Findings (Sydney (N.S.W.)最新文献_第9页

Examining the Use and Non-use of Special Transport Services in Sweden’s Large City-Regions: The Last Resort? 审查瑞典大城市地区特殊交通服务的使用和不使用：最后的选择？

Findings (Sydney (N.S.W.) Pub Date : 2022-12-05 DOI: 10.32866/001c.49873

Jean Ryan, M. Zingmark

引用次数: 0

Effect of Social Vulnerability on Taxi Trip Times during Hurricane Sandy 飓风桑迪期间社会脆弱性对出租车出行时间的影响

Findings (Sydney (N.S.W.) Pub Date : 2022-11-21 DOI: 10.32866/001c.53070

Avipsa Roy, B. Kar

引用次数: 0

An Online Interactive Dashboard to Explore Personal Exposure to Air Pollution 探索个人暴露在空气污染中的在线互动仪表板

Findings (Sydney (N.S.W.) Pub Date : 2022-11-18 DOI: 10.32866/001c.49875

W. Lee, Kayla Schulte, T. Schwanen

引用次数: 0

Exploring Key Correlates of Trail Satisfaction and their Nonlinear Relationships in Suburban Areas 探索郊区步道满意度的关键相关性及其非线性关系

Findings (Sydney (N.S.W.) Pub Date : 2022-11-15 DOI: 10.32866/001c.53105

Jasmine Cao, Chun Yin

引用次数: 0

Generating Synthetic Speech from SpokenVocab for Speech Translation 从SpokenVocab生成合成语音用于语音翻译

Findings (Sydney (N.S.W.) Pub Date : 2022-10-15 DOI: 10.48550/arXiv.2210.08174

Jinming Zhao, Gholamreza Haffar, Ehsan Shareghi

引用次数: 2

Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers 人口统计学因素能改善文本分类吗?重新审视变形金刚时代的人口适应

Findings (Sydney (N.S.W.) Pub Date : 2022-10-13 DOI: 10.48550/arXiv.2210.07362

Chia-Chien Hung, Anne Lauscher, Dirk Hovy, Simone Paolo Ponzetto, Goran Glavavs

{"title":"Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers","authors":"Chia-Chien Hung, Anne Lauscher, Dirk Hovy, Simone Paolo Ponzetto, Goran Glavavs","doi":"10.48550/arXiv.2210.07362","DOIUrl":"https://doi.org/10.48550/arXiv.2210.07362","url":null,"abstract":"Demographic factors (e.g., gender or age) shape our language. Previous work showed that incorporating demographic factors can consistently improve performance for various NLP tasks with traditional NLP models. In this work, we investigate whether these previous findings still hold with state-of-the-art pretrained Transformer-based language models (PLMs). We use three common specialization methods proven effective for incorporating external knowledge into pretrained Transformers (e.g., domain-specific or geographic knowledge). We adapt the language representations for the demographic dimensions of gender and age, using continuous language modeling and dynamic multi-task learning for adaptation, where we couple language modeling objectives with the prediction of demographic classes. Our results, when employing a multilingual PLM, show substantial gains in task performance across four languages (English, German, French, and Danish), which is consistent with the results of previous work. However, controlling for confounding factors – primarily domain and language proficiency of Transformer-based PLMs – shows that downstream performance gains from our demographic adaptation do not actually stem from demographic knowledge. Our results indicate that demographic specialization of PLMs, while holding promise for positive societal impact, still represents an unsolved problem for (modern) NLP.","PeriodicalId":73025,"journal":{"name":"Findings (Sydney (N.S.W.)","volume":"1 1","pages":"1520-1535"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48775945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Joint Reasoning on Hybrid-knowledge sources for Task-Oriented Dialog 面向任务对话的混合知识源联合推理

Findings (Sydney (N.S.W.) Pub Date : 2022-10-13 DOI: 10.48550/arXiv.2210.07295

Mayank Mishra, Danish Contractor, Dinesh Raghu

{"title":"Joint Reasoning on Hybrid-knowledge sources for Task-Oriented Dialog","authors":"Mayank Mishra, Danish Contractor, Dinesh Raghu","doi":"10.48550/arXiv.2210.07295","DOIUrl":"https://doi.org/10.48550/arXiv.2210.07295","url":null,"abstract":"Traditional systems designed for task oriented dialog utilize knowledge present only in structured knowledge sources to generate responses. However, relevant information required to generate responses may also reside in unstructured sources, such as documents. Recent state of the art models such as HyKnow (Gao et al., 2021b) and SEKNOW (Gao et al., 2021a) aimed at overcoming these challenges make limiting assumptions about the knowledge sources. For instance, these systems assume that certain types of information, such as a phone number, is always present in a structured knowledge base (KB) while information about aspects such as entrance ticket prices, would always be available in documents.In this paper, we create a modified version of the MutliWOZ-based dataset prepared by (Gao et al., 2021a) to demonstrate how current methods have significant degradation in performance when strict assumptions about the source of information are removed. Then, in line with recent work exploiting pre-trained language models, we fine-tune a BART (Lewiset al., 2020) based model using prompts (Brown et al., 2020; Sun et al., 2021) for the tasks of querying knowledge sources, as well as, for response generation, without makingassumptions about the information present in each knowledge source. Through a series of experiments, we demonstrate that our model is robust to perturbations to knowledge modality (source of information), and that it can fuse information from structured as well as unstructured knowledge to generate responses.","PeriodicalId":73025,"journal":{"name":"Findings (Sydney (N.S.W.)","volume":"1 1","pages":"1733-1742"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42413600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution ezCoref：统一共参照解析的注释准则

Findings (Sydney (N.S.W.) Pub Date : 2022-10-13 DOI: 10.48550/arXiv.2210.07188

Ankita Gupta, Marzena Karpinska, Wenlong Zhao, Kalpesh Krishna, Jack Merullo, Luke Yeh, Mohit Iyyer, Brendan T. O'Connor

{"title":"ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution","authors":"Ankita Gupta, Marzena Karpinska, Wenlong Zhao, Kalpesh Krishna, Jack Merullo, Luke Yeh, Mohit Iyyer, Brendan T. O'Connor","doi":"10.48550/arXiv.2210.07188","DOIUrl":"https://doi.org/10.48550/arXiv.2210.07188","url":null,"abstract":"Large-scale, high-quality corpora are critical for advancing research in coreference resolution. However, existing datasets vary in their definition of coreferences and have been collected via complex and lengthy guidelines that are curated for linguistic experts. These concerns have sparked a growing interest among researchers to curate a unified set of guidelines suitable for annotators with various backgrounds. In this work, we develop a crowdsourcing-friendly coreference annotation methodology, ezCoref, consisting of an annotation tool and an interactive tutorial. We use ezCoref to re-annotate 240 passages from seven existing English coreference datasets (spanning fiction, news, and multiple other domains) while teaching annotators only cases that are treated similarly across these datasets. Surprisingly, we find that reasonable quality annotations were already achievable (90% agreement between the crowd and expert annotations) even without extensive training. On carefully analyzing the remaining disagreements, we identify the presence of linguistic cases that our annotators unanimously agree upon but lack unified treatments (e.g., generic pronouns, appositives) in existing datasets. We propose the research community should revisit these phenomena when curating future unified annotation guidelines.","PeriodicalId":73025,"journal":{"name":"Findings (Sydney (N.S.W.)","volume":"1 1","pages":"312-330"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45459122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Electric On Demand Transit Expands Network Coverage in Auckland 电动按需运输扩大奥克兰网络覆盖范围

Findings (Sydney (N.S.W.) Pub Date : 2022-10-13 DOI: 10.32866/001c.38773

Benjamin Kaufman, Ainsley Hughes, Elena Pihera, Srishti Lal

引用次数: 0

Best Practices in the Creation and Use of Emotion Lexicons 创造和使用情感词汇的最佳实践

Findings (Sydney (N.S.W.) Pub Date : 2022-10-13 DOI: 10.48550/arXiv.2210.07206

Saif M. Mohammad

引用次数: 9