يميل مؤلفو النص إلى استخدام إحساس واحد في الغالب ل Lemma التي يمكن أن تختلف بين المؤلفين المختلفين.قد لا يتم التقاط هذا بنموذج Disambiguation Sense (WSD) المعذر (WSD) الذي تم تدريبه على المؤلفين المتعددين.يجد عملنا أن الحواس الأولى في WordNet، والحواس السائدة من نوع DataSet الخاص بنا، والاستحواذ السائدة للمؤلف يمكن أن تكون مختلفة، وبالتالي، يمكن أن تؤدي النماذج المؤلف للأذرع بشكل جيد على مجموعة البيانات بأكملها، ولكن بشكل سيء على المؤلفين الأفراد.في هذا العمل، نستكشف أساليب تخصيص نماذج WSD عن طريق خياطة النماذج الموجودة من أحدث النماذج نحو الفرد من خلال استغلال توزيعات معنى المؤلف.نقترح مجموعة بيانات WSD الجديدة وإظهار أن تخصيص نظام WSD مع معرفة توزيعات معنى المؤلف أو الحواس السائدة يمكن أن تزيد بشكل كبير أدائها.
Authors of text tend to predominantly use a single sense for a lemma that can differ among different authors. This might not be captured with an author-agnostic word sense disambiguation (WSD) model that was trained on multiple authors. Our work finds that WordNet's first senses, the predominant senses of our dataset's genre, and the predominant senses of an author can all be different and therefore, author-agnostic models could perform well over the entire dataset, but poorly on individual authors. In this work, we explore methods for personalizing WSD models by tailoring existing state-of-the-art models toward an individual by exploiting the author's sense distributions. We propose a novel WSD dataset and show that personalizing a WSD system with knowledge of an author's sense distributions or predominant senses can greatly increase its performance.
References used
https://aclanthology.org/
Supervised systems have nowadays become the standard recipe for Word Sense Disambiguation (WSD), with Transformer-based language models as their primary ingredient. However, while these systems have certainly attained unprecedented performances, virt
Words are defined based on their meanings in various ways in different resources. Aligning word senses across monolingual lexicographic resources increases domain coverage and enables integration and incorporation of data. In this paper, we explore t
This paper describes our submission to SemEval 2021 Task 2. We compare XLM-RoBERTa Base and Large in the few-shot and zero-shot settings and additionally test the effectiveness of using a k-nearest neighbors classifier in the few-shot setting instead
In parataxis languages like Chinese, word meanings are constructed using specific word-formations, which can help to disambiguate word senses. However, such knowledge is rarely explored in previous word sense disambiguation (WSD) methods. In this pap
In this paper, we describe our proposed methods for the multilingual word-in-Context disambiguation task in SemEval-2021. In this task, systems should determine whether a word that occurs in two different sentences is used with the same meaning or no