SeterusnyaPanduan seterusnya
Pembenaman Perkataan
AI bahasa
PANDUAN AI Bahasa
ELMo (Embeddings from Language Models), introduced by Peters and colleagues at AI2 in 2018, creates contextual word representations from a deep bidirectional language model.
Dengar panduan iniAI-diceritakan · ~2 min
Its task-specific representation combines internal recurrent layers instead of assigning one fixed vector to each word type.
Peters et al. introduce Embeddings from Language Models (ELMo), based on a deep bidirectional LSTM language model trained on the One Billion Word Benchmark. Character convolutions produce word inputs; a forward model predicts the next token and a backward model predicts the previous token. A downstream task forms ELMo by a learned, task-specific weighted combination of internal layers. The paper reports evaluations on six benchmark tasks. Those results describe the paper’s models and experiments, not a general ranking against later systems. The authors analyze layer behavior: lower layers tend to encode syntactic information, while upper layers can carry more context-dependent semantic information; these are reported tendencies, not strict layer guarantees.
Paper evaluation: the ELMo paper reports results on six downstream benchmarks, including question answering and named-entity recognition.
Paper architecture: forward and backward language models read character-CNN word inputs.
Paper method: learned task-specific weights combine representations from the language-model layers.
Illustrative use: compare contextual and static representations on a task with context-dependent word meaning.
To evaluate contextual representations, compare on the intended task and data, with matched training and evaluation conditions. This guide makes no claim that ELMo was universally replaced by a particular later architecture; such comparisons require their own sources and controlled evidence.
Newsletter percuma
Tiga cerita AI yang disahkan setiap pagi hari bekerja, ditulis dalam Bahasa Inggeris biasa. Percuma selamanya, tiada iklan.
Satu e-mel setiap hari bekerja. Berhenti melanggan dalam satu klik. Kami tidak pernah menjual atau berkongsi alamat anda.
Uji diri anda
Maklum balas segera pada setiap jawapan, dan sijil yang boleh dikongsi dengan ID yang boleh disahkan sebaik sahaja anda lulus kursus.
Sokong pendidikan AI percuma. AI Understanding ialah pertubuhan bukan keuntungan 501(c)(3) — tiada iklan, tiada bayaran dinding, selamanya. Buat derma
ELMo (Embeddings from Language Models), introduced by Peters and colleagues at AI2 in 2018, creates contextual word representations from a deep bidirectional language model. Its task-specific representation combines internal recurrent layers instead of assigning one fixed vector to each word type.
ELMo menghasilkan pembenaman kontekstual: vektor untuk perkataan berubah berdasarkan ayat sekeliling, tidak seperti vektor tetap tunggal Word2Vec bagi setiap perkataan.
ELMo dibina di atas LSTM dwiarah dalam yang dilatih sebagai model bahasa, memproses jujukan secara berulang.
ELMo mempelajari pemberat ternormal softmax khusus tugas untuk menggabungkan semua lapisan biLM, membenarkan setiap tugasan menekankan sintaks atau semantik seperti yang diperlukan.
ELMo membina input perkataan daripada CNN peringkat aksara, jadi ia boleh mewakili perkataan yang tidak pernah dilihat semasa latihan.
ELMo diterbitkan pada 2018 oleh Peters et al. di Institut Allen untuk AI (AI2).
Teruskan belajar
Lebih banyak panduan dipilih untuk topik ini
SeterusnyaPanduan seterusnya
Pembenaman Perkataan
AI bahasa