paper-with-me

Papers

Supervised and unsupervised approaches to measuring usage similarity

2017-04-01 · WS 2017 4 · Milton King, Paul Cook

Usage similarity (USim) is an approach to determining word meaning in context that does not rely on a sense inventory. Instead, pairs of usages of a target lemma are rated on a scale. In this paper we propose unsupervised approaches to USim based on embeddings for words, contexts, and sentences, and achieve state-of-the-art results over two USim datasets. We further consider supervised approaches to USim, and find that although they outperform unsupervised approaches, they are unable to generalize to lemmas that are unseen in the training data.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

LEMMAWord Sense DisambiguationWord Sense Induction

Similar Papers 제목 키워드 기반

Unsupervised Sentence Textual Similarity with Compositional Phrase Semantics

2022-10-05 · COLING 2022 10 · ZiHao Wang, Jiaheng Dou, Yong Zhang

Measuring Sentence Textual Similarity (STS) is a classic task that can be applied to many downstream NLP applications such as text generation and retrieval. In this paper, we focus on unsupervised STS that works on vario…

RetrievalSentenceSentence EmbeddingsSTS+1

Unsupervised Estimation of Word Usage Similarity

2012-12-01 · ALTA 2012 12 · Marco Lui, Timothy Baldwin, Diana McCarthy
Topic ModelsWord Sense DisambiguationWord Sense Induction

Unsupervised Word Usage Similarity in Social Media Texts

2013-06-01 · SEMEVAL 2013 6 · Sp Gella, ana, Paul Cook, Bo Han
Word Sense Disambiguation

Learning Flat Latent Manifolds with VAEs

2020-02-12 · ICML 2020 1 · Nutan Chen, Alexej Klushyn, Francesco Ferroni, Justin Bayer 외

Measuring the similarity between data points often requires domain knowledge, which can in parts be compensated by relying on unsupervised methods such as latent-variable models, where similarity/distance is estimated in…

Computational EfficiencyDecoder

An Empirical Study on Measuring the Similarity of Sentential Arguments with Language Model Domain Adaptation

2021-02-19 · ChaeHun Park, Sangwoo Seo

Measuring the similarity between two different sentential arguments is an important task in argument mining. However, one of the challenges in this field is that the dataset must be annotated using expertise in a variety…

Argument MiningClusteringDomain AdaptationLanguage Modeling+3