Papers with pre-training objective
Question Answering Infused Pre-training of General-Purpose Contextualized Representations (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing pretraining objectives for question answering (QA) are not optimized for being immediately useful without fine-tuning. |
| Approach: | They propose a pre-training objective based on question answering (QA) that is based more directly on context. |
| Outcome: | The proposed model matches predictions of a more accurate cross-encoder model on 80 million synthesized QA pairs and achieves large improvements over previous state-of-the-art models on paraphrase detection and fewshot named entity recognition. |
ELMER: A Non-Autoregressive Pre-trained Language Model for Efficient and Effective Text Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for text generation use auto-regressive (AR) methods, but inefficient inference is a problem. |
| Approach: | They propose an efficient and effective PLM to explicitly model the token dependency during NAR text generation. |
| Outcome: | The proposed model outperforms existing models on three text generation tasks while achieving 10 times faster inference speedup. |
CoMave: Contrastive Pre-training with Multi-scale Masking for Attribute Value Extraction (2023.findings-acl)
Copied to clipboard
Xinnan Guo, Wentao Deng, Yongrui Chen, Yang Li, Mengdi Zhou, Guilin Qi, Tianxing Wu, Dong Yang, Liubin Wang, Yong Pan
| Challenge: | Existing methods to extract product features from unstructured text still suffer from problems . e-commerce platforms are focusing on multi-scale values, which can be confusing . |
| Approach: | They propose a pre-training technique to automatically obtain attribute value pairs from product descriptions to aid e-commerce. |
| Outcome: | The proposed method improves on the existing token-level masking strategy and achieves state-of-the-art on four benchmarks. |
Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning (2022.coling-1)
Copied to clipboard
| Challenge: | Multilingual pre-trained language models have shown impressive performance on several downstream tasks for both high-resourced and low-resource languages. |
| Approach: | They propose to apply multilingual adaptive fine-tuning to 17 most-resourced African languages and three other high-resource languages to encourage cross-lingual transfer learning. |
| Outcome: | The proposed approach is competitive to LAFT on individual languages while requiring significantly less disk space. |
PairSpanBERT: An Enhanced Language Model for Bridging Resolution (2023.acl-long)
Copied to clipboard
| Challenge: | bridging resolution is crucial for machine comprehension of discourse entities for various downstream applications. |
| Approach: | They propose a SpanBERT-based pre-trained model specialized for bridging resolution. |
| Outcome: | The proposed model achieves the best results on three evaluation datasets for bridging resolution despite the noise inherent in the automatically generated data . |
DocLLM: A Layout-Aware Generative Language Model for Multimodal Document Understanding (2024.acl-long)
Copied to clipboard
Dongsheng Wang, Natraj Raman, Mathieu Sibue, Zhiqiang Ma, Petr Babkin, Simerjot Kaur, Yulong Pei, Armineh Nourbakhsh, Xiaomo Liu
| Challenge: | Documents with rich layouts are a significant portion of enterprise corpora and document AI is still a challenge. |
| Approach: | They propose a lightweight extension to traditional large language models for reasoning over visual documents that takes into account both textual semantics and spatial layout. |
| Outcome: | The proposed model outperforms existing large language models on 14 out of 16 datasets and generalizes well to 4 out of 5 previously unseen datasets. |
Evaluating Pre-training Objectives for Low-Resource Translation into Morphologically Rich Languages (2022.lrec-1)
Copied to clipboard
| Challenge: | a lack of parallel data is a major limitation for Neural Machine Translation systems, especially for morphologically rich languages. |
| Approach: | They propose to leverage target monolingual data to overcome the lack of parallel data . they introduce a new technique called PT-Inflect to train NMT systems . |
| Outcome: | The proposed techniques outperform NMT systems trained on parallel data on four typologically diverse target languages. |
Pre-Training Curriculum for Multi-Token Prediction in Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Multi-token prediction (MTP) is a pre-training objective for language models . prior work has shown that smaller language models struggle with the MTP objective . |
| Approach: | They propose a curriculum learning strategy that uses multiple prediction heads to predict the next tokens at each prediction step. |
| Outcome: | The proposed curriculum improves performance and output quality while retaining the benefits of self-speculative decoding. |