paper-with-me

Papers

EDS-MEMBED: Multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses

2021-02-27 · Eniafe Festus Ayetiran, Petr Sojka, Vít Novotný

Several language applications often require word semantics as a core part of their processing pipeline, either as precise meaning inference or semantic similarity. Multi-sense embeddings (M-SE) can be exploited for this important requirement. M-SE seeks to represent each word by their distinct senses in order to resolve the conflation of meanings of words as used in different contexts. Previous works usually approach this task by training a model on a large corpus and often ignore the effect and usefulness of the semantic relations offered by lexical resources. However, even with large training data, coverage of all possible word senses is still an issue. In addition, a considerable percentage of contextual semantic knowledge are never learned because a huge amount of possible distributional semantic structures are never explored. In this paper, we leverage the rich semantic structures in WordNet using a graph-theoretic walk technique over word senses to enhance the quality of multi-sense embeddings. This algorithm composes enriched texts from the original texts. Furthermore, we derive new distributional semantic similarity measures for M-SE from prior ones. We adapt these measures to word sense disambiguation (WSD) aspect of our experiment. We report evaluation results on 11 benchmark datasets involving WSD and Word Similarity tasks and show that our method for enhancing distributional semantic structures improves embeddings quality on the baselines. Despite the small training data, it achieves state-of-the-art performance on some of the datasets.

📄 PDF Abstract BibTeX arXiv:2103.00232

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic SimilaritySemantic Textual SimilarityWord Sense DisambiguationWord Similarity

Similar Papers 제목 키워드 기반

LSTMEmbed: Learning Word and Sense Representations from a Large Semantically Annotated Corpus with Long Short-Term Memories

2019-07-01 · ACL 2019 7 · Ignacio Iacobacci, Roberto Navigli

While word embeddings are now a de facto standard representation of words in most NLP tasks, recently the attention has been shifting towards vector representations which capture the different meanings, i.e., senses, of …

Word Embeddings

LLMEmbed: Rethinking Lightweight LLM's Genuine Function in Text Classification

2024-06-06 · Chun Liu, Hongguang Zhang, Kainan Zhao, Xinghai Ju 외

With the booming of Large Language Models (LLMs), prompt-learning has become a promising method mainly researched in various research areas. Recently, many attempts based on prompt-learning have been made to improve the …

Prompt Learningtext-classificationText ClassificationTransfer Learning

Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings

2018-04-09 · WS 2018 6 · Haw-Shiuan Chang, Amol Agrawal, Ananya Ganesh, Anirudha Desai 외

Word sense induction (WSI), which addresses polysemy by unsupervised discovery of multiple word senses, resolves ambiguities for downstream NLP tasks and also makes word representations more interpretable. This paper pro…

Word Sense Induction

Distributional Analysis of Polysemous Function Words

2019-07-24 · Sebastian Pado, Daniel Hole

In this paper, we are concerned with the phenomenon of function word polysemy. We adopt the framework of distributional semantics, which characterizes word meaning by observing occurrence contexts in large corpora and wh…

Word Embeddings

An Enhanced Lesk Word Sense Disambiguation Algorithm through a Distributional Semantic Model

2014-08-01 · COLING 2014 8 · Pierpaolo Basile, Annalina Caputo, Giovanni Semeraro
Word Sense Disambiguation