UCD-CS at TREC 2021 Incident Streams Track

• URL: http://arxiv.org/abs/2112.03737v1
• Date: Tue, 7 Dec 2021 14:47:27 GMT
• Title: UCD-CS at TREC 2021 Incident Streams Track
• Authors: Congcong Wang and David Lillis
• Abstract summary: The TREC Incident Streams (IS) track is a research challenge organised for this purpose. The track asks participating systems to both classify a stream of crisis-related tweets into humanitarian aid related information types. We report on the participation of the University College Dublin School of Computer Science (UCD-CS) in TREC-IS 2021.
• Score: 3.4392739159262145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, the task of mining important information from social media posts during crises has become a focus of research for the purposes of assisting emergency response (ES). The TREC Incident Streams (IS) track is a research challenge organised for this purpose. The track asks participating systems to both classify a stream of crisis-related tweets into humanitarian aid related information types and estimate their importance regarding criticality. The former refers to a multi-label information type classification task and the latter refers to a priority estimation task. In this paper, we report on the participation of the University College Dublin School of Computer Science (UCD-CS) in TREC-IS 2021. We explored a variety of approaches, including simple machine learning algorithms, multi-task learning techniques, text augmentation, and ensemble approaches. The official evaluation results indicate that our runs achieve the highest scores in many metrics. To aid reproducibility, our code is publicly available at https://github.com/wangcongcong123/crisis-mtl.

Related papers

• A Comprehensive Survey on Underwater Image Enhancement Based on Deep Learning [51.7818820745221]
  Underwater image enhancement (UIE) presents a significant challenge within computer vision research. Despite the development of numerous UIE algorithms, a thorough and systematic review is still absent.
  arXiv  Detail & Related papers  (2024-05-30T04:46:40Z)
• SMP Challenge: An Overview and Analysis of Social Media Prediction Challenge [63.311045291016555]
  Social Media Popularity Prediction (SMPP) is a crucial task that involves automatically predicting future popularity values of online posts. This paper summarizes the challenging task, data, and research progress.
  arXiv  Detail & Related papers  (2024-05-17T02:36:14Z)
• Multi-Query Focused Disaster Summarization via Instruction-Based Prompting [3.6199702611839792]
  CrisisFACTS aims to advance disaster summarization based on multi-stream fact-finding. Here, participants are asked to develop systems that can extract key facts from several disaster-related events. This paper describes our method to tackle this challenging task.
  arXiv  Detail & Related papers  (2024-02-14T08:22:58Z)
• Data-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning [85.66907881270785]
  We propose a data curriculum method, namely Data-CUBE, that arranges the orders of all the multi-task data for training. In the task level, we aim to find the optimal task order to minimize the total cross-task interference risk. In the instance level, we measure the difficulty of all instances per task, then divide them into the easy-to-difficult mini-batches for training.
  arXiv  Detail & Related papers  (2024-01-07T18:12:20Z)
• CrisisMatch: Semi-Supervised Few-Shot Learning for Fine-Grained Disaster Tweet Classification [51.58605842457186]
  We present a fine-grained disaster tweet classification model under the semi-supervised, few-shot learning setting. Our model, CrisisMatch, effectively classifies tweets into fine-grained classes of interest using few labeled data and large amounts of unlabeled data.
  arXiv  Detail & Related papers  (2023-10-23T07:01:09Z)
• Enhancing Crisis-Related Tweet Classification with Entity-Masked Language Modeling and Multi-Task Learning [0.30458514384586394]
  We propose a combination of entity-masked language modeling and hierarchical multi-label classification as a multi-task learning problem. We evaluate our method on tweets from the TREC-IS dataset and show an absolute performance gain w.r.t. F1-score of up to 10% for actionable information types.
  arXiv  Detail & Related papers  (2022-11-21T13:54:10Z)
• Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem [46.028180604304985]
  We propose an autoregressive entity linking model, that is trained with two auxiliary tasks, and learns to re-rank generated samples at inference time. We show through ablation studies that each of the two auxiliary tasks increases performance, and that re-ranking is an important factor to the increase.
  arXiv  Detail & Related papers  (2022-04-12T17:55:22Z)
• Transformer-based Multi-task Learning for Disaster Tweet Categorisation [2.9112649816695204]
  Social media has enabled people to circulate information in a timely fashion, thus motivating people to post messages seeking help during crisis situations. These messages can contribute to the situational awareness of emergency responders, who have a need for them to be categorised according to information types. We introduce a transformer-based multi-task learning (MTL) technique for classifying information types and estimating the priority of these messages.
  arXiv  Detail & Related papers  (2021-10-15T11:13:46Z)
• Wizard of Search Engine: Access to Information Through Conversations with Search Engines [58.53420685514819]
  We make efforts to facilitate research on CIS from three aspects. We formulate a pipeline for CIS with six sub-tasks: intent detection (ID), keyphrase extraction (KE), action prediction (AP), query selection (QS), passage selection (PS) and response generation (RG) We release a benchmark dataset, called wizard of search engine (WISE), which allows for comprehensive and in-depth research on all aspects of CIS.
  arXiv  Detail & Related papers  (2021-05-18T06:35:36Z)
• 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)
• An Empirical Methodology for Detecting and Prioritizing Needs during Crisis Events [2.0605537665985687]
  Social media platforms such as Twitter contain vast amount of information about the general public's needs. In this study, we propose two novel methods for two distinct but related needs detection tasks. We evaluated our methods on a set of tweets about the COVID-19 crisis.
  arXiv  Detail & Related papers  (2020-06-02T08:02:29Z)

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.