From word to sense embeddings: A survey on vector representations of meaning
J Camacho-Collados, MT Pilehvar - Journal of Artificial Intelligence …, 2018 - jair.org
Over the past years, distributed semantic representations have proved to be effective and
flexible keepers of prior knowledge to be integrated into downstream applications. This …
flexible keepers of prior knowledge to be integrated into downstream applications. This …
Moving down the long tail of word sense disambiguation with gloss-informed biencoders
T Blevins, L Zettlemoyer - arXiv preprint arXiv:2005.02590, 2020 - arxiv.org
A major obstacle in Word Sense Disambiguation (WSD) is that word senses are not
uniformly distributed, causing existing models to generally perform poorly on senses that are …
uniformly distributed, causing existing models to generally perform poorly on senses that are …
Zero-shot word sense disambiguation using sense definition embeddings
Abstract Word Sense Disambiguation (WSD) is a long-standing but open problem in Natural
Language Processing (NLP). WSD corpora are typically small in size, owing to an expensive …
Language Processing (NLP). WSD corpora are typically small in size, owing to an expensive …
Word sense disambiguation using a bidirectional lstm
M Kågebäck, H Salomonsson - arXiv preprint arXiv:1606.03568, 2016 - arxiv.org
In this paper we present a clean, yet effective, model for word sense disambiguation. Our
approach leverage a bidirectional long short-term memory network which is shared between …
approach leverage a bidirectional long short-term memory network which is shared between …
Cesi: Canonicalizing open knowledge bases using embeddings and side information
S Vashishth, P Jain, P Talukdar - Proceedings of the 2018 World Wide …, 2018 - dl.acm.org
Open Information Extraction (OpenIE) methods extract (noun phrase, relation phrase, noun
phrase) triples from text, resulting in the construction of large Open Knowledge Bases (Open …
phrase) triples from text, resulting in the construction of large Open Knowledge Bases (Open …
Large-scale information extraction from textual definitions through deep syntactic and semantic analysis
CD Bovi, L Telesca, R Navigli - Transactions of the Association for …, 2015 - direct.mit.edu
We present DefIE, an approach to large-scale Information Extraction (IE) based on a
syntactic-semantic analysis of textual definitions. Given a large corpus of definitions we …
syntactic-semantic analysis of textual definitions. Given a large corpus of definitions we …
Supervised distributional hypernym discovery via domain adaptation
L Espinosa-Anke, J Camacho-Collados… - … on Empirical Methods …, 2016 - repositori.upf.edu
Lexical taxonomies are graph-like hierarchical structures that provide a formal
representation of knowledge. Most knowledge graphs to date rely on is-a (hypernymic) …
representation of knowledge. Most knowledge graphs to date rely on is-a (hypernymic) …
On aligning OpenIE extractions with knowledge bases: A case study
Open information extraction (OIE) is the task of extracting relations and their corresponding
arguments from a natural language text in un-supervised manner. Outputs of such systems …
arguments from a natural language text in un-supervised manner. Outputs of such systems …
OPIEC: an open information extraction corpus
K Gashteovski, S Wanner, S Hertling… - arXiv preprint arXiv …, 2019 - arxiv.org
Open information extraction (OIE) systems extract relations and their arguments from natural
language text in an unsupervised manner. The resulting extractions are a valuable resource …
language text in an unsupervised manner. The resulting extractions are a valuable resource …
[PDF][PDF] Supersense embeddings: A unified model for supersense interpretation, prediction, and utilization
L Flekova, I Gurevych - Proceedings of the 54th Annual Meeting …, 2016 - aclanthology.org
Coarse-grained semantic categories such as supersenses have proven useful for a range of
downstream tasks such as question answering or machine translation. To date, no effort has …
downstream tasks such as question answering or machine translation. To date, no effort has …