Papers with deep neural network models
Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Data (2021.findings-emnlp)
Copied to clipboard
| Challenge: | despite considerable progress, most machine reading comprehension tasks lack sufficient training data to fully exploit powerful deep neural network models. |
| Approach: | They propose to use QA data to generate more training data for machine reading comprehension tasks by crowdsourcing . they first collect a large-scale multiple-choice QA dataset for Chinese, ExamQA, and then use incomplete, yet relevant snippets returned by a web search engine as the context for each QA instance. |
| Outcome: | The proposed model improves a Chinese MRC task with +5.1% accuracy and +3.8% exact match. |
Affective and Contextual Embedding for Sarcasm Detection (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods to detect sarcasm from text lack vocal intonation or facial gestures in textual data. |
| Approach: | They propose two deep neural network models for sarcasm detection that extend the architecture of BERT by incorporating both affective and contextual features. |
| Outcome: | The proposed models outperform state-of-the-art models on different datasets with significant margins. |
Medical Code Assignment with Gated Convolution and Note-Code Interaction (2021.findings-acl)
Copied to clipboard
| Challenge: | Medical code assignment from clinical text is a longstanding challenge due to lengthy semantic information in medical notes. |
| Approach: | They propose a method to capture the semantic information of medical notes and a note-code interaction to automate medical code assignment from clinical text. |
| Outcome: | The proposed method outperforms state-of-the-art models on real-world clinical datasets and is on par with light-weighted baselines. |
Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations (2020.coling-main)
Copied to clipboard
| Challenge: | Recent advances in deep neural network models have improved parsing performance on in-domain texts . however, the problem is to improve performance on out-of-domain text data when there is only a small-scale out-domain labeled data. |
| Approach: | They propose to use adversarial learning and fine-tuning BERT to improve contextualized word representations on out-of-domain texts. |
| Outcome: | The proposed models achieve consistent improvement and fine-tune BERT processes boost parsing accuracy by a large margin. |
Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in hardware, modeling, and optimization for deep neural networks have led to improvements in memory and inference efficiency. |
| Approach: | They propose to combine sharpness-aware minimization with various model compression methods to improve model compressibility. |
| Outcome: | Empirically, optimizing for flatter minima leads to greater compressibility of parameters compared to vanilla Adam when fine-tuning BERT models, with little to no loss in accuracy on the GLUE text classification and SQuAD question answering benchmarks. |
Deep JSLC: A Multimodal Corpus Collection for Data-driven Generation of Japanese Sign Language Expressions (L18-1)
Copied to clipboard
| Challenge: | Existing technologies for CG-supported data display are not able to depict all relevant features of a natural signing sequence such as facial expression, spatial references or inter-sign movement. |
| Approach: | They collected a corpus of Japanese Sign Language sentences for deep neural network learning. |
| Outcome: | The proposed model could be used to train language features in Japanese Sign Language (JSL) |
Probing Representations for Document-level Event Extraction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Document-level information extraction tasks require a more comprehensive understanding that often extends to the entire input document. |
| Approach: | They propose to use probing to analyze document-level information extraction representations by embedding probes into a standard dataset. |
| Outcome: | The proposed models improve argument detections but struggle with document length and cross-sentence discourse. |