Next-Generation Academic Search
SEER combines semantic retrieval, task-aware parsing, and explainable AI to revolutionize how you discover research.
Search Results
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova • 2019
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT representations can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications.
Why this matches your search
This paper matches your search for "transformer models for NLP tasks" because it introduces BERT, a transformer-based architecture that achieves state-of-the-art results on multiple NLP benchmarks. The paper specifically addresses question answering and text classification tasks you mentioned.
Attention Is All You Need
Ashish Vaswani, Noam Shazeer, Niki Parmar, et al. • 2017
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a decoder. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train.
Why this matches your search
This foundational paper matches your interest in "transformer architectures" as it introduces the original Transformer model. While focused on machine translation, the architecture has become fundamental to NLP tasks like those you're researching.
SEER's Unique Capabilities
Semantic Understanding
SEER goes beyond keywords to understand research concepts, methodologies, and findings at a deeper level.
Task-Aware Filtering
Find papers relevant to your specific research task, whether it's classification, generation, or QA.
Dataset/Model Search
Search for papers that use specific datasets or model architectures like BERT or GPT-3.
Explainable Matches
Understand why each paper was matched to your query with clear, interpretable explanations.
Dynamic Reranking
Results improve as you provide feedback, learning your preferences over time.
Research Graph
Visualize connections between papers, datasets, and methodologies in your field.
