Papers with unsupervised pre-training
Empirical Evaluation of Active Learning Techniques for Neural MT (D19-61)
Copied to clipboard
| Challenge: | Several active learning (AL) algorithms for machine translation (MT) have been well-studied for phrase-based MT. |
| Approach: | They propose to use a phrase-based algorithm to compare different AL methods in a simulated AL framework to demonstrate how unsupervised pre-training and paraphrastic embedding can be used to improve existing AL methods. |
| Outcome: | The proposed method outperforms existing methods in the context of phrase-based MT and is based on a simulated phrase-driven dataset. |
Extractive NarrativeQA with Heuristic Pre-Training (D19-58)
Copied to clipboard
| Challenge: | Automated question answering (QA) from text remains a challenge for humans . a striking gap exists between machine and human performance on NLP tasks . |
| Approach: | They propose a heuristic extractive version of a data set to solve the problem of answer extraction rather than generation. |
| Outcome: | The proposed model outperforms previous models on summary-level QA from full narratives and on the METEOR metric. |
TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for Relation Extraction (RE) still show a high error rate . label errors account for 8% absolute F1 test error, and more than 50% of examples need to be relabeled. |
| Approach: | They validate the most challenging 5K examples using trained annotators and analyze misclassifications on the challenging instances. |
| Outcome: | The proposed methods perform well on the most challenging datasets and improve on the relabeled test set. |
GiBERT: Enhancing BERT with Linguistic Information using a Lightweight Gated Injection Method (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Recent pre-trained language models such as BERT have led to noticeable improvements in semantic similarity detection. |
| Approach: | They propose to explicitly inject linguistic information in the form of word embeddings into any layer of a pre-trained BERT. |
| Outcome: | The proposed method improves on multiple semantic similarity datasets and shows that it is beneficial and currently missing from the original model. |
A Unified Supervised and Unsupervised Dialogue Topic Segmentation Framework Based on Utterance Pair Modeling (2025.naacl-long)
Copied to clipboard
| Challenge: | Unsupervised methods for dialogue topic segmentation are difficult to surpass due to short sentences, serious references and non-standard language. |
| Approach: | They propose a method to divide a dialogue into different topic paragraphs to better understand its structure and content. |
| Outcome: | The proposed method achieves the best results on multiple benchmark datasets across different scenarios. |
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback (2023.emnlp-main)
Copied to clipboard
Katherine Tian, Eric Mitchell, Allan Zhou, Archit Sharma, Rafael Rafailov, Huaxiu Yao, Chelsea Finn, Christopher Manning
| Challenge: | Recent studies have shown that unsupervised pre-training produces large language models whose conditional probabilities are remarkably well-calibrated. |
| Approach: | They propose to use verbalized confidences to extract confidence from large language models with reinforcement learning from human feedback to improve their accuracy. |
| Outcome: | The proposed methods reduce the expected calibration error by 50% for RLHF-LMs such as ChatGPT, GPT-4, and Claude. |
Multilingual Constituency Parsing with Self-Attention and Pre-Training (P19-1)
Copied to clipboard
| Challenge: | a range of pre-training conditions can be used for constituency parsing, but large model sizes make it expensive to train separate models for each language. |
| Approach: | They compare the benefits of no pre-training, fastText, ELMo, and BERT for English . they also find that pre- training is beneficial across all 11 languages tested . |
| Outcome: | The proposed model outperforms fastText, ELMo, and BERT for English . but large model sizes make it expensive to train separate models for each language . |
Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing models require large amounts of image-caption data for pre-training . existing models require expensive data collection and curation . |
| Approach: | They propose to conduct "mask-and-predict" pre-training on text-only and image-only corpora and introduce the object tags detected by an object recognition model as anchor points to bridge two modalities. |
| Outcome: | The proposed approach achieves performance close to a model pre-trained with aligned data, on four English benchmarks. |
End-to-End Training of Neural Retrievers for Open-Domain Question Answering (2021.acl-long)
Copied to clipboard
Devendra Sachan, Mostofa Patwary, Mohammad Shoeybi, Neel Kant, Wei Ping, William L. Hamilton, Bryan Catanzaro
| Challenge: | Recent work on training neural retrievers for open-domain question answering (OpenQA) has employed both supervised and unsupervised methods. |
| Approach: | They propose an approach of unsupervised pre-training with the Inverse Cloze Task and masked salient spans followed by supervised finetuning using question-context pairs. |
| Outcome: | The proposed approach outperforms models like REALM and RAG in retrieval accuracy and answer extraction. |
Calibrating Language Models with Adaptive Temperature Scaling (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models' confidence scores are degraded after fine-tuning with reinforcement learning from human feedback. |
| Approach: | They propose a post-hoc calibration method that predicts a temperature scaling parameter for each token prediction. |
| Outcome: | Adaptive temperature scaling improves calibration by over 10% compared to prior methods . RLHF fine-tuning improves model accuracy, but degradation is not significant . |
VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain (2024.lrec-main)
Copied to clipboard
| Challenge: | Currently, there are no publicly available speech recognition datasets in the medical domain due to privacy restrictions. |
| Approach: | They present a Vietnamese speech recognition dataset in the medical domain comprising 16h of labeled medical speech, 1000h of unlabeled medical and 1200h of general-domain speech. |
| Outcome: | The proposed model outperforms state-of-the-art models from 51.8% to 29.6% WER on test set. |