Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPoint-of-Interest Type Prediction using Text and Images
نوع نقطة الفائدة التنبؤ باستخدام النص والصور
124
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تنبؤ نوع نقطة الفائدة (POI) هو مهمة استنتاج نوع المكان الذي تم فيه مشاركة مشاركة وسائل التواصل الاجتماعي. إن الاستنتاج من نوع POI مفيد للدراسات في العلوم الاجتماعية الحاسوبية بما في ذلك الاجتماع الاجتماعي، والجيولوجيوسيوس، والجغرافيا الثقافية، ولديه تطبيقات في تكنولوجيات الشبكات الجيولوجية مثل أنظمة التوصية والتصور. الجهود السابقة في التنبؤ بنوع POI التركيز فقط على النص، دون أخذ معلومات مرئية في الاعتبار. ولكن في الواقع، مجموعة متنوعة من الطرائق، فضلا عن علاقاتهم شبهية مع بعضها البعض، شكل التواصل والتفاعلات في وسائل التواصل الاجتماعي. تقدم هذه الورقة دراسة حول التنبؤ بنوع POI باستخدام معلومات متعددة الوسائط من النص والصور المتوفرة في وقت النشر. لهذا الغرض، فإننا نشعر بإثراء البيانات المتاحة حاليا لتنبؤ بنوع POI مع الصور التي ترافق الرسائل النصية. يتم استخراج الأسلوب المقترح لدينا المعلومات ذات الصلة من كل طريقة لالتقاط التفاعلات الفعالة بين النصوص والصورة تحقيق ماكرو F1 من 47.21 من 4 فئات تتفوق بشكل كبير على الطريقة التي من بين الفني للتنبؤ بنوع POI بناء على طرق النص فقط. أخيرا، نقدم تحليلا مفصلا لإلقاء الضوء على التفاعلات عبر الوسائط والقيود المتمثلة في أفضل نموذج أداء لدينا.
Point-of-interest (POI) type prediction is the task of inferring the type of a place from where a social media post was shared. Inferring a POI's type is useful for studies in computational social science including sociolinguistics, geosemiotics, and cultural geography, and has applications in geosocial networking technologies such as recommendation and visualization systems. Prior efforts in POI type prediction focus solely on text, without taking visual information into account. However in reality, the variety of modalities, as well as their semiotic relationships with one another, shape communication and interactions in social media. This paper presents a study on POI type prediction using multimodal information from text and images available at posting time. For that purpose, we enrich a currently available data set for POI type prediction with the images that accompany the text messages. Our proposed method extracts relevant information from each modality to effectively capture interactions between text and image achieving a macro F1 of 47.21 across 8 categories significantly outperforming the state-of-the-art method for POI type prediction based on text-only methods. Finally, we provide a detailed analysis to shed light on cross-modal interactions and the limitations of our best performing model.
References used
https://aclanthology.org/
rate research
Read More
Language models such as GPT-2 have performed well on constructing syntactically sound sentences for text auto-completion tasks. However, such models often require considerable training effort to adapt to specific writing domains (e.g., medical). In t
his paper, we propose an intermediate training strategy to enhance pre-trained language models' performance in the text auto-completion task and fastly adapt them to specific domains. Our strategy includes a novel self-supervised training objective called Next Phrase Prediction (NPP), which encourages a language model to complete the partial query with enriched phrases and eventually improve the model's text auto-completion performance. Preliminary experiments have shown that our approach is able to outperform the baselines in auto-completion for email and academic-writing domains.
Fuzzy logic control is used to connect a photovoltaic system to the electrical grid by using three phase fully
controlled converter (inverter), This controller is going to track the maximum power point and inject the
maximum available power from th
e PV system to the grid by determining the trigger angle that must be
applied on the switches: Linguistic variables are going to be chosen to determine the amount of change in
the trigger angle of the inverter to track the maximum power.
Pronunciation lexicons and prediction models are a key component in several speech synthesis and recognition systems. We know that morphologically related words typically follow a fixed pattern of pronunciation which can be described by language-spec
ific paradigms. In this work we explore how deep recurrent neural networks can be used to automatically learn and exploit this pattern to improve the pronunciation prediction quality of words related by morphological inflection. We propose two novel approaches for supplying morphological information, using the word's morphological class and its lemma, which are typically annotated in standard lexicons. We report improvements across a number of European languages with varying degrees of phonological and morphological complexity, and two language families, with greater improvements for languages where the pronunciation prediction task is inherently more challenging. We also observe that combining bidirectional LSTM networks with attention mechanisms is an effective neural approach for the computational problem considered, across languages. Our approach seems particularly beneficial in the low resource setting, both by itself and in conjunction with transfer learning.
We discussed in this work some predictive methods for time series and it is decomposing time series to its component (trend, Seasonality, cycle, random), Exponential smoothing, ARIMA, then we discussed some combining methods, then we formed a new c
ombine for predict time series which depends on combining exponential smoothing and ARIMA using weighted average with MAPE weights, and applied all methods above on three seasonal time series , first hourly temperature in Aleppo in august 2011 ,second monthly milk production peer cow in Australia from Jan 1962 to Dec 1975,third quartly electricity production in Australia from Mar 1956 to Sep 1994, and compared the results which approved that the suggested method is the best.
With the growing popularity of smart speakers, such as Amazon Alexa, speech is becoming one of the most important modes of human-computer interaction. Automatic speech recognition (ASR) is arguably the most critical component of such systems, as erro
rs in speech recognition propagate to the downstream components and drastically degrade the user experience. A simple and effective way to improve the speech recognition accuracy is to apply automatic post-processor to the recognition result. However, training a post-processor requires parallel corpora created by human annotators, which are expensive and not scalable. To alleviate this problem, we propose Back TranScription (BTS), a denoising-based method that can create such corpora without human labor. Using a raw corpus, BTS corrupts the text using Text-to-Speech (TTS) and Speech-to-Text (STT) systems. Then, a post-processing model can be trained to reconstruct the original text given the corrupted input. Quantitative and qualitative evaluations show that a post-processor trained using our approach is highly effective in fixing non-trivial speech recognition errors such as mishandling foreign words. We present the generated parallel corpus and post-processing platform to make our results publicly available.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
