paper-with-me

Papers

Attending to Long-Distance Document Context for Sequence Labeling

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Matthew J{\"o}rke, Jon Gillick, Matthew Sims, David Bamman

We present in this work a method for incorporating global context in long documents when making local decisions in sequence labeling problems like NER. Inspired by work in featurized log-linear models (Chieu and Ng, 2002; Sutton and McCallum, 2004), our model learns to attend to multiple mentions of the same word type in generating a representation for each token in context, extending that work to learning representations that can be incorporated into modern neural models. Attending to broader context at test time provides complementary information to pretraining (Gururangan et al., 2020), yields strong gains over equivalently parameterized models lacking such context, and performs best at recognizing entities with high TF-IDF scores (i.e., those that are important within a document).

📄 PDF Abstract BibTeX

Code (1)

mjoerke/doc-arc 공식 구현 pytorch

Tasks

NER

Similar Papers 제목 키워드 기반

Coarse-to-Fine Attention Models for Document Summarization

2017-09-01 · WS 2017 9 · Jeffrey Ling, Alex Rush, er

Sequence-to-sequence models with attention have been successful for a variety of NLP problems, but their speed does not scale well for tasks with long source sequences such as document summarization. We propose a novel c…

Document SummarizationMachine TranslationQuestion Answering

Improving Long Context Document-Level Machine Translation

2023-06-08 · Christian Herold, Hermann Ney

Document-level context for neural machine translation (NMT) is crucial to improve the translation consistency and cohesion, the translation of ambiguous inputs, as well as several other linguistic phenomena. Many works h…

Document Level Machine TranslationMachine TranslationNMTSentence+1

Unlimiformer: Long-Range Transformers with Unlimited Length Input

2023-05-02 · NeurIPS 2023 11 · Amanda Bertsch, Uri Alon, Graham Neubig, Matthew R. Gormley

Since the proposal of transformers, these models have been limited to bounded input lengths, because of their need to attend to every token in the input. In this work, we propose Unlimiformer: a general approach that wra…

Book summarizationCPUDecoderGPU

Untie the Knots: An Efficient Data Augmentation Strategy for Long-Context Pre-Training in Language Models

2024-09-07 · Junfeng Tian, Da Zheng, Yang Cheng, Rui Wang 외

Large language models (LLM) have prioritized expanding the context window from which models can incorporate more information. However, training models to handle long contexts presents significant challenges. These includ…

Data Augmentation

Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context Selection

2026-05-28 · Yutong Wang, Xuebo Liu, Derek F. Wong, Zhilin Li 외 arxiv

Document-level translation remains one of the most challenging tasks for large language models, which are constrained by limited context windows that impede global cohesion, while simultaneously suffering from redundant …

Reinforcement Learning