غالبا ما تشمل توصيات المرادف التقليدية اقتراحات غير مناسبة للسياقات المحددة للكاتب.نقترح نهج بسيط لتوصية مرادف السياق من خلال الجمع بين الرسوم البيانية القائمة على الإنسان، على سبيل المثالWordnet، مع نماذج اللغة المدربة مسبقا.نقوم بتقييم تقنيةنا عن طريق برعاية مجموعة من أزواج الجملة بكلمة الكلمة متوازنة عبر كوربورا وأجزاء الكلام، ثم قم بتسليم كل زوج جملة الكلمة مع مجموعة من المرادفات المناسبة للسياق.وجدنا أن نهج نموذج اللغة الأساسية لها دقة أعلى.الأساليب الاستفادة من سياق الجملة لها استدعاء أعلى.بشكل عام، كانت النهج السياقي الأخير لديه أعلى درجة F.
Traditional synonym recommendations often include ill-suited suggestions for writer's specific contexts. We propose a simple approach for contextual synonym recommendation by combining existing human-curated thesauri, e.g. WordNet, with pre-trained language models. We evaluate our technique by curating a set of word-sentence pairs balanced across corpora and parts of speech, then annotating each word-sentence pair with the contextually appropriate set of synonyms. We found that basic language model approaches have higher precision. Approaches leveraging sentence context have higher recall. Overall, the latter contextual approach had the highest F-score.
References used
https://aclanthology.org/
The quality of fully automated text simplification systems is not good enough for use in real-world settings; instead, human simplifications are used. In this paper, we examine how to improve the cost and quality of human simplifications by leveragin
How do people understand the meaning of the word small'' when used to describe a mosquito, a church, or a planet? While humans have a remarkable ability to form meanings by combining existing concepts, modeling this process is challenging. This paper
Tag recommendation relies on either a ranking function for top-k tags or an autoregressive generation method. However, the previous methods neglect one of two seemingly conflicting yet desirable characteristics of a tag set: orderlessness and inter-d
This paper describes our system (IREL) for 3C-Citation Context Classification shared task of the Scholarly Document Processing Workshop at NAACL 2021. We participated in both subtask A and subtask B. Our best system achieved a Macro F1 score of 0.269
We study the problem of Cross-lingual Event Argument Extraction (CEAE). The task aims to predict argument roles of entity mentions for events in text, whose language is different from the language that a predictive model has been trained on. Previous