Conciseness: An Overlooked Language Task

2022-11-08 · Felix Stahlberg, Aashish Kumar, Chris Alberti, Shankar Kumar

We report on novel investigations into training models that make sentences concise. We define the task and show that it is different from related tasks such as summarization and simplification. For evaluation, we release two test sets, consisting of 2000 sentences each, that were annotated by two and five human annotators, respectively. We demonstrate that conciseness is a difficult task for which zero-shot setups with large neural language models often do not perform well. Given the limitations of these approaches, we propose a synthetic data generation method based on round-trip translations. Using this data to either train Transformers from scratch or fine-tune T5 models yields our strongest baselines that can be further improved by fine-tuning on an artificial conciseness dataset that we derived from multi-annotator machine translation test sets.

📄 PDF Abstract BibTeX arXiv:2211.04126

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translation Synthetic Data Generation Translation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Test 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Residual Connection 설명 없음

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

SentencePiece 설명 없음

Unifying Conformal Language Tasks with In-Context Ensembles

2026-09-02 · Xiao Shi Huang, Chen-Yuan Lin, Bruce Kuwahara, Kin Kwan Leung 외 hf

Many NLP tasks, such as summarization and extractive question answering, reduce to retrieving relevant content from documents under two constraints: coverage, retaining enough pertinent information to achieve some goal, …

Question Answering Prompt Engineering

Can Grammarly and ChatGPT accelerate language change? AI-powered technologies and their impact on the English language: wordiness vs. conciseness

2025-02-06 · Karolina Rudnicka

The proliferation of NLP-powered language technologies, AI-based natural language generation models, and English as a mainstream means of communication among both native and non-native speakers make the output of AI-powe…

Text Generation

Concise Reasoning via Reinforcement Learning

2025-04-07 · Mehdi Fatemi, Banafsheh Rafiee, Mingjie Tang, Kartik Talamadupula

Despite significant advancements in large language models (LLMs), a major drawback of reasoning models is their enormous token usage, which increases computational cost, resource requirements, and response time. In this …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Improving Radiology Report Conciseness and Structure via Local Large Language Models

2024-11-06 · Iryna Hartsock, Cyrillo Araujo, Les Folio, Ghulam Rasool

In this study, we aim to enhance radiology reporting by improving both the conciseness and structured organization of findings (also referred to as templating), specifically by organizing information according to anatomi…

Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost

2024-07-29 · Sania Nayab, Giulio Rossolini, Marco Simoni, Andrea Saracino 외

Today's large language models (LLMs) can solve challenging question-answering tasks, and prompt engineering techniques, such as chain-of-thought (CoT), have gained attention for enhancing the explanation and correctness …

GSM8K Prompt Engineering Question Answering