Deep Active Learning for Data Mining from Conflict Text Corpora
Uppsala University（乌普萨拉大学）；Peace Research Institute Oslo (PRIO)（奥斯陆和平研究所（PRIO））
Mihai Croicu
备注：
40 pages, 6 figures. Paper presented at the Using LLMs and Text-as-Data in Political Science Research Workshop at the University of Barcelona, 29 January 2024
High-resolution event data on armed conflict and related processes have revolutionized the study of political contention with datasets like UCDP GED, ACLED etc. However, most of these datasets limit themselves to collecting spatio-temporal (high-resolution) and intensity data. Information on dynamics, such as targets, tactics, purposes etc. are rarely collected owing to the extreme workload of collecting data. However, most datasets rely on a rich corpus of textual data allowing further mining of further information connected to each event. This paper proposes one such approach that is inexpensive and high performance, leveraging active learning - an iterative process of improving a machine learning model based on sequential (guided) human input. Active learning is employed to then step-wise train (fine-tuning) of a large, encoder-only language model adapted for extracting sub-classes of events relating to conflict dynamics. The approach shows performance similar to human (gold-standard) coding while reducing the amount of required human annotation by as much as 99%.
The University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；Microsoft Research（微软研究院）；Army Research Laboratory（陆军研究实验室）
While most topic modeling algorithms model text corpora with unigrams, human interpretation often relies on inherent grouping of terms into phrases. As such, we consider the problem of discovering topical phrases of mixed lengths. Existing work either performs post processing to the inference results of unigram-based topic models, or utilizes complex n-gram-discovery topic models. These methods generally produce low-quality topical phrases or suffer from poor scalability on even moderately-sized datasets. We propose a different approach that is both computationally efficient and effective. Our…
Polish-Japanese Academy of Information Technology（波兰-日本信息技术学院）
The multilingual nature of the world makes translation a crucial requirement today. Parallel dictionaries constructed by humans are a widely-available resource, but they are limited and do not provide enough coverage for good quality translation purposes, due to out-of-vocabulary words and neologisms. This motivates the use of statistical translation systems, which are unfortunately dependent on the quantity and quality of training data. Such has a very limited availability especially for some languages and very narrow text domains. Is this research we present our improvements to Yalign mining…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Google Research（谷歌研究院）；Army Research Laboratory（陆军研究实验室）
As one of the fundamental tasks in text analysis, phrase mining aims at extracting quality phrases from a text corpus. Phrase mining is important in various tasks such as information extraction/retrieval, taxonomy construction, and topic modeling. Most existing methods rely on complex, trained linguistic analyzers, and thus likely have unsatisfactory performance on text corpora of new domains and genres without extra but expensive adaption. Recently, a few data-driven methods have been developed successfully for extraction of phrases from massive domain-specific text. However, none of the stat…
Kyoto University（京都大学）；National Institute of Information and Communications Technology（国立信息与通信技术研究所）
Lectures translation is a case of spoken language translation and there is a lack of publicly available parallel corpora for this purpose. To address this, we examine a language independent framework for parallel corpus mining which is a quick and effective way to mine a parallel corpus from publicly available lectures at Coursera. Our approach determines sentence alignments, relying on machine translation and cosine similarity over continuous-space sentence representations. We also show how to use the resulting corpora in a multistage fine-tuning based domain adaptation for high-quality lectu…
The growing interest in developing corpora of persuasive texts has promoted applications in automated systems, e.g., debating and essay scoring systems; however, there is little prior work mining image persuasiveness from an argumentative perspective. To expand persuasiveness mining into a multi-modal realm, we present a multi-modal dataset, ImageArg, consisting of annotations of image persuasiveness in tweets. The annotations are based on a persuasion taxonomy we developed to explore image functionalities and the means of persuasion. We benchmark image persuasiveness tasks on ImageArg using w…
The automatic extraction of acronyms and their meaning from corpora is an important sub-task of text mining. It can be seen as a special case of string alignment, where a text chunk is aligned with an acronym. Alternative alignments have different cost, and ideally the least costly one should give the correct meaning of the acronym. We show how this approach can be implemented by means of a 3-tape weighted finite-state machine (3-WFSM) which reads a text chunk on tape 1 and an acronym on tape 2, and generates all alternative alignments on tape 3. The 3-WFSM can be automatically generated from …
Stanford University（斯坦福大学）；Harvard Business School（哈佛商学院）；Carnegie Mellon University（卡内基梅隆大学）；University of Southern California（南加利福尼亚大学）
What kind of basic research ideas are more likely to get applied in practice? There is a long line of research investigating patterns of knowledge transfer, but it generally focuses on documents as the unit of analysis and follow their transfer into practice for a specific scientific domain. Here we study translational research at the level of scientific concepts for all scientific fields. We do this through text mining and predictive modeling using three corpora: 38.6 million paper abstracts, 4 million patent documents, and 0.28 million clinical trials. We extract scientific concepts (i.e., p…
Information Sciences Institute, University of Southern California（南加州大学信息科学研究所）；University of Southern California（南加州大学）；Outreach, Inc.（Outreach公司）
Named entity recognition (NER) identifies typed entity mentions in raw text. While the task is well-established, there is no universally used tagset: often, datasets are annotated for use in downstream applications and accordingly only cover a small set of entity types relevant to a particular task. For instance, in the biomedical domain, one corpus might annotate genes, another chemicals, and another diseases---despite the texts in each corpus containing references to all three types of entities. In this paper, we propose a deep structured model to integrate these "partially annotated" datase…
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）；IIIT-Delhi（德里印度理工学院）
Multi-document summarization (MDS) is the task of reflecting key points from any set of documents into a concise text paragraph. In the past, it has been used to aggregate news, tweets, product reviews, etc. from various sources. Owing to no standard definition of the task, we encounter a plethora of datasets with varying levels of overlap and conflict between participating documents. There is also no standard regarding what constitutes summary information in MDS. Adding to the challenge is the fact that new systems report results on a set of chosen datasets, which might not correlate with the…
National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health（美国国立卫生研究院国家医学图书馆国家生物技术信息中心）
Capturing sentence semantics plays a vital role in a range of text mining applications. Despite continuous efforts on the development of related datasets and models in the general domain, both datasets and models are limited in biomedical and clinical domains. The BioCreative/OHNLP organizers have made the first attempt to annotate 1,068 sentence pairs from clinical notes and have called for a community effort to tackle the Semantic Textual Similarity (BioCreative/OHNLP STS) challenge. We developed models using traditional machine learning and deep learning approaches. For the post challenge, …
Automated event detection from news corpora is a crucial task towards mining fast-evolving structured knowledge. As real-world events have different granularities, from the top-level themes to key events and then to event mentions corresponding to concrete actions, there are generally two lines of research: (1) theme detection identifies from a news corpus major themes (e.g., "2019 Hong Kong Protests" vs. "2020 U.S. Presidential Election") that have very distinct semantics; and (2) action extraction extracts from one document mention-level actions (e.g., "the police hit the left arm of the pro…
National University of Singapore（新加坡国立大学）；Koc University（科奇大学）；Rijksuniversiteit Groningen（格罗宁根大学）；Radboud University（拉德堡德大学）；National Institute of Japanese Literature（日本文学研究所）；Birmingham City University（伯明翰城市大学）；Instituto Politécnico Nacional（国立理工学院）；Mersin University（梅尔辛大学）；University of East Anglia（东英吉利大学）；ETH Zürich（苏黎世联邦理工学院）
Despite the importance of understanding causality, corpora addressing causal relations are limited. There is a discrepancy between existing annotation guidelines of event causality and conventional causality corpora that focus more on linguistics. Many guidelines restrict themselves to include only explicit relations or clause-based arguments. Therefore, we propose an annotation schema for event causality that addresses these concerns. We annotated 3,559 event sentences from protest event news with labels on whether it contains causal relations or not. Our corpus is known as the Causal News Co…
Although Natural Language Processing (NLP) research on argument mining has advanced considerably in recent years, most studies draw on corpora of asynchronous and written texts, often produced by individuals. Few published corpora of synchronous, multi-party argumentation are available. The Discussion Tracker corpus, collected in American high school English classes, is an annotated dataset of transcripts of spoken, multi-party argumentation. The corpus consists of 29 multi-party discussions of English literature transcribed from 985 minutes of audio. The transcripts were annotated for three d…
The Linked Open Data practice has led to a significant growth of structured data on the Web in the last decade. Such structured data describe real-world entities in a machine-readable way, and have created an unprecedented opportunity for research in the field of Natural Language Processing. However, there is a lack of studies on how such data can be used, for what kind of tasks, and to what extent they can be useful for these tasks. This work focuses on the e-commerce domain to explore methods of utilising such structured data to create language resources that may be used for product classifi…
DEBISS: a Corpus of Individual, Semi-structured and Spoken Debates
Federal University of Campina Grande (UFCG) - System（坎皮纳格雷联邦大学（UFCG）- 系统）；Computing Campina Grande, Brazil Federal Institute of Paraíba (IFPB) Monteiro, Brazil（坎皮纳格雷计算，巴西帕拉州联邦理工学院（IFPB）蒙特伊罗，巴西）
Vrije Universiteit Brussel（布鲁塞尔自由大学）；Max Planck Institute for Mathematics in the Sciences（马克斯·普朗克数学科学研究所）
News website comment sections are spaces where potentially conflicting opinions and beliefs are voiced. Addressing questions of how to study such cultural and societal conflicts through technological means, the present article critically examines possibilities and limitations of machine-guided exploration and potential facilitation of on-line opinion dynamics. These investigations are guided by a discussion of an experimental observatory for mining and analyzing opinions from climate change-related user comments on news articles from the TheGuardian.com. This observatory combines causal mappin…
The goal of the paper is to quantify the simultaneous competition and cooperation that takes place in organizations. As the concepts seem to be dichotomous opposites at first, the term internal coopetition duality is put forth. Parallels are drawn between coopetitive processes in big multinational corporations (MNCs) and these taking place in universities, also the structural solutions used in both are analyzed. Data mining is used while looking at how specializations inside the university are in competition for better students. We look at the profiles that students have and find natural divis…
Military intelligence is underutilized in the study of civil war violence. Declassified records are hard to acquire and difficult to explore with the standard econometrics toolbox. I investigate a contemporary government database of civilians targeted during the Vietnam War. The data are detailed, with up to 45 attributes recorded for 73,712 individual civilian suspects. I employ an unsupervised machine learning approach of cleaning, variable selection, dimensionality reduction, and clustering. I find support for a simplifying typology of civilian targeting that distinguishes different kinds o…
A potential objective of every financial organization is to retain existing customers and attain new prospective customers for long-term. The economic behaviour of customer and the nature of the organization are controlled by a prescribed form called Know Your Customer (KYC) in manual banking. Depositor customers in some sectors (business of Jewellery/Gold, Arms, Money exchanger etc) are with high risk; whereas in some sectors (Transport Operators, Auto-delear, religious) are with medium risk; and in remaining sectors (Retail, Corporate, Service, Farmer etc) belongs to low risk. Presently, cre…
Socio-economic data mining has a great potential in terms of gaining a better understanding of problems that our economy and society are facing, such as financial instability, shortages of resources, or conflicts. Without large-scale data mining, progress in these areas seems hard or impossible. Therefore, a suitable, distributed data mining infrastructure and research centers should be built in Europe. It also appears appropriate to build a network of Crisis Observatories. They can be imagined as laboratories devoted to the gathering and processing of enormous volumes of data on both natural …
