paper-with-me

홈 › Papers

LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution

2022-05-25 · Shon Otmazgin, Arie Cattan, Yoav Goldberg

While coreference resolution typically involves various linguistic challenges, recent models are based on a single pairwise scorer for all types of pairs. We present LingMess, a new coreference model that defines different categories of coreference cases and optimize multiple pairwise scorers, where each scorer learns a specific set of linguistic challenges. Our model substantially improves pairwise scores for most categories and outperforms cluster-level performance on Ontonotes and 5 additional datasets. Our model is available in https://github.com/shon-otmazgin/lingmess-coref

📄 PDF Abstract BibTeX arXiv:2205.12644

Code (2)

shon-otmazgin/lingmess-coref 공식 구현 pytorch
shon-otmazgin/fastcoref pytorch

Tasks

coreference-resolutionCoreference Resolution

Similar Papers 제목 키워드 기반

F-coref: Fast, Accurate and Easy to Use Coreference Resolution

2022-09-09 · Shon Otmazgin, Arie Cattan, Yoav Goldberg

We introduce fastcoref, a python package for fast, accurate, and easy-to-use English coreference resolution. The package is pip-installable, and allows two modes: an accurate mode based on the LingMess architecture, prov…

coreference-resolutionCoreference ResolutionGPU

COVCOR20 at WNUT-2020 Task 2: An Attempt to Combine Deep Learning and Expert rules

2020-09-07 · EMNLP (WNUT) 2020 11 · Ali Hürriyetoğlu, Ali Safaya, Nelleke Oostdijk, Osman Mutlu 외

In the scope of WNUT-2020 Task 2, we developed various text classification systems, using deep learning models and one using linguistically informed rules. While both of the deep learning systems outperformed the system …

Deep LearningTask 2text-classificationText Classification

Linguistically-Informed Transformations (LIT): A Method for Automatically Generating Contrast Sets

2020-10-16 · EMNLP (BlackboxNLP) 2020 11 · Chuanrong Li, Lin Shengshuo, Leo Z. Liu, Xinyi Wu 외

Although large-scale pretrained language models, such as BERT and RoBERTa, have achieved superhuman performance on in-distribution test sets, their performance suffers on out-of-distribution test sets (e.g., on contrast …

Understanding the Polarity of Events in the Biomedical Literature: Deep Learning vs. Linguistically-informed Methods

2019-06-01 · WS 2019 6 · Enrique Noriega-Atala, Zhengzhong Liang, John Bachman, Clayton Morrison 외

An important task in the machine reading of biochemical events expressed in biomedical texts is correctly reading the polarity, i.e., attributing whether the biochemical event is a promotion or an inhibition. Here we pre…

Deep LearningReading Comprehension

LingBench++: A Linguistically-Informed Benchmark and Reasoning Framework for Multi-Step and Cross-Cultural Inference with LLMs

2025-07-22 · Da-Chen Lian, Ri-Sheng Huang, Pin-Er Chen, Chunki Lim 외 arxiv

We propose LingBench++, a linguistically-informed benchmark and reasoning framework designed to evaluate large language models (LLMs) on complex linguistic tasks inspired by the International Linguistics Olympiad (IOL). …