Papers with transformer-based classifier
Developing a Production System for Purpose of Call Detection in Business Phone Conversations (2022.naacl-industry)
Copied to clipboard
| Challenge: | a commercial system detects Purpose of Call statements in call transcripts . the model is based on a set of rules and a neural model . |
| Approach: | They propose a system to detect Purpose of Call statements in English business call transcripts in real time. |
| Outcome: | The proposed model achieves 88.6 F1 on average in various types of business calls and has low inference time. |
Detecting LLM-Assisted Cheating on Open-Ended Writing Tasks on Language Proficiency Tests (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been used for open-ended writing tasks . however, there are limitations in detecting LLM-generated samples . |
| Approach: | They propose a framework for training LLM-generated text detectors that can detect LLM generated samples after being copy-typed. |
| Outcome: | The proposed model outperforms the transformer-based classifier on a high-stakes online English proficiency test. |
Active Learning for Corpus Refinement: Cost-Effective Preprocessing to Improve Validity of Applied Quantitative Text Analysis (2026.eacl-srw)
Copied to clipboard
| Challenge: | Quantitative text analysis relies on high-quality corpora, but keyword-based collection often retrieves irrelevant material, undermining validity. |
| Approach: | They propose to use a transformer-based classifier to iteratively refine corpora by excluding irrelevant documents. |
| Outcome: | The proposed method outperforms random sampling and weakly supervised sampling and outperformed random sampling. |
TACO – Twitter Arguments from COnversations (2024.lrec-main)
Copied to clipboard
| Challenge: | Argument mining aims to identify the structural elements of arguments, denoted as information and inference, in online discourses. |
| Approach: | They propose to use Twitter Arguments to identify structural elements of arguments, denoted as information and inference, in a dataset that uses 1,814 tweets and an annotation framework that incorporates definitions from the Cambridge Dictionary to define and identify argument components. |
| Outcome: | The proposed dataset identifies arguments on Twitter and achieves an 85.06% macro F1 score in detecting arguments. |