An Empirical Study on Learning and Improving the Search Objective for Unsupervised Paraphrasing

• URL: http://arxiv.org/abs/2203.12106v1
• Date: Wed, 23 Mar 2022 00:30:28 GMT
• Title: An Empirical Study on Learning and Improving the Search Objective for Unsupervised Paraphrasing
• Abstract summary: We study the problem of smoothing the noise in the search objective by learning to model the search dynamics. Then, the learned model is combined with the original objective function to guide the search in a bootstrapping fashion. Experimental results show that the learned models combined with the original search objective can indeed provide a smoothing effect.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Research in unsupervised text generation has been gaining attention over the years. One recent approach is local search towards a heuristically defined objective, which specifies language fluency, semantic meanings, and other task-specific attributes. Search in the sentence space is realized by word-level edit operations including insertion, replacement, and deletion. However, such objective function is manually designed with multiple components. Although previous work has shown maximizing this objective yields good performance in terms of true measure of success (i.e. BLEU and iBLEU), the objective landscape is considered to be non-smooth with significant noises, posing challenges for optimization. In this dissertation, we address the research problem of smoothing the noise in the heuristic search objective by learning to model the search dynamics. Then, the learned model is combined with the original objective function to guide the search in a bootstrapping fashion. Experimental results show that the learned models combined with the original search objective can indeed provide a smoothing effect, improving the search performance by a small margin.

Related papers

• Rethinking Layer Redundancy in Large Language Models: Calibration Objectives and Search for Depth Pruning [4.422051502416615]
  We show that different objectives yield qualitatively different redundant layers, and that perplexity and downstream accuracy rankings do not consistently align.<n>Under a fixed objective, however, search algorithms tend to produce similar solutions.
  arXiv  Detail & Related papers  (2026-04-27T19:25:28Z)
• SEM: Reinforcement Learning for Search-Efficient Large Language Models [26.075903427834838]
  Large Language Models (LLMs) have demonstrated their capabilities not only in reasoning but also in invoking external tools.<n>Existing reinforcement learning approaches often lead to redundant search behaviors, resulting in inefficiencies and over-cost.<n>We propose SEM, a novel post-training reinforcement learning framework that explicitly trains LLMs to optimize search usage.
  arXiv  Detail & Related papers  (2025-05-12T09:45:40Z)
• Likelihood as a Performance Gauge for Retrieval-Augmented Generation [78.28197013467157]
  We show that likelihoods serve as an effective gauge for language model performance. We propose two methods that use question likelihood as a gauge for selecting and constructing prompts that lead to better performance.
  arXiv  Detail & Related papers  (2024-11-12T13:14:09Z)
• Does the Order of Fine-tuning Matter and Why? [11.975836356680855]
  We study the effect of fine-tuning multiple intermediate tasks and their ordering on target task performance. Experimental results show that there is an impact of task ordering on target task performance by up to 6% of performance gain and up to 4% of performance loss.
  arXiv  Detail & Related papers  (2024-10-03T19:07:14Z)
• Semantic-Based Active Perception for Humanoid Visual Tasks with Foveal Sensors [49.99728312519117]
  The aim of this work is to establish how accurately a recent semantic-based active perception model is able to complete visual tasks that are regularly performed by humans. This model exploits the ability of current object detectors to localize and classify a large number of object classes and to update a semantic description of a scene across multiple fixations. In the task of scene exploration, the semantic-based method demonstrates superior performance compared to the traditional saliency-based model.
  arXiv  Detail & Related papers  (2024-04-16T18:15:57Z)
• Beyond Semantics: Learning a Behavior Augmented Relevance Model with Self-supervised Learning [25.356999988217325]
  Relevance modeling aims to locate desirable items for corresponding queries. auxiliary query-item interactions extracted from user historical behavior data could provide hints to reveal users' search intents further. Our model builds multi-level co-attention for distilling coarse-grained and fine-grained semantic representations from both neighbor and target views.
  arXiv  Detail & Related papers  (2023-08-10T06:52:53Z)
• Cycle Consistency Driven Object Discovery [75.60399804639403]
  We introduce a method that explicitly optimize the constraint that each object in a scene should be associated with a distinct slot. By integrating these consistency objectives into various existing slot-based object-centric methods, we showcase substantial improvements in object-discovery performance. Our results suggest that the proposed approach not only improves object discovery, but also provides richer features for downstream tasks.
  arXiv  Detail & Related papers  (2023-06-03T21:49:06Z)
• Visualizing the Relationship Between Encoded Linguistic Information and Task Performance [53.223789395577796]
  We study the dynamic relationship between the encoded linguistic information and task performance from the viewpoint of Pareto Optimality. We conduct experiments on two popular NLP tasks, i.e., machine translation and language modeling, and investigate the relationship between several kinds of linguistic information and task performances. Our empirical findings suggest that some syntactic information is helpful for NLP tasks whereas encoding more syntactic information does not necessarily lead to better performance.
  arXiv  Detail & Related papers  (2022-03-29T19:03:10Z)
• Efficient Relation-aware Scoring Function Search for Knowledge Graph Embedding [37.24099392064309]
  AutoML techniques have been introduced into knowledge graphs to design task-aware scoring functions. But the effectiveness of searched scoring functions is still not as good as desired. We propose to encode the space as a supernet and propose an efficient alternative minimization algorithm to search through the supernet in a one-shot manner.
  arXiv  Detail & Related papers  (2021-04-22T06:05:13Z)
• Inverse Bayesian Optimization: Learning Human Search Strategies in a Sequential Optimization Task [0.10499611180329801]
  In this paper, we explore the inverse problem of Bayesian optimization. We estimate the agent's latent acquisition function based on observed search paths. We illustrate our methods by analyzing human behavior from an experiment.
  arXiv  Detail & Related papers  (2021-04-16T15:40:34Z)
• Neural Architecture Search From Fr\'echet Task Distance [50.9995960884133]
  We show how the distance between a target task and each task in a given set of baseline tasks can be used to reduce the neural architecture search space for the target task. The complexity reduction in search space for task-specific architectures is achieved by building on the optimized architectures for similar tasks instead of doing a full search without using this side information.
  arXiv  Detail & Related papers  (2021-03-23T20:43:31Z)
• Unsupervised Text Generation by Learning from Search [86.51619839836331]
  TGLS is a novel framework to unsupervised Text Generation by Learning. We demonstrate the effectiveness of TGLS on two real-world natural language generation tasks, paraphrase generation and text formalization.
  arXiv  Detail & Related papers  (2020-07-09T04:34:48Z)
• Words aren't enough, their order matters: On the Robustness of Grounding Visual Referring Expressions [87.33156149634392]
  We critically examine RefCOg, a standard benchmark for visual referring expression recognition. We show that 83.7% of test instances do not require reasoning on linguistic structure. We propose two methods, one based on contrastive learning and the other based on multi-task learning, to increase the robustness of ViLBERT.
  arXiv  Detail & Related papers  (2020-05-04T17:09:15Z)

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.