paper-with-me

Papers

Why we have switched from building full-fledged taxonomies to simply detecting hypernymy relations

2017-03-12 · Jose Camacho-Collados

The study of taxonomies and hypernymy relations has been extensive on the Natural Language Processing (NLP) literature. However, the evaluation of taxonomy learning approaches has been traditionally troublesome, as it mainly relies on ad-hoc experiments which are hardly reproducible and manually expensive. Partly because of this, current research has been lately focusing on the hypernymy detection task. In this paper we reflect on this trend, analyzing issues related to current evaluation procedures. Finally, we propose three potential avenues for future work so that is-a relations and resources based on them play a more important role in downstream NLP applications.

📄 PDF Abstract BibTeX arXiv:1703.04178

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The ContrastMedium Algorithm: Taxonomy Induction From Noisy Knowledge Graphs With Just A Few Links

2017-04-01 · EACL 2017 4 · Stefano Faralli, Alex Panchenko, er, Chris Biemann 외

In this paper, we present ContrastMedium, an algorithm that transforms noisy semantic networks into full-fledged, clean taxonomies. ContrastMedium is able to identify the embedded taxonomy structure from a noisy knowledg…

Knowledge GraphsOpen Information Extraction

Learning Concept Taxonomies from Multi-modal Data

2016-06-29 · ACL 2016 8 · Hao Zhang, Zhiting Hu, Yuntian Deng, Mrinmaya Sachan 외

We study the problem of automatically building hypernym taxonomies from textual and visual data. Previous works in taxonomy induction generally ignore the increasingly prominent visual data, which encode important percep…

Feature Engineering

Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration

2025-09-19 · Nan Li, Bo Kang, Tijl De Bie arxiv

Creating robust occupation taxonomies, vital for applications ranging from job recommendation to labor market intelligence, is challenging. Manual curation is slow, while existing automated methods are either not adaptiv…

Towards Natural Bilingual and Code-Switched Speech Synthesis Based on Mix of Monolingual Recordings and Cross-Lingual Voice Conversion

2020-10-16 · Shengkui Zhao, Trung Hieu Nguyen, Hao Wang, Bin Ma

Recent state-of-the-art neural text-to-speech (TTS) synthesis models have dramatically improved intelligibility and naturalness of generated speech from text. However, building a good bilingual or code-switched TTS for a…

Speech Synthesistext-to-speechText to SpeechVoice Conversion

TaBIIC: Taxonomy Building through Iterative and Interactive Clustering

2023-12-10 · Mathieu d'Aquin

Building taxonomies is often a significant part of building an ontology, and many attempts have been made to automate the creation of such taxonomies from relevant data. The idea in such approaches is either that relevan…

Clustering