Papers with pre-training approach
REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models have achieved great success on Machine Reading Comprehension (MRC) however, the poor support in evidence extraction hinders them from further advancing MRC. |
| Approach: | They propose a REtrieval-based pre-training approach that strengthens evidence extraction during pre-training by inherited downstream MRC tasks. |
| Outcome: | The proposed approach strengthens evidence extraction during pre-training, which is further inherited by downstream tasks. |
Sentence-Level Propaganda Detection in News Articles with Transfer Learning and BERT-BiLSTM-Capsule Model (D19-50)
Copied to clipboard
| Challenge: | a new task is needed to detect propaganda in news articles . the need for communication has increased in online social media platforms . a proposed solution to the problem of sentence-level propaganda classification is ranked 12th . |
| Approach: | They propose to build a binary classifier able to provide corresponding propaganda labels . their solution ranks 12th among 26 teams in the NLP4IF-2019 Shared Task SLC . |
| Outcome: | The proposed model outperforms baseline approach and the winning system on a similar task. |
Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders (2024.acl-long)
Copied to clipboard
| Challenge: | Conversational systems often rely on embedding models for intent classification and intent clustering tasks. |
| Approach: | They propose a toolkit that gives a more holistic view of intent embedding models by considering three tasks– (1) intent classification, (2) intent clustering, and (3) a novel triplet task. |
| Outcome: | The proposed model improves on the linguistic dimensions while affecting performance on downstream task metrics. |
Learning to Generate Questions by Learning to Recover Answer-containing Sentences (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent research has focused on synthetically generating a question from a given context and an annotated answer by training an additional generative model. |
| Approach: | They propose a method that learns to generate contextually rich questions by recovering answer-containing sentences. |
| Outcome: | The proposed approach improves the quality and accuracy of existing models and achieves comparable results to the state-of-the-art on MS MARCO and NewsQA. |
Combining Static and Contextualised Multilingual Embeddings (2022.findings-acl)
Copied to clipboard
| Challenge: | Static embeddings are less expressive than contextual language models, but can be more straightforwardly aligned across multiple languages. |
| Approach: | They extract static embeddings for 40 languages from XLM-R and validate them with cross-lingual word retrieval and then align them using VecMap. |
| Outcome: | The proposed approach improves multilingual representations by leveraging static embeddings and a pre-training code. |
CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation (2025.emnlp-main)
Copied to clipboard
Ziyue Liu, Ruijie Zhang, Zhengyang Wang, Mingsong Yan, Zi Yang, Paul D. Hovland, Bogdan Nicolae, Franck Cappello, Sui Tang, Zheng Zhang
| Challenge: | Large foundation models have become huge, but they consume computational resources in pretraining. |
| Approach: | They propose to replace full-size layers with compute-efficient auto-encoders that enforce low-rank activations throughout training. |
| Outcome: | The proposed method reduces the computing cost by 2pmbtimes and improves training throughput by 1.86pmtime. |
Span Selection Pre-training for Question Answering (2020.acl-main)
Copied to clipboard
Michael Glass, Alfio Gliozzo, Rishav Chakravarti, Anthony Ferritto, Lin Pan, G P Shrivatsa Bhargav, Dinesh Garg, Avi Sil
| Challenge: | Pre-trained BERTs provide large gains across many language understanding tasks, achieving a new state-of-the-art (SOTA). |
| Approach: | They propose a new pre-training task inspired by reading comprehension to better align the pre- training from memorization to understanding. |
| Outcome: | The proposed model outperforms BERT-BASE and BERT LARGE on a new dataset and improves answer prediction F1 by 4 points and supporting fact prediction F1. |
Data Efficient Masked Language Modeling for Vision and Language (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. |
| Approach: | They propose a masking strategy that masks tokens with a 15% probability for text-only data. |
| Outcome: | The proposed masking strategy outperforms the baseline model on a prompt-based probing task designed to elicit image objects. |
Towards Learning (Dis)-Similarity of Source Code from Program Contrasts (2022.acl-long)
Copied to clipboard
| Challenge: | Existing models that focus on identifying functional (dis)similarity of source code get confused when trying to identify functional (Dis)-similarities. |
| Approach: | They propose to pre-train a Transformer model with such automatically generated program contrasts to better identify similar code in the wild and differentiate vulnerable programs from benign ones. |
| Outcome: | The proposed model outperforms existing models in vulnerability and code clone detection tasks even with much less data. |
Causal Document-Grounded Dialogue Pre-training (2023.emnlp-main)
Copied to clipboard
Yingxiu Zhao, Bowen Yu, Bowen Li, Haiyang Yu, Jinyang Li, Chao Wang, Fei Huang, Yongbin Li, Nevin Zhang
| Challenge: | Existing methods for document-grounded dialogue (DocGD) rely on general pre-trained language models without a tailored pre-training approach that explicitly captures causal relationships. |
| Approach: | They propose a causally-complete dataset construction strategy for developing million-scale DocGD pre-training corpora and a perturbation-based strategy to capture causality. |
| Outcome: | The proposed strategy yields significant and consistent improvements in fully-supervised, low-resource, few-shot, and zero-shot settings. |
StructuralLM: Structural Pre-training for Form Understanding (2021.acl-long)
Copied to clipboard
| Challenge: | Existing pre-trained language models focus on text-only representation, neglecting cell-level layout information. |
| Approach: | They propose a pre-training approach to leverage cell and layout information from scanned documents. |
| Outcome: | The proposed model achieves state-of-the-art in various downstream tasks . it uses 2Dposition embeddings to model word-level layout information . |
FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Prior work on multimodal fashion tasks has been limited by the data in individual benchmarks or has leveraged generic vision-and-language pre-training but have not taken advantage of the characteristics of fashion data. |
| Approach: | They propose a fashion-specific pre-training framework based on weakly-supervised triplets constructed from fashion image-text pairs. |
| Outcome: | The proposed framework is based on weakly-supervised triplets constructed from fashion image-text pairs and is competitive on a diverse set of fashion tasks. |
ConPrompt: Pre-training a Language Model with Machine-Generated Data for Implicit Hate Speech Detection (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing pre-trained language models for hate speech detection are not specialized in implicit hate speech. |
| Approach: | They propose a pre-trained language model for implicit hate speech detection that leverages machine-generated data to train the model. |
| Outcome: | The proposed model can be trained on a massive hate speech dataset with positive samples . it can be generalized and reduce identity term bias, the authors show . |
IMU2CLIP: Language-grounded Motion Sensor Translation with Multimodal Contrastive Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to align motion sensors with text and video are limited in their scale and limited in the use of IMU models. |
| Approach: | They propose to project IMU motion sensor recordings into the joint representation space of Contrastive Language-Image Pre-training (CLIP) they introduce several new IMU-based Wearable AI applications such as motion-based media search, or an LM-based multimodal reasoning with motion sensor data. |
| Outcome: | The proposed approach significantly improves downstream performance when fine-tuned for each application, demonstrating its universal usage as a new pre-trained resource. |