A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction (2022.naacl-demo)
Copied to clipboard
Robert Vacareanu, George C.G. Barbosa, Enrique Noriega-Atala, Gus Hahn-Powell, Rebecca Sharp, Marco A. Valenzuela-Escárcega, Mihai Surdeanu
| Challenge: | Vacareanu et al., 2021) proposes a system that helps users build transparent information extraction models . rule-based methods address the opacity of neural architectures by producing models that are transparent . |
| Approach: | They propose a system that assists a user in constructing transparent information extraction models . the system generates high-precision rules even in a 1-shot setting, they show . |
| Outcome: | The proposed system generates high-precision rules even in a 1-shot setting . it outperforms manually written patterns on a widely-used relation extraction dataset . |
Similar Papers
From Examples to Rules: Neural Guided Rule Synthesis for Information Extraction (2022.lrec-1)
Copied to clipboard
Robert Vacareanu, Marco A. Valenzuela-Escárcega, George Caique Gouveia Barbosa, Rebecca Sharp, Gustave Hahn-Powell, Mihai Surdeanu
| Challenge: | a "deep learning tsunami" has brought tremendous improvements in performance to most NLP applications. |
| Approach: | They propose a method for rule synthesis from examples that combines the advantages of deep learning and rule-based methods. |
| Outcome: | The proposed method achieves state-of-the-art on 1-shot task and competitive performance in 5-shot scenario. |
Learning to Generate Rules for Realistic Few-Shot Relation Classification: An Encoder-Decoder Approach (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a new approach to relation classification is proposed to use data-driven approaches to perform fewshot tasks with limited training data. |
| Approach: | They propose a neuro-symbolic approach for realistic few-shot relation classification via rules . they propose to generate rules that can be used to extract relations using custom T5-style models . |
| Outcome: | The proposed approach is interpretable and pliable and outperforms the state-of-the-art on TACRED and NYT29 benchmarks while maintaining pliability. |
KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction (2024.acl-long)
Copied to clipboard
Zixuan Li, Yutao Zeng, Yuxin Zuo, Weicheng Ren, Wenxuan Liu, Miao Su, Yucan Guo, Yantao Liu, Lixiang Lixiang, Zhilei Hu, Long Bai, Wei Li, Yidan Liu, Pan Yang, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
| Challenge: | None. None.. None! |
| Approach: | None. None.. None! |
| Outcome: | None. None. No. : |
Reasoning Makes Good Annotators : An Automatic Task-specific Rules Distilling Framework for Low-resource Relation Extraction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to extract knowledge from unlabeled data generate noise labels. |
| Approach: | They propose an automatic task-specific rules distilling framework to generate a logic rule from unlabeled data. |
| Outcome: | The proposed framework could power the labeling ability by discovering reliable model-labeled data. |
Human in the Loop: How to Effectively Create Coherent Topics by Manually Labeling Only a Few Documents per Class (2024.lrec-main)
Copied to clipboard
| Challenge: | Few-shot methods for accurate modeling under sparse label-settings are still challenging in document classification. |
| Approach: | They propose to combine supervised few-shot learning with a topic extraction method to generate coherent topics in large text corpora. |
| Outcome: | The proposed method outperforms unsupervised topic modeling methods in document classification. |
Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to few-shot text classification require domain expertise and an understanding of the language model's abilities to define the mapping between words and labels. |
| Approach: | They propose a method that converts textual inputs to cloze questions that contain some form of task description and processes them with a pretrained language model to map the predicted words to labels. |
| Outcome: | The proposed approach performs almost as well as hand-crafted label-to-word mappings for a number of tasks with small amounts of training data. |
Syntactic Patterns Improve Information Extraction for Medical Search (N18-2)
Copied to clipboard
| Challenge: | Medical professionals search the literature by specifying the type of patients, the medical intervention(s) and the outcome measure(s). |
| Approach: | They propose to exploit the availability of structured abstracts to extract medically relevant information from syntactic patterns. |
| Outcome: | The proposed models differ from the constituent unigrams in the extracted patterns, suggesting that they capture contextual information that is otherwise lost. |
Odinson: A Fast Rule-based Information Extraction Framework (2020.lrec-1)
Copied to clipboard
| Challenge: | Odinson is a rule-based information extraction framework that matches over multiple representations of text in near real time. |
| Approach: | They propose a rule-based information extraction framework that matches patterns over multiple representations of text with a runtime system that operates in near real time. |
| Outcome: | The proposed framework matches a graph traversal in 2.8 seconds in a corpus of over 134 million sentences, nearly 150,000 times faster than its predecessor. |
MultiTACRED: A Multilingual Version of the TAC Relation Extraction Dataset (2023.acl-long)
Copied to clipboard
| Challenge: | Relation extraction (RE) is a fundamental task in information extraction, but its extension to multilingual settings is hindered by the lack of supervised resources comparable in size to large English datasets. |
| Approach: | They propose a dataset to analyze relation extraction (RE) in multilingual settings . they find machine translation is a viable strategy to transfer RE instances . |
| Outcome: | The proposed dataset covers 12 typologically diverse languages from 9 language families and is compared with existing datasets. |
Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have great potential for synthetic data generation. |
| Approach: | They show that large language models can generate useful data even for complex tasks . they use a symmetric task difficulty asymmetry to prompt an LLM to generate plausible input text for a target output structure. |
| Outcome: | The proposed approach outperforms existing models by a substantial margin on closed information extraction tasks with 1.8M data points and 770M parameters. |