paper-with-me

홈 › Papers

Antonym-Synonym Classification Based on New Sub-space Embeddings

2019-06-13 · Muhammad Asif Ali, Yifang Sun, Xiaoling Zhou, Wei Wang, Xiang Zhao

Distinguishing antonyms from synonyms is a key challenge for many NLP applications focused on the lexical-semantic relation extraction. Existing solutions relying on large-scale corpora yield low performance because of huge contextual overlap of antonym and synonym pairs. We propose a novel approach entirely based on pre-trained embeddings. We hypothesize that the pre-trained embeddings comprehend a blend of lexical-semantic information and we may distill the task-specific information using Distiller, a model proposed in this paper. Later, a classifier is trained based on features constructed from the distilled sub-spaces along with some word level features to distinguish antonyms from synonyms. Experimental results show that the proposed model outperforms existing research on antonym synonym distinction in both speed and performance.

📄 PDF Abstract BibTeX arXiv:1906.05612

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral ClassificationRelation Extraction

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Antonymy-Synonymy Discrimination through the Repelling Parasiamese Neural Network

2021-09-29 · Mathias Etcheverry, Dina Wonsever

Antonymic and synonymic pairs may both occur nearby in word embeddings spaces because they have similar distributional information. Different methods have been used in order to distinguish antonyms from synonyms, making …

Word Embeddings

Combining Discourse Markers and Cross-lingual Embeddings for Synonym--Antonym Classification

2019-06-01 · NAACL 2019 6 · Michael Roth, Shyam Upadhyay

It is well-known that distributional semantic approaches have difficulty in distinguishing between synonyms and antonyms (Grefenstette, 1992; Pad{\'o} and Lapata, 2003). Recent work has shown that supervision available i…

Cross-Lingual Word EmbeddingsGeneral ClassificationWord Embeddings

Semantic Word Clusters Using Signed Spectral Clustering

2017-07-01 · ACL 2017 7 · Jo{\~a}o Sedoc, Jean Gallier, Dean Foster, Lyle Ungar

Vector space representations of words capture many aspects of word similarity, but such methods tend to produce vector spaces in which antonyms (as well as synonyms) are close to each other. For spectral clustering using…

ClusteringGraph ClusteringSemantic Textual SimilarityWord Embeddings+1

Constructing a Corpus of Japanese Predicate Phrases for Synonym/Antonym Relations

2014-05-01 · LREC 2014 5 · Tomoko Izumi, Tomohide Shibata, Hisako Asano, Yoshihiro Matsuo 외

We construct a large corpus of Japanese predicate phrases for synonym-antonym relations. The corpus consists of 7,278 pairs of predicates such as “receive-permission (ACC)” vs. “obtain-permission (ACC)”, in which each pr…

Binary ClassificationGeneral ClassificationInformation Retrieval

Integrating Distributional Lexical Contrast into Word Embeddings for Antonym-Synonym Distinction

2016-05-25 · ACL 2016 8 · Kim Anh Nguyen, Sabine Schulte im Walde, Ngoc Thang Vu

We propose a novel vector representation that integrates lexical contrast into distributional vectors and strengthens the most salient features for determining degrees of word similarity. The improved vectors significant…

Word EmbeddingsWord Similarity