A Legal Question Answering System Based on BERT

Wang, Chenxi; Luo, Xudong

doi:10.1145/3507548.3507591

Cited by 4 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study [34] suggests utilizing the Milvus vector query engine and BERT-based problematic vector format "a strategy to enhance cognitive query-answering systems" in certain applications. When the threshold level is set at 0.2, the recommended approach has a rate of retrieval of 86% and a discrepancy rate of 84%.…”

Section: Detailed Literaturementioning

confidence: 99%

Deep Learning Based Question Answering System (Survey)

Saeed,

ashraf,

Jhanjhi

2023

Preprint

View full text Add to dashboard Cite

Deep learning-based question answering systems have transformed the discipline of natural language processing (NLP) by automating the extraction of answers from textual data. This survey paper provides a captivating overview of these systems, exploring methodologies, techniques, and architectures such as recurrent neural networks (RNNs), BERT model, and transformer models. Extractive and generative approaches are examined, alongside the challenges of handling complex questions, managing noisy input, and addressing rare or unseen words. This survey serves as a stimulating reference, offering valuable insights to researchers and practitioners, fueling innovation and advancement in question answering systems within NLP.

show abstract

Section: Detailed Literaturementioning

confidence: 99%

Deep Learning Based Question Answering System (Survey)

Saeed,

ashraf,

Jhanjhi

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Under an information-retrieval approach, the search is carried out by identifying the entities of interest (topics, named entities) and then, with the extracted features and score functions, producing a ranking [6]. QA has been recently approached with deep learning techniques such as Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNN) [7] and BERT models [8], obtaining good results.…”

Section: Related Workmentioning

confidence: 99%

Short Answer Detection for Open Questions: A Sequence Labeling Approach with Deep Learning Models

et al. 2022

View full text Add to dashboard Cite

Evaluating the response to open questions is a complex process since it requires prior knowledge of a specific topic and language. The computational challenge is to analyze the text by learning from a set of correct examples to train a model and then predict unseen cases. Thus, we will be able to capture patterns that characterize answers to open questions. In this work, we used a sequence labeling and deep learning approach to detect if a text segment corresponds to the answer to an open question. We focused our efforts on analyzing the general objective of a thesis according to three methodological questions: Q1: What will be done? Q2: Why is it going to be done? Q3: How is it going to be done? First, we use the Beginning-Inside-Outside (BIO) format to label a corpus of targets with the help of two annotators. Subsequently, we adapted four state-of-the-art architectures to analyze the objective: Bidirectional Encoder Representations from Transformers (BERT-BETO) for Spanish, Code Switching Embeddings from Language Model (CS-ELMo), Multitask Neural Network (MTNN), and Bidirectional Long Short-Term Memory (Bi-LSTM). The results of the F-measure for detection of the answers to the three questions indicate that the BERT-BETO and CS-ELMo architecture obtained the best effectivity. The architecture that obtained the best results was BERT-BETO. BERT was the architecture that obtained more accurate results. The result of a detection analysis for Q1, Q2 and Q3 on a non-annotated corpus at the graduate and undergraduate levels is also reported. We found that for detecting the three questions, only the doctoral academic level reached 100%; that is, the doctoral objectives did contain the answer to the three questions.

show abstract