Search Results for author:
Found 9 papers, 2 papers with code
LexGPT 0.1: pre-trained GPT-J models with Pile of Law
By fine-tuning models with specialized data and without modifying any source code, legal professionals can create custom language models for downstream tasks with minimum effort and technical knowledge.
The Effectiveness of Bidirectional Generative Patent Language Models
Since text generation is bidirectional, the calculation of autocomplete effectiveness can be bidirectional and starts from anywhere in the text.
Evaluating Generative Patent Language Models
The perspective is to measure the ratio of keystrokes that can be saved by autocompletion based on generative patent language models.
Prior Art Search and Reranking for Generated Patent Text
The steps of reranking are: (1) search the most similar text in the training data of GPT-2 by taking a bag-of-word ranking approach (BM25), (2) convert the search results in text format to BERT embeddings, and (3) provide the final result by ranking the BERT embeddings based on their similarities with the patent text generated by GPT-2.
Measuring Patent Claim Generation by Span Relevancy
Specifically, we fine-tune a pre-trained Google BERT model to measure the patent claim spans generated by a fine-tuned OpenAI GPT-2 model.
Patent Claim Generation by Fine-Tuning OpenAI GPT-2
Our contributions include: (1) being the first to generate patent claims by machines and being the first to apply GPT-2 to patent claim generation, (2) providing various experiment results for qualitative analysis and future research, (3) proposing a new sampling approach for text generation, and (4) building an e-mail bot for future researchers to explore the fine-tuned GPT-2 model further.
PatentBERT: Patent Classification with Fine-Tuning a pre-trained BERT Model
In this work we focus on fine-tuning a pre-trained BERT model and applying it to patent classification.
Ranked #1 on
Multi-Label Text Classification
on USPTO-3M
