Hasil Pencarian  ::  Simpan CSV :: Kembali

"This book develops a general coarse-to-fine framework for learning and inference in large statistical models for natural language processing.Coarse-to-fine approaches exploit a sequence of models which introduce complexity gradually. At the top of the sequence is a trivial model in which learning and inference are both cheap. Each subsequent model refines the previous one, until a final, full-complexity model is reached. Applications of this framework to syntactic parsing, speech recognition and machine translation are presented, demonstrating the effectiveness of the approach in terms of accuracy and speed. "

"ABSTRAKBanyaknya pengguna internet di Indonesia berkontribusi pada potensi pertumbuhan Indonesia secara umum terutama dalam sisi ekonomi digital. Pesatnya pertumbuhan ini mendorong pemerintah untuk merencanakan revolusi industri 4.0. Pada praktisnya, landasan dalam membangun sistem yang diperlukan dalam revolusi industri 4.0 adalah teknologi artificial intelligence (AI). Inovasi dalam bidang AI banyak datang dari perusahaan startup. Meskipun pemanfaatan AI membawa banyak manfaat, 60% dari perusahaan belum memanfaatkan teknologi tersebut pada area fungsional seperti layanan chatbot, robot layanan pelanggan, otomasi proses robotik, monitoring media, dan pengamatan sosial. Celah ini perlu disikapi melihat bahwa 89% dari pengguna internet di Indonesia memanfaatkan layanan chatting, dan 87% lebih untuk media sosial. Pemanfaatan AI dapat dilakukan salah satu caranya adalah dengan menggunakan jasa perusahaan yang bergerak di bidang AI, namun pemetaan dari startup yang bergerak di bidang AI belum tersedia. Selain itu, dampak praktis dari penerapan AI di Indonesia perlu untuk dilakukan sebagai motivasi dan juga pengetahuan bagi pihak yang belum menerapkan AI sebagai bagian dari proses bisnis perusahaan. Penelitian ini melakukan pemetaan terhadap perusahaan startup di Indonesia yang bergerak di bidang AI, dan didapatkan 68 perusahaan startup yang terpetakan. Selain itu, penelitian ini juga melakukan identifikasi dampak dari penerapan AI bagi perusahaan dari perspektif startup penyedia layanan dengan melakukan wawancara kepada level-C dan manajer produk perusahaan penyedia layanan, dan mendapatkan bahwa dampak yang terjadi dapat dikategorikan ke dalam delapan aspek, yaitu motivasi, keuntungan, kepentingan, perubahan strategi, tantangan, kepuasan, kepercayaan, dan etika. Rekomendasi yang dapat diberikan kepada perusahaan klien terkait dengan penerapan NLP meliputi otomasi, kolaborasi, pengembangan berlanjut, humanisasi, melihat pasar, melihat peluang, tahu tujuan, siap secara teknis, dan berani mencoba.

---

ABSTRACT

The large number of internet users in Indonesia contributes to Indonesia's growth potential in general, especially in the digital economy. This rapid growth urged the government to plan for the industrial 4.0 revolution. In practice, the basis for building industrial 4.0 system is artificial intelligence (AI) technology. Innovations in the field of AI come from many startup companies. Despite of many benefits obtained from the use of AI, 60% of the companies have not utilized the technology in functional areas such as chatbot services, customer service robots, automation of robotic processes, media monitoring, and social observation. This gap needs to be addressed considering that more than 89% of internet users in Indonesia utilize chat services, and more than 87% of them use it for social media. The use of AI can be done one way is to use the services of companies engaged in AI. However, startup mapping from AI-based startups is not yet available. In addition, the practical impact of implementing AI in Indonesia needs to be done as motivation and knowledge for those who have not implemented AI as part of the company's business processes. This research mapped the startups in Indonesia who are engaged in AI, and obtained 68 mapped startup companies. In addition, this study also evaluates the implementation of AI for companies from the perspective of the implementor by conducting interviews with C-Levels and product managers of the service provider, and found that the impacts can be categorized into eight categories, namely motivation, profit, interest, change in strategy, competition, satisfaction, trust, and ethics. Recommendations is given to companies related to NLP related to automation, collaboration, accepted development, humanization, looking at the market, seeing opportunities, knowing goals, preparing technically, and dare to try.

"

"This book constitutes the refereed proceedings of the 8th International Conference on Advances in Natural Language Processing, JapTAL 2012, Kanazawa, Japan, in October 2012.

The 27 revised full papers and 5 revised short papers presented were carefully reviewed and selected from 42 submissions. The papers are organized in topical sections on machine translation, multilingual issues, resouces, semantic analysis, sentiment analysis, as well as speech and generation."

"This book constitutes the refereed proceedings of the 17th International Conference on Applications of Natural Language to Information Systems, held in Groningen, The Netherlands, in June 2012. The 12 full papers, 24 short papers and 16 poster papers presented in this volume together with a full-paper length invited talks were carefully reviewed and selected from 90 submissions. The rapidly evolving state-of-the-art in NLP and the shifting interest to appcliations targeting document and data collections available on the Web, including an increasing amount of user generated content, is reflected in the contributions to this book. Topics covered are information retrieval, text classification and clustering, summarization, normalization of user generated content, "forensic" NLP, ontologies and natural language, sentiment analysis, question answering and information extraction, terminology and named entity recognition, and NLP tools development."

"This book constitutes the refereed proceedings of the First CCF Conference, NLPCC 2012, held in Beijing, China, during October/November, 2012. The 43 revised full papers presented were carefully reviewed and selected from 151 submissions. The papers are organized in topical sections on applications on language computing, fundamentals on language computing, machine translation and multi-lingual information access, NLP for search, ads and social networks, question answering and web mining."

"Sistem tanya jawab merupakan salah satu tugas dalam domain natural language processing (NLP) yang sederhananya bertugas untuk menjawab pertanyaan sesuai konteks yang pengguna berikan ke sistem tanya jawab tersebut. Sistem tanya jawab berbahasa Indonesia sebenarnya sudah ada, namun masih memiliki performa yang terbilang kurang baik. Penelitian ini bereksperimen untuk mencoba meningkatkan performa dari sistem tanya jawab berbahasa Indonesia dengan memanfaatkan natural language inference (NLI). Eksperimen untuk meningkatkan sistem tanya jawab berbahasa Indonesia, penulis menggunakan dua metode, yaitu: intermediate-task transfer learning dan task recasting sebagai verifikator. Dengan metode intermediate-task transfer learning, performa sistem tanya jawab berbahasa Indonesia meningkat, hingga skor F1-nya naik sekitar 5.69 dibandingkan tanpa menggunakan pemanfaatan NLI sama sekali, dan berhasil mendapatkan skor F1 tertinggi sebesar 85.14, namun, peningkatan performa dengan metode intermediate-task transfer learning cenderung tidak signifikan, kecuali pada beberapa kasus khusus model tertentu. Sedangkan dengan metode task recasting sebagai verifikator dengan parameter tipe filtering dan tipe perubahan format kalimat, performa sistem tanya jawab berbahasa Indonesia cenderung menurun, penurunan performa ini bervariasi signifikansinya. Pada penelitian ini juga dilakukan analisis karakteristik pasangan konteks-pertanyaan-jawaban seperti apa yang bisa dijawab dengan lebih baik oleh sistem tanya jawab dengan memanfaatkan NLI, dan didapatkan kesimpulan bahwa: performa sistem tanya jawab meningkat dibandingkan hasil baseline-nya pada berbagai karakteristik, antara lain: pada tipe pertanyaan apa, dimana, kapan, siapa, bagaimana, dan lainnya; kemudian pada panjang konteks ≤ 100 dan 101 ≤ 150; lalu pada panjang pertanyaan ≤ 5 dan 6 ≤ 10; kemudian pada panjang jawaban golden truth ≤ 5 dan 6 ≤ 10; lalu pada keseluruhan answer type selain law dan time; terakhir pada reasoning type WM, SSR, dan MSR.

---

The question-answering system is one of the tasks within the domain of natural language processing (NLP) that, in simple terms, aims to answer questions based on the context provided by the user to the question-answering system. While there is an existing Indonesian question-answering system, its performance is considered somewhat inadequate. This research conducts experiments to improve the performance of the Indonesian question answering system by utilizing natural language inference (NLI). In order to enhance the Indonesian question-answering system, the author employs two methods: intermediate task transfer learning and task recasting as verifiers. Using the intermediate-task transfer learning method, the performance of the Indonesian question-answering system improves significantly, with an increase of approximately 5.69 in F1 score compared to not utilizing NLI at all, achieving the highest F1 score of 85.14. However, the performance improvement with the intermediate-task transfer learning method tends to be non-significant, except in certain specific cases and particular models. On the other hand, employing the task recasting method as a verifier with filtering parameter type and sentence format change type leads to a decline in the performance of the Indonesian question-answering system, with the significance of this performance decrease varying. Additionally, this research conducts an analysis on the characteristics of context-question-answer pairs that can be better answered by the question-answering system utilizing NLI. The findings conclude that the question-answering system’s performance improves compared to its baseline across various characteristics, including different question types such as what, where, when, who, how, and others. Furthermore, it improves with context lengths ≤ 100 and 101 ≤ 150, question lengths ≤ 5 and 6 ≤ 10, as well as answer lengths (golden truth) ≤ 5 and 6 ≤ 10. Additionally, it performs better in overall answer types excluding law and time, and lastly, in reasoning types WM, SSR, and MSR."