects in multi-task learning, where role prediction and role-filling are supervised tasks, while several thematic fit tasks are outside the models' direct supervision. We observe a non-monotonous relation between some tasks' quality score and the training data size. In order to better understand this observation, we analyze these results using easier, per-verb versions of these tasks.

Related papers

• Leveraging knowledge distillation for partial multi-task learning from multiple remote sensing datasets [2.1178416840822023]
  Partial multi-task learning where training examples are annotated for one of the target tasks is a promising idea in remote sensing. This paper proposes using knowledge distillation to replace the need of ground truths for the alternate task and enhance the performance of such approach.
  arXiv  Detail & Related papers  (2024-05-24T09:48:50Z)
• Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks [33.98624423578388]
  Auxiliary tasks improve representations learned by deep reinforcement learning agents. We derive a new family of auxiliary tasks based on the successor measure. We show that proto-value networks produce rich features that may be used to obtain performance comparable to established algorithms.
  arXiv  Detail & Related papers  (2023-04-25T04:25:08Z)
• Composite Learning for Robust and Effective Dense Predictions [81.2055761433725]
  Multi-task learning promises better model generalization on a target task by jointly optimizing it with an auxiliary task. We find that jointly training a dense prediction (target) task with a self-supervised (auxiliary) task can consistently improve the performance of the target task, while eliminating the need for labeling auxiliary tasks.
  arXiv  Detail & Related papers  (2022-10-13T17:59:16Z)
• Task Compass: Scaling Multi-task Pre-training with Task Prefix [122.49242976184617]
  Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks. We propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks. Our model can not only serve as the strong foundation backbone for a wide range of tasks but also be feasible as a probing tool for analyzing task relationships.
  arXiv  Detail & Related papers  (2022-10-12T15:02:04Z)
• Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering [58.82325933356066]
  Continual learning aims to train a model incrementally on a sequence of tasks without forgetting previous knowledge. We present a detailed study of how different settings affect performance for Visual Question Answering.
  arXiv  Detail & Related papers  (2022-09-30T19:12:58Z)
• Negation, Coordination, and Quantifiers in Contextualized Language Models [4.46783454797272]
  We explore whether the semantic constraints of function words are learned and how the surrounding context impacts their embeddings. We create suitable datasets, provide new insights into the inner workings of LMs vis-a-vis function words and implement an assisting visual web interface for qualitative analysis.
  arXiv  Detail & Related papers  (2022-09-16T10:01:11Z)
• Saliency-Regularized Deep Multi-Task Learning [7.3810864598379755]
  Multitask learning enforces multiple learning tasks to share knowledge to improve their generalization abilities. Modern deep multitask learning can jointly learn latent features and task sharing, but they are obscure in task relation. This paper proposes a new multitask learning framework that jointly learns latent features and explicit task relations.
  arXiv  Detail & Related papers  (2022-07-03T20:26:44Z)
• On the relationship between disentanglement and multi-task learning [62.997667081978825]
  We take a closer look at the relationship between disentanglement and multi-task learning based on hard parameter sharing. We show that disentanglement appears naturally during the process of multi-task neural network training.
  arXiv  Detail & Related papers  (2021-10-07T14:35:34Z)
• Conditional Meta-Learning of Linear Representations [57.90025697492041]
  Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. In this work we overcome this issue by inferring a conditioning function, mapping the tasks' side information into a representation tailored to the task at hand. We propose a meta-algorithm capable of leveraging this advantage in practice.
  arXiv  Detail & Related papers  (2021-03-30T12:02:14Z)
• Usable Information and Evolution of Optimal Representations During Training [79.38872675793813]
  In particular, we find that semantically meaningful but ultimately irrelevant information is encoded in the early transient dynamics of training. We show these effects on both perceptual decision-making tasks inspired by literature, as well as on standard image classification tasks.
  arXiv  Detail & Related papers  (2020-10-06T03:50:19Z)

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.