{"title":"调整人类和计算的一致性评估","authors":"Jia Peng Lim, Hady W. Lauw","doi":"10.1162/coli_a_00518","DOIUrl":null,"url":null,"abstract":"Automated coherence metrics constitute an efficient and popular way to evaluate topic models. Previous works present a mixed picture of their presumed correlation with human judgment. This work proposes a novel sampling approach to mine topic representations at a large-scale while seeking to mitigate bias from sampling, enabling the investigation of widely-used automated coherence metrics via large corpora. Additionally, this article proposes a novel user study design, an amalgamation of different proxy tasks, to derive a finer insight into the human decision-making processes. This design subsumes the purpose of simple rating and outlier-detection user studies. Similar to the sampling approach, the user study conducted is very extensive, comprising forty study participants split into eight different study groups tasked with evaluating their respective set of one hundred topic representations. Usually, when substantiating the use of these metrics, human responses are treated as the golden standard. This article further investigates the reliability of human judgment by flipping the comparison and conducting a novel extended analysis of human response at the group and individual level against a generic corpus. The investigation results show a moderate to good correlation between these metrics and human judgment, especially for generic corpora, and derive further insights into the human perception of coherence. Analysing inter-metric correlations across corpora shows moderate to good correlation amongst these metrics. As these metrics depend on corpus statistics, this article further investigates the topical differences between corpora revealing nuances in applications of these metrics.","PeriodicalId":49089,"journal":{"name":"Computational Linguistics","volume":"64 1","pages":""},"PeriodicalIF":9.3000,"publicationDate":"2024-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Aligning Human and Computational Coherence Evaluations\",\"authors\":\"Jia Peng Lim, Hady W. Lauw\",\"doi\":\"10.1162/coli_a_00518\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Automated coherence metrics constitute an efficient and popular way to evaluate topic models. Previous works present a mixed picture of their presumed correlation with human judgment. This work proposes a novel sampling approach to mine topic representations at a large-scale while seeking to mitigate bias from sampling, enabling the investigation of widely-used automated coherence metrics via large corpora. Additionally, this article proposes a novel user study design, an amalgamation of different proxy tasks, to derive a finer insight into the human decision-making processes. This design subsumes the purpose of simple rating and outlier-detection user studies. Similar to the sampling approach, the user study conducted is very extensive, comprising forty study participants split into eight different study groups tasked with evaluating their respective set of one hundred topic representations. Usually, when substantiating the use of these metrics, human responses are treated as the golden standard. This article further investigates the reliability of human judgment by flipping the comparison and conducting a novel extended analysis of human response at the group and individual level against a generic corpus. The investigation results show a moderate to good correlation between these metrics and human judgment, especially for generic corpora, and derive further insights into the human perception of coherence. Analysing inter-metric correlations across corpora shows moderate to good correlation amongst these metrics. As these metrics depend on corpus statistics, this article further investigates the topical differences between corpora revealing nuances in applications of these metrics.\",\"PeriodicalId\":49089,\"journal\":{\"name\":\"Computational Linguistics\",\"volume\":\"64 1\",\"pages\":\"\"},\"PeriodicalIF\":9.3000,\"publicationDate\":\"2024-05-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computational Linguistics\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1162/coli_a_00518\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computational Linguistics","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1162/coli_a_00518","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Aligning Human and Computational Coherence Evaluations
Automated coherence metrics constitute an efficient and popular way to evaluate topic models. Previous works present a mixed picture of their presumed correlation with human judgment. This work proposes a novel sampling approach to mine topic representations at a large-scale while seeking to mitigate bias from sampling, enabling the investigation of widely-used automated coherence metrics via large corpora. Additionally, this article proposes a novel user study design, an amalgamation of different proxy tasks, to derive a finer insight into the human decision-making processes. This design subsumes the purpose of simple rating and outlier-detection user studies. Similar to the sampling approach, the user study conducted is very extensive, comprising forty study participants split into eight different study groups tasked with evaluating their respective set of one hundred topic representations. Usually, when substantiating the use of these metrics, human responses are treated as the golden standard. This article further investigates the reliability of human judgment by flipping the comparison and conducting a novel extended analysis of human response at the group and individual level against a generic corpus. The investigation results show a moderate to good correlation between these metrics and human judgment, especially for generic corpora, and derive further insights into the human perception of coherence. Analysing inter-metric correlations across corpora shows moderate to good correlation amongst these metrics. As these metrics depend on corpus statistics, this article further investigates the topical differences between corpora revealing nuances in applications of these metrics.
期刊介绍:
Computational Linguistics is the longest-running publication devoted exclusively to the computational and mathematical properties of language and the design and analysis of natural language processing systems. This highly regarded quarterly offers university and industry linguists, computational linguists, artificial intelligence and machine learning investigators, cognitive scientists, speech specialists, and philosophers the latest information about the computational aspects of all the facets of research on language.