Two Knowledge-based Methods for High-Performance Sense Distribution Learning

نویسندگان

  • Tommaso Pasini
  • Roberto Navigli
چکیده

Knowing the correct distribution of senses within a corpus can potentially boost the performance of Word Sense Disambiguation (WSD) systems by many points. We present two fully automatic and language-independent methods for computing the distribution of senses given a raw corpus of sentences. Intrinsic and extrinsic evaluations show that our methods outperform the current state of the art in sense distribution learning and the strongest baselines for the most frequent sense in multiple languages and on domain-specific test sets. Our sense distributions are available at http:// trainomatic.org.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Comparing the Efficiency of Electronic Learning and Workshop Learning on Knowledge and Performance of Nursing Students in Controlling Nosocomial Infections

Background Being familiar with new teaching methods and comparing their result helps teachers achieve better planning for applying such methods in the future. This study is aimed on comparing the efficiency of electronic learning and workshop on knowledge and performance of nursing students in controlling nosocomial infections. Methods Two groups were selected by pre-test post-test method. Stud...

متن کامل

The Interplay between Young Learners' Sense of Self-Efficacy in Reading Comprehension and English Language Proficiency

This study intended to explore the interplay between young language learners' sense of self-efficacy regarding reading comprehension in their reading test performance associated with learning English among universities. To undertake the study, a purposive sampling method was adopted. A total of 60 freshmen undergraduate learners of English consented to participate in this study.  A self-efficac...

متن کامل

Effect of Hybrid Problem-Based Learning versus the Conventional Teaching Method on Dental Students’ Knowledge and Performance in Endodontics

Background and Aim: With the advent of problem-based learning (PBL), pioneer universities across the world started using this method to improve learning quality. One of its modifications, hybrid-PBL, incorporates a combination of PBL and traditional teaching skills. This study compared the efficacy of hybrid PBL and the conventional instruction in terms of preclinical test scores and clinical p...

متن کامل

Image Classification via Sparse Representation and Subspace Alignment

Image representation is a crucial problem in image processing where there exist many low-level representations of image, i.e., SIFT, HOG and so on. But there is a missing link across low-level and high-level semantic representations. In fact, traditional machine learning approaches, e.g., non-negative matrix factorization, sparse representation and principle component analysis are employed to d...

متن کامل

Lecturing or Problem-based Learning: Comparing Effects of the Two Teaching Methods in Academic Achievement and Knowledge Retention in Pediatrics Course for Nursing Students

Introduction: Using the appropriate teaching methods, nursing educators are trying to improve students` both effective learning and knowledge retention. The survey reveals the impact of lecturing and problem-based learning in academic achievement and knowledge retention in the pediatrics course. Methods: A quasi-experimental design was used to compare the effects of the two teaching methods. ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017