Summary of Towards Unsupervised Question Answering System with Multi-level Summarization For Legal Text, by M Manvith Prabhu et al.
Towards Unsupervised Question Answering System with Multi-level Summarization for Legal Text
by M Manvith Prabhu, Haricharana Srinivasa, Anand Kumar M
First submitted to arxiv on: 19 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Computers and Society (cs.CY); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents Team SCaLAR’s contribution to SemEval-2024 Task 5: Legal Argument Reasoning in Civil Procedure. The task involves binary classification of legal texts, which requires a sophisticated approach. To address this challenge, the team proposes an unsupervised method that uses similarity and distance metrics to generate labels. Additionally, they explore multi-level fusion of Legal-Bert embeddings using ensemble features like CNN, GRU, and LSTM. To tackle the lengthiness of legal explanations in the dataset, they introduce T5-based segment-wise summarization, which preserves crucial information and improves model performance. The unsupervised system shows a 20-point increase in macro F1-score on the development set and a 10-point increase on the test set, demonstrating its potential despite its uncomplicated architecture. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using artificial intelligence to help lawyers make better decisions. The researchers developed a new way to analyze complex legal texts without needing human labels. They used special techniques called “similarity and distance” to group similar text together and then combined this with another technique called “Legal-Bert” that helps the AI understand the meaning of the text. To make it easier for the AI to process long legal explanations, they developed a new way to summarize these texts while keeping the important information. This approach improved the AI’s performance and could be useful in many areas where lawyers need help making decisions. |
Keywords
» Artificial intelligence » Bert » Classification » Cnn » F1 score » Lstm » Summarization » T5 » Unsupervised
