Papers with PE
Systematic Analysis for Pretrained Language Model Priming for Parameter-Efficient Fine-tuning (2024.naacl-srw)
Copied to clipboard
| Challenge: | Parameter-efficient (PE) methods for adapting pre-trained language models to downstream tasks are still lacking in many cases. |
| Approach: | They propose a general PE priming framework to enhance few-shot adaptation and generalization ability of PE methods. |
| Outcome: | The proposed framework reveals that the best priming strategy facilitates adaptation to target tasks. |
MMPE: A Multi-Modal Interface using Handwriting, Touch Reordering, and Speech Commands for Post-Editing Machine Translation (2020.acl-demos)
Copied to clipboard
Nico Herbig, Santanu Pal, Tim Düwel, Kalliopi Meladaki, Mahsa Monshizadeh, Vladislav Hnatovskiy, Antonio Krüger, Josef van Genabith
| Challenge: | a shift from traditional translation to post-editing (PE) of machine-translated text can save time and reduce errors, but it also affects the design of translation interfaces. |
| Approach: | They propose a prototype that combines traditional input modes with pen, touch, and speech modalities for post-editing of machine-translated (MT) they propose to use these modalités to cross out or hand-write new text, drag and drop words for reordering, or use spoken commands to update the text in place. |
| Outcome: | The proposed interfaces can be used to cross out or hand-write new text, drag and drop words for reordering, or use spoken commands to update the text in place. |
Sample Design Engineering: An Empirical Study on Designing Better Fine-Tuning Samples for Information Extraction with LLMs (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Prompt Engineering (PE) is renowned for improving IE performance through prompt modifications, but the realm of sample design for downstream fine-tuning remains unexplored. |
| Approach: | They propose a methodical approach to enhancing LLMs’ post-tuning performance by refining input, output, and reasoning designs. |
| Outcome: | The proposed approach outperforms heuristic design strategies on three complex IE tasks with four additional LLMs. |
Exploring the Potential of ChatGPT on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relations (2024.findings-eacl)
Copied to clipboard
| Challenge: | Recent studies have demonstrated ChatGPT's remarkable few-shot, even zero-shot learning abilities when compared to other models. |
| Approach: | They quantitatively evaluate the performance of ChatGPT on inter-sentential relations such as temporal relations, causal relations, and discourse relations. |
| Outcome: | The proposed model performs well on temporal relations, causal relations, and discourse relations. |
PE-QAT: Parameter-Efficient Quantization-Aware Training for Large Language Models (2026.acl-srw)
Copied to clipboard
| Challenge: | Quantization Aware Training (QAT) is expensive to train and unscalable to large models. |
| Approach: | They propose a parameter-efficient framework targeting per-channel 4-bit weight-activation quantization of large language models. |
| Outcome: | The proposed framework preserves accuracy within 0.11 percentage points of the full-precision baseline on Llama-2-7B zero-shot tasks while training only 1.26% of total parameters. |
DecBERT: Enhancing the Language Understanding of BERT with Causal Attention Masks (2022.findings-naacl)
Copied to clipboard
| Challenge: | Experimental results show that Transformer Encoder model can't automatically capture word order, so explicit position embeddings are required to be fed into the target model. |
| Approach: | They propose a Transformer-based language model DecBERT that uses a causal attention mask to capture word order. |
| Outcome: | The proposed model improves on the GLUE language understanding benchmark and accelerates the pre-training process. |
Self-Attention with Cross-Lingual Position Representation (2020.acl-main)
Copied to clipboard
| Challenge: | Position encoding (PE) is used to preserve word order information for natural language processing tasks, generating fixed position indices for input sequences. |
| Approach: | They propose to augment SANs with cross-lingual position representations to model bilingually aware latent structure for the input sentence. |
| Outcome: | The proposed model significantly improves translation quality over baselines on EnglishGerman, JapaneseEnglish, and ChineseEnglish translation tasks. |
MMPE: A Multi-Modal Interface for Post-Editing Machine Translation (2020.acl-main)
Copied to clipboard
Nico Herbig, Tim Düwel, Santanu Pal, Kalliopi Meladaki, Mahsa Monshizadeh, Antonio Krüger, Josef van Genabith
| Challenge: | Current advances in machine translation (MT) increase the need for translators to switch from traditional translation to post-editing (PE) of machine-translated text. |
| Approach: | They propose to combine traditional input modes with pen, touch, and speech modalities for post-editing of machine-translated text. |
| Outcome: | The proposed interfaces are designed to reduce errors and save time. |
Position Encoding with Random Float Sampling Enhances Length Generalization of Transformers (2026.findings-eacl)
Copied to clipboard
| Challenge: | Length generalization is the ability of language models to maintain performance on inputs longer than those seen during pretraining. |
| Approach: | They propose a position encoding strategy that uses random float sampling to generalize to unseen lengths. |
| Outcome: | The proposed strategy can generalize to lengths unseen during training and in benchmarks. |
Incorporating Noisy Length Constraints into Transformer with Length-aware Positional Encodings (2020.coling-main)
Copied to clipboard
| Challenge: | Neural Machine Translation suffers from an under-translation problem due to limited modeling of output sequence lengths. |
| Approach: | They propose a method to train a Transformer model using length constraints based on positional encoding. |
| Outcome: | The proposed method outperforms a vanilla Transformer in an English-to-Japanese translation by 3.22 points . the noise injection improved robustness for length prediction errors, especially within the window size. |
Automatic Post-Editing of Machine Translation: A Neural Programmer-Interpreter Approach (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to inducing APE have suffered from over-correction, where the APE system tends to keep the machine translated text without any modification. |
| Approach: | They propose a neural programmer-interpreter approach to automated post-editing (APE) that mimics human perform post- editing using discrete edit operations . their model outperforms previous neural models for inducing PE programs on the WMT17 APE task for German-English up to +1 BLEU score and -0.7 TER scores. |
| Outcome: | The proposed model outperforms previous neural models for inducing PE programs on the WMT17 APE task for German-English up to +1 BLEU score and -0.7 TER scores. |
MedicalSum: A Guided Clinical Abstractive Summarization Model for Generating Medical Reports from Patient-Doctor Conversations (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for summarizing medical conversations do not take clinical knowledge into account and are difficult to control. |
| Approach: | They propose a transformer-based sequence-to-sequence architecture for summarizing medical conversations by integrating medical domain knowledge from the Unified Medical Language System (UMLS). |
| Outcome: | The proposed model achieves state-of-the-art ROUGE score improvements of 0.8-2.1 points (including 6.2% error reduction in the PE section) it incorporates medical domain knowledge from the Unified Medical Language System (UMLS). |
WeTS: A Benchmark for Translation Suggestion (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on overall performance of machine translation but ignore TS performance, authors say . if TS is applied into post-editing, it will reduce the time and cost of post-production. |
| Approach: | They propose to use a golden corpus annotated by experts to generate a translation suggestion model. |
| Outcome: | The proposed model improves on the golden corpus annotated by translators on four translation directions. |
An Anchor-based Relative Position Embedding Method for Cross-Modal Tasks (2022.emnlp-main)
Copied to clipboard
| Challenge: | Position Embedding (PE) is essential for transformer to capture the sequence ordering of input tokens. |
| Approach: | They propose a unified position embedding method that bridges the semantic gap between modalities and embeds the anchor-based distance to guide computation of cross-attention. |
| Outcome: | The proposed method obtains new SOTA results on a wide range of benchmarks. |
Probing Simile Knowledge from Pre-trained Language Models (2022.acl-long)
Copied to clipboard
Weijie Chen, Yongzhu Chang, Rongsheng Zhang, Jiashu Pu, Guandan Chen, Le Zhang, Yadong Xi, Yijiang Chen, Chang Su
| Challenge: | Existing approaches to learn generic knowledge from a large corpus are time-consuming and labor-intensive. |
| Approach: | They propose a framework to probe simile knowledge from pre-trained language models to solve SI and SG tasks. |
| Outcome: | The proposed framework solves the SI and SG tasks in a simile triple completion task. |
Argument Mining with Fine-Tuned Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Argument Mining (AM) pipelines use fine-tuned large language models (LLMs) . initial approaches employ supervised machine learning algorithms, such as Maximum Entropy classifiers and Logistic Regressions. |
| Approach: | They propose to model the three main AM sub-tasks as text generation tasks and fine-tune eight popular quantized and non-quantized large language models (LLMs) on the benchmark PE, AbstRCT, and CDCP datasets. |
| Outcome: | The proposed pipeline achieves state-of-the-art across all AM sub-tasks and datasets, showing significant improvements over previous benchmarks. |
PE: A Poincare Explanation Method for Fast Text Hierarchy Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work on feature interactions neglects underlying linguistic information in feature representations. |
| Approach: | They propose a method for modeling feature interactions with hyperbolic spaces using Poincare Explanation. |
| Outcome: | The proposed method is able to model feature interactions with hyperbolic spaces in a time efficient manner. |
Mid-Air Hand Gestures for Post-Editing of Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | In a well-connected world, translation is of everincreasing importance. |
| Approach: | They propose to use mid-air hand gestures in combination with the keyboard for editing in machine translation and post-editing workflows to improve quality. |
| Outcome: | The proposed prototype supports mid-air hand gestures for cursor placement, text selection, deletion, and reordering. |
Evaluating Automatic Subtitling: Correlating Post-editing Effort and Automatic Metrics (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing metrics for automatic subtitling are not yet fully explored. |
| Approach: | They propose to use machine translation metrics to measure post-editing effort in automatic subtitling to collect data on product-, process- and participant-based data. |
| Outcome: | The proposed metrics correlate with measures of post-editing effort in automatic subtitling. |
Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding (2024.findings-emnlp)
Copied to clipboard
Liang Zhao, Xiachong Feng, Xiaocheng Feng, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin, Ting Liu
| Challenge: | Existing methods to enhance length extrapolation of large language models have been developed, but a systematic survey is lacking. |
| Approach: | They propose to examine the effects of positional encoding on length extrapolation. |
| Outcome: | The proposed methods improve the extrapolation of large language models, but they are still lacking a systematic survey. |
Disentangle to Decay: Linear Attention with Trainable Decay Factor (2025.coling-main)
Copied to clipboard
| Challenge: | Existing linear attention models use a decay factor based positional encoding (PE), but the decay factor is manually designed and non-trainable, limiting further optimization. |
| Approach: | They propose a PE-based positional encoding that disentangles decay factor into two parts to achieve further optimization and stable training. |
| Outcome: | The proposed model achieves stable training of decay factor and improves inference efficiency in normal context and extrapolation scenarios. |
Investigating the Helpfulness of Word-Level Quality Estimation for Post-Editing Machine Translation Output (2021.emnlp-main)
Copied to clipboard
| Challenge: | Post-editing (PE) machine translation (MT) output can save time and reduce errors. |
| Approach: | They propose to use automatic word-level quality estimation to predict correctness of MT output to flag problematic output. |
| Outcome: | The proposed model is not good enough to support human translations, but is based on a visualization reflecting uncertainty of the model. |
How Real Are Synthetic Therapy Conversations? Evaluating Fidelity in Prolonged Exposure Dialogues (2025.findings-emnlp)
Copied to clipboard
Suhas Bn, Dominik O. Mattioli, Andrew M. Sherrill, Rosa I. Arriaga, Christopher Wiese, Saeed Abdullah
| Challenge: | Synthetic data adoption in healthcare is driven by privacy concerns, data access limitations, and high annotation costs. |
| Approach: | They compare real and synthetic PTSD therapy conversations using linguistic, structural, and protocol-specific metrics like turn-taking and treatment fidelity. |
| Outcome: | The proposed framework assesses clinical fidelity beyond surface fluency. |
Understanding How Positional Encodings Work in Transformer Model (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies have reported superiority of relative PEs in translation tasks. |
| Approach: | They analyze in which part of a transformer model PEs work and compare them using experiments . they find that relative PEs should be added only to query and key of attention mechanism . |
| Outcome: | The results show that relative and absolute PEs work in a transformer model, and should be added to the query and key of an attention mechanism, not to the value. |
GSM-Noise: Exploring and Enhancing Large Language Models’ Reasoning under Noisy Inputs (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models struggle when dealing with complex, ill-formed, or noisy inputs . open-source models are less robust, while closed-source ones are more robust . |
| Approach: | They propose to use GSM-Noise to refine inputs before engaging in in-depth analysis to improve LLM robustness under noisy conditions. |
| Outcome: | The proposed model can achieve consistent performance gains under noisy conditions with prompt engineering, supervised finetuning, and reinforcement learning. |