Strategies to Harness the Transformers' Potential: UNSL at eRisk 2023

• URL: http://arxiv.org/abs/2310.19970v1
• Date: Mon, 30 Oct 2023 19:34:33 GMT
• Title: Strategies to Harness the Transformers' Potential: UNSL at eRisk 2023
• Authors: Horacio Thompson, Leticia Cagnina and Marcelo Errecalde
• Abstract summary: The CLEF eRisk Laboratory explores solutions to different tasks related to risk detection on the Internet. In the 2023 edition, Task 1 consisted of searching for symptoms of depression, the objective of which was to extract user writings according to their relevance to the BDI Questionnaire symptoms. Task 2 was related to the problem of early detection of pathological gambling risks, where the participants had to detect users at risk as quickly as possible. Task 3 consisted of estimating the severity levels of signs of eating disorders.
• Score: 0.9208007322096532
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The CLEF eRisk Laboratory explores solutions to different tasks related to risk detection on the Internet. In the 2023 edition, Task 1 consisted of searching for symptoms of depression, the objective of which was to extract user writings according to their relevance to the BDI Questionnaire symptoms. Task 2 was related to the problem of early detection of pathological gambling risks, where the participants had to detect users at risk as quickly as possible. Finally, Task 3 consisted of estimating the severity levels of signs of eating disorders. Our research group participated in the first two tasks, proposing solutions based on Transformers. For Task 1, we applied different approaches that can be interesting in information retrieval tasks. Two proposals were based on the similarity of contextualized embedding vectors, and the other one was based on prompting, an attractive current technique of machine learning. For Task 2, we proposed three fine-tuned models followed by decision policy according to criteria defined by an early detection framework. One model presented extended vocabulary with important words to the addressed domain. In the last task, we obtained good performances considering the decision-based metrics, ranking-based metrics, and runtime. In this work, we explore different ways to deploy the predictive potential of Transformers in eRisk tasks.

Related papers

• A Time-Aware Approach to Early Detection of Anorexia: UNSL at eRisk 2024 [0.9208007322096532]
  The eRisk laboratory aims to address issues related to early risk detection on the Web. Our research group solved Task 2 by defining a CPI+DMC approach, addressing both objectives independently, and a time-aware approach. We achieved outstanding results for the ERDE50 metric and ranking-based metrics, demonstrating consistency in solving ERD problems.
  arXiv  Detail & Related papers  (2024-10-23T15:30:37Z)
• DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents [49.74065769505137]
  We introduce DISCOVERYWORLD, the first virtual environment for developing and benchmarking an agent's ability to perform complete cycles of novel scientific discovery. It includes 120 different challenge tasks spanning eight topics each with three levels of difficulty and several parametric variations. We find that strong baseline agents, that perform well in prior published environments, struggle on most DISCOVERYWORLD tasks.
  arXiv  Detail & Related papers  (2024-06-10T20:08:44Z)
• Task-Agnostic Detector for Insertion-Based Backdoor Attacks [53.77294614671166]
  We introduce TABDet (Task-Agnostic Backdoor Detector), a pioneering task-agnostic method for backdoor detection. TABDet leverages final layer logits combined with an efficient pooling technique, enabling unified logit representation across three prominent NLP tasks. TABDet can jointly learn from diverse task-specific models, demonstrating superior detection efficacy over traditional task-specific methods.
  arXiv  Detail & Related papers  (2024-03-25T20:12:02Z)
• Assaying on the Robustness of Zero-Shot Machine-Generated Text Detectors [57.7003399760813]
  We explore advanced Large Language Models (LLMs) and their specialized variants, contributing to this field in several ways. We uncover a significant correlation between topics and detection performance. These investigations shed light on the adaptability and robustness of these detection methods across diverse topics.
  arXiv  Detail & Related papers  (2023-12-20T10:53:53Z)
• Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs [58.620269228776294]
  We propose a task-agnostic framework for resolving ambiguity by asking users clarifying questions. We evaluate systems across three NLP applications: question answering, machine translation and natural language inference. We find that intent-sim is robust, demonstrating improvements across a wide range of NLP tasks and LMs.
  arXiv  Detail & Related papers  (2023-11-16T00:18:50Z)
• Early Detection of Depression and Eating Disorders in Spanish: UNSL at MentalRiskES 2023 [1.0878040851637998]
  MentalRiskES is a novel challenge that proposes to solve problems related to early risk detection for the Spanish language. The objective is to detect, as soon as possible, Telegram users who show signs of mental disorders considering different tasks.
  arXiv  Detail & Related papers  (2023-10-30T20:38:31Z)
• Deep Reinforcement Learning with Task-Adaptive Retrieval via Hypernetwork [34.75894450864568]
  Humans rely on their hippocampus to retrieve relevant information from past experiences of relevant tasks. A hippocampus-like module for an agent to incorporate past experiences into established reinforcement learning algorithms presents two challenges. We propose a novel method that utilizes a retrieval network based on task-conditioned hypernetwork.
  arXiv  Detail & Related papers  (2023-06-19T04:48:36Z)
• Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization [101.72755769194677]
  We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph. Our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks. Our experiment results on 2D grid-world and complex web navigation domains show that the proposed method can learn and leverage the common underlying structure of the tasks for faster adaptation to the unseen tasks.
  arXiv  Detail & Related papers  (2022-05-25T10:44:25Z)
• Decision-Theoretic Question Generation for Situated Reference Resolution: An Empirical Study and Computational Model [11.543386846947554]
  We analyzed dialogue data from an interactive study in which participants controlled a virtual robot tasked with organizing a set of tools while engaging in dialogue with a live, remote experimenter. We discovered a number of novel results, including the distribution of question types used to resolve ambiguity and the influence of dialogue-level factors on the reference resolution process.
  arXiv  Detail & Related papers  (2021-10-12T19:23:25Z)
• Multi-task transfer learning for finding actionable information from crisis-related messages on social media [3.4392739159262145]
  The Incident streams (IS) track is a research challenge aimed at finding important information from social media during crises for emergency response purposes. Given a stream of crisis-related tweets, the IS challenge asks a participating system to classify what the types of users' concerns or needs are expressed in each tweet. We describe our multi-task transfer learning approach for this challenge.
  arXiv  Detail & Related papers  (2021-02-26T11:11:33Z)
• Sequential Transfer in Reinforcement Learning with a Generative Model [48.40219742217783]
  We show how to reduce the sample complexity for learning new tasks by transferring knowledge from previously-solved ones. We derive PAC bounds on its sample complexity which clearly demonstrate the benefits of using this kind of prior knowledge. We empirically verify our theoretical findings in simple simulated domains.
  arXiv  Detail & Related papers  (2020-07-01T19:53:35Z)

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.