書目名稱Artificial Intelligence and Natural Language影響因子(影響力)學科排名
書目名稱Artificial Intelligence and Natural Language網絡公開度
書目名稱Artificial Intelligence and Natural Language網絡公開度學科排名
書目名稱Artificial Intelligence and Natural Language被引頻次
書目名稱Artificial Intelligence and Natural Language被引頻次學科排名
書目名稱Artificial Intelligence and Natural Language年度引用
書目名稱Artificial Intelligence and Natural Language年度引用學科排名
書目名稱Artificial Intelligence and Natural Language讀者反饋
書目名稱Artificial Intelligence and Natural Language讀者反饋學科排名
作者: AVOW 時間: 2025-3-21 23:05 作者: Congruous 時間: 2025-3-22 01:48 作者: 他一致 時間: 2025-3-22 07:53 作者: 舊石器 時間: 2025-3-22 09:49 作者: 沙文主義 時間: 2025-3-22 16:37 作者: BLAZE 時間: 2025-3-22 18:09
Corpus of Syntactic Co-Occurrences: A Delayed Promisen the Russian language. The paper includes an overview of the corpora collected for CoSyCo creation and the amount of collected combinations. In the paper, we also provide a short evaluation of the gathered information.作者: 不合 時間: 2025-3-22 21:25 作者: 桉樹 時間: 2025-3-23 05:23
Tanmay,Lakshmi,Vijay Kumar Soni,Adarsh Kumaranging from psychology to marketing, but there are very few works of this kind on Russian-speaking samples. We use Latent Dirichlet Allocation on the Facebook status updates to extract interpretable features that we then use to identify Facebook users with certain negative psychological traits (the 作者: fringe 時間: 2025-3-23 05:49
Lecture Notes in Electrical Engineeringeyword-based answer retrieval heuristic. We test two neural network approaches to the near-duplicate question detection task as a first step towards a better answer retrieval method. A convolutional neural network architecture gives promising results on this difficult task.作者: correspondent 時間: 2025-3-23 12:44 作者: 戰(zhàn)勝 時間: 2025-3-23 17:42 作者: 冥界三河 時間: 2025-3-23 18:55 作者: myocardium 時間: 2025-3-23 23:17 作者: 巧辦法 時間: 2025-3-24 05:05
https://doi.org/10.1007/978-3-031-72047-5n text documents into predefined categories called tags, such as person names, quantity expressions, percentage expressions, names of locations, organizations, as well as expression of time, currency and others. Although there is a number of approaches have been proposed for this task in Russian lan作者: 小臼 時間: 2025-3-24 08:30
,Angenehme Emotionen gezielt erm?glichen,as been done in the direction of using this data when working with Russian data. This work describes the first step of a research, attempting to create a coreference resolution system for Russian based on semantic data, concerned with using Wikipedia information for the task. The obtained results ar作者: 不持續(xù)就爆 時間: 2025-3-24 11:28 作者: FAWN 時間: 2025-3-24 16:24
A ‘Pilgrimage of Emotions’: ‘The Duel’n the Russian language. The paper includes an overview of the corpora collected for CoSyCo creation and the amount of collected combinations. In the paper, we also provide a short evaluation of the gathered information.作者: 偏離 時間: 2025-3-24 20:30 作者: artless 時間: 2025-3-25 02:55 作者: Facet-Joints 時間: 2025-3-25 05:56 作者: 講個故事逗他 時間: 2025-3-25 10:40
Andrey Filchenkov,Lidia Pivovarova,Jan ?i?kaIncludes supplementary material: 作者: 持續(xù) 時間: 2025-3-25 14:07
Communications in Computer and Information Sciencehttp://image.papertrans.cn/b/image/162256.jpg作者: MAPLE 時間: 2025-3-25 17:14 作者: 死亡 時間: 2025-3-25 21:59
978-3-319-71745-6Springer International Publishing AG 2018作者: 都相信我的話 時間: 2025-3-26 01:40
Semantic Feature Aggregation for Gender Identification in Russian Facebook Russian. We collect Facebook posts of Russian-speaking users and apply them as a dataset for two topic modelling techniques and a distributional clustering approach. The output of the algorithms is applied as a feature aggregation method in a task of gender classification based on a smaller Faceboo作者: 萬靈丹 時間: 2025-3-26 07:06
Using Linguistic Activity in Social Networks to Predict and Interpret Dark Psychological Traitsanging from psychology to marketing, but there are very few works of this kind on Russian-speaking samples. We use Latent Dirichlet Allocation on the Facebook status updates to extract interpretable features that we then use to identify Facebook users with certain negative psychological traits (the 作者: HAVOC 時間: 2025-3-26 12:13 作者: APNEA 時間: 2025-3-26 14:53
Deep Learning for Acoustic Addressee Detection in Spoken Dialogue Systemsspeech addressed to real humans. In this work, several modalities were analyzed, and acoustic data has been chosen as the main modality by reason of the most flexible usability in modern SDSs. To resolve the problem of addressee detection, deep learning methods such as fully-connected neural network作者: 異端邪說2 時間: 2025-3-26 17:36
Deep Neural Networks in Russian Speech Recognitionts. We propose applying various DNNs in automatic recognition of Russian continuous speech. We used different neural network models such as Convolutional Neural Networks (CNNs), modifications of Long short-term memory?(LSTM), Residual Networks and Recurrent Convolutional Networks (RCNNs). The presen作者: 聽覺 時間: 2025-3-26 23:34
Combined Feature Representation for Emotion Classification from Russian Speechtics that preserve temporal structure of the utterance. On the other hand, utterance-level features represent functionals applied to the low-level descriptors and contain important information about speaker emotional state. Utterance-level features are particularly useful for determining emotion int作者: 逢迎白雪 時間: 2025-3-27 01:25
Active Learning with Adaptive Density Weighted Sampling for Information Extraction from Scientific Pn and result extraction from scientific publications in Russian are considered. We note that annotation of scientific texts for creation of training dataset is very labor insensitive and expensive process. To tackle this problem, we propose methods and tools based on active learning. We describe and作者: ALIBI 時間: 2025-3-27 07:48
Application of a Hybrid Bi-LSTM-CRF Model to the Task of Russian Named Entity Recognitionn text documents into predefined categories called tags, such as person names, quantity expressions, percentage expressions, names of locations, organizations, as well as expression of time, currency and others. Although there is a number of approaches have been proposed for this task in Russian lan作者: 宣稱 時間: 2025-3-27 10:49 作者: 正式通知 時間: 2025-3-27 17:29
Building Wordnet for Russian Language from Ru.Wiktionarymary concern of this study is to describe a procedure of relating words to their meanings throughout Wiktionary pages and establish synonym and hyponym-hypernym relation between specific senses of words. The produced database contains 104696 synsets and is publicly available in alpha version as a py作者: 抱狗不敢前 時間: 2025-3-27 19:58
Corpus of Syntactic Co-Occurrences: A Delayed Promisen the Russian language. The paper includes an overview of the corpora collected for CoSyCo creation and the amount of collected combinations. In the paper, we also provide a short evaluation of the gathered information.作者: 大吃大喝 時間: 2025-3-28 00:51
A Close Look at Russian Morphological Parsers: Which One Is the Best?ain tasks of morphological analysis: lemmatization and POS tagging. The experiments were conducted on three currently available Russian corpora which have qualitative morphological labeling – Russian National Corpus, OpenCorpora, and RU-EVAL (a small corpus created in 2010 to evaluate parsers). As e作者: 外形 時間: 2025-3-28 05:37 作者: 奇怪 時間: 2025-3-28 09:15 作者: 悄悄移動 時間: 2025-3-28 11:13
Endemic Arenaviruses in Latin America,lization to increase the training speed. A fully-connected neural network reaches an average recall of 0.78, a Long Short-Term Memory neural network shows an average recall of 0.65. Advantages and disadvantages of both architectures are provided for the particular task.作者: 固定某物 時間: 2025-3-28 18:05
https://doi.org/10.1007/978-90-368-3041-6vantage of both methods. This paper proposes to obtain low-level feature representation feeding frame-level descriptor sequences to a Long Short-Term Memory (LSTM) network, combine the outcome with the Principal Component Analysis (PCA) representation of utterance-level features, and make the final prediction with a logistic regression classifier.作者: Lumbar-Stenosis 時間: 2025-3-28 22:08 作者: stressors 時間: 2025-3-29 01:13 作者: 泄露 時間: 2025-3-29 07:00
Deep Learning for Acoustic Addressee Detection in Spoken Dialogue Systemslization to increase the training speed. A fully-connected neural network reaches an average recall of 0.78, a Long Short-Term Memory neural network shows an average recall of 0.65. Advantages and disadvantages of both architectures are provided for the particular task.作者: Crumple 時間: 2025-3-29 09:20
Combined Feature Representation for Emotion Classification from Russian Speechvantage of both methods. This paper proposes to obtain low-level feature representation feeding frame-level descriptor sequences to a Long Short-Term Memory (LSTM) network, combine the outcome with the Principal Component Analysis (PCA) representation of utterance-level features, and make the final prediction with a logistic regression classifier.作者: biopsy 時間: 2025-3-29 11:35 作者: 裝入膠囊 時間: 2025-3-29 18:10
Morpheme Level Word Embeddingriments. Firstly, we describe how to build morpheme extractor from prepared vocabularies. Our extractor reached 91% accuracy on the vocabularies of known morpheme segmentation. Secondly we show the way how it can be applied for NLP tasks, and then we discuss our results, pros and cons, and our future work.作者: CAPE 時間: 2025-3-29 21:20 作者: pericardium 時間: 2025-3-30 01:02 作者: Nomadic 時間: 2025-3-30 06:36
Tanmay,Lakshmi,Vijay Kumar Soni,Adarsh KumarFacebook status updates to extract interpretable features that we then use to identify Facebook users with certain negative psychological traits (the so-called Dark Triad: narcissism, psychopathy, and Machiavellianism) and to find the themes that are most important to such individuals.作者: 前面 時間: 2025-3-30 11:05
Lien Goossens,Caroline Braet,Jolien De Coennal Neural Networks (CNNs), modifications of Long short-term memory?(LSTM), Residual Networks and Recurrent Convolutional Networks (RCNNs). The presented model achieved . reducing of word error rate?(WER) compared with Kaldi baseline. Experiments are performed with extra-large vocabulary (more than 30?h) of Russian speech.作者: 用肘 時間: 2025-3-30 16:25
,Angenehme Emotionen gezielt erm?glichen,e a coreference resolution system for Russian based on semantic data, concerned with using Wikipedia information for the task. The obtained results are comparable to ones for English data, which gives reasons to expect their improvement in further steps of the research.作者: 廚師 時間: 2025-3-30 17:53 作者: rheumatism 時間: 2025-3-30 23:22 作者: MIRE 時間: 2025-3-31 03:51
