Results 1 to 10 of about 4,006 (157)
Understanding Citizen Issues through Reviews: A Step towards Data Informed Planning in Smart Cities
Applied Sciences (Switzerland), 2018 Governments these days are demanding better Smart City technologies in order to connect with citizens and understand their demands. For such governments, much needed information exists on social media where members belonging to diverse groups share ...
Noman Dilawar +2 more
exaly +3 more sources
BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs [PDF]
arXiv, 2017 In this paper we describe our attempt at producing a state-of-the-art Twitter sentiment classifier using Convolutional Neural Networks (CNNs) and Long Short Term Memory (LSTMs) networks. Our system leverages a large amount of unlabeled data to pre-train word embeddings.
exaly +1 more source
SemEval-2015 Task 12: Aspect Based Sentiment Analysis [PDF]
, 2015 Maria Pontiki +4 more
exaly +2 more sources
Multilingual Fine-Grained Named Entity Recognition [PDF]
Computer Science Journal of Moldova, 2023 The “MultiCoNER II Multilingual Complex Named Entity Recognition” task\footnote[1]{\url{https://multiconer.github.io}} within SemEval 2023 competition focuses on identifying complex named entities (NEs), such as the titles of creative works (e.g., songs,
Viorica-Camelia Lupancu, Adrian Iftene
doaj +1 more source
MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection [PDF]
Proceedings of the 15th International Workshop on Semantic
Evaluation (SemEval-2021)", pp. 913-918, 2021, 2021 This paper describes our system for SemEval-2021 Task 5 on Toxic Spans Detection. We developed ensemble models using BERT-based neural architectures and post-processing to combine tokens into spans. We evaluated several pre-trained language models using various ensemble techniques for toxic span identification and achieved sizable improvements over our
arxiv +1 more source
Zhestyatsky at SemEval-2021 Task 2: ReLU over Cosine Similarity for BERT Fine-tuning [PDF]
Proceedings of the 15th International Workshop on Semantic
Evaluation (SemEval-2021), pp. 163-168, 2021, 2021 This paper presents our contribution to SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation (MCL-WiC). Our experiments cover English (EN-EN) sub-track from the multilingual setting of the task. We experiment with several pre-trained language models and investigate an impact of different top-layers on fine-tuning.
arxiv +1 more source
Improving Semantic Dependency Parsing with Higher-Order Information Encoded by Graph Neural Networks
Applied Sciences, 2022 Higher-order information brings significant accuracy gains in semantic dependency parsing. However, modeling higher-order information is non-trivial. Graph neural networks (GNNs) have been demonstrated to be an effective tool for encoding higher-order ...
Bin Li +4 more
doaj +1 more source
TWE‐WSD: An effective topical word embedding based word sense disambiguation
CAAI Transactions on Intelligence Technology, 2021 Word embedding has been widely used in word sense disambiguation (WSD) and many other tasks in recent years for it can well represent the semantics of words.
Lianyin Jia +5 more
doaj +1 more source
A survey of consumer health question answering systems
AI Magazine, Volume 44, Issue 4, Page 482-507, Winter 2023., 2023 Abstract Consumers are increasingly using the web to find answers to their health‐related queries. Unfortunately, they often struggle with formulating the questions, further compounded by the burden of having to traverse long documents returned by the search engine to look for reliable answers. To ease these burdens for users, automated consumer health
Anuradha Welivita, Pearl Pu
wiley +1 more source