Learning Word Embeddings from Portuguese Lexical-Semantic Knowledge Bases

Oliveira, Hugo Gonçalo

doi:10.1007/978-3-319-99722-3_27

Cited by 5 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, as shown in Section 2, wordnets are theoretically simple and intuitive. Aside from this, wordnets like PWN are more formalized since they have been created and maintained by experts who are responsible for grouping synsets and defining relations amongst them [Gonçalo Oliveira et al 2021].…”

Section: In Defense Of Wordnet-based Stsmentioning

confidence: 99%

Semantic Textual Similarity: In Defense of Wordnet-Based Methods

Gonçalves

2023

Anais Do XIV Simpósio Brasileiro De Tecnologia Da Informação E Da Linguagem Humana (STIL 2023)

View full text Add to dashboard Cite

Wordnets have long been used as a tool for evaluating the semantic similarity between short texts. In addition to being simpler than recent deep learning approaches, methods based on wordnets offer an important advantage: they deliver results that are easy to interpret as their decisions are usually taken by considering the proximity between graph nodes. In this work, we explore a lightweight approach based on a Portuguese wordnet to solve the ASSIN 2 Semantic Textual Similarity (STS) shared task. In this task, each object of a dataset consists of a pair of Portuguese sentences annotated with its semantic score and the goal is to learn an STS model to estimate the similarity value of new, previously unseen, sentence pairs. Experiments show that our results are competitive with state-of-the-art methods in terms of mean squared error.

show abstract

Section: In Defense Of Wordnet-based Stsmentioning

confidence: 99%

Semantic Textual Similarity: In Defense of Wordnet-Based Methods

Gonçalves

2023

Anais Do XIV Simpósio Brasileiro De Tecnologia Da Informação E Da Linguagem Humana (STIL 2023)

View full text Add to dashboard Cite

show abstract

“…Based on the extracted relations, implicit in the text, other relations are inferred, when combined with relations in PoeTryMe's semantic network. For Portuguese, the network currently used includes all the relations in at least two out of nine Portuguese lexical-semantic knowledge bases, including wordnets and dictionaries (Gonçalo Oliveira, 2017a). Therefore, it covers a rich set of relation types including not only synonymy, hypernymy and partOf, but also others, such as isSaid-OfWhatDoes (in Portuguese, dizSeDoQue), isSaid-About (dizSeSobre), hasQuality (temQualidade), has-State (temEstado), antonymyOf (antonimoDe), is-Part/Member/MaterialOf (parte/membro/materialDe), and isPartOfWhatIs (parteDeAlgoComPropriedade), which are exploited by Poeta 2.0 A set of rules was handcrafted for inferring new relations from a combination of one relation extracted from the tweets and another in PoeTryMe's semantic network.…”

Section: Relation Inferencementioning

confidence: 99%

O Poeta Artificial 2.0: Increasing Meaningfulness in a Poetry Generation Twitter bot

Oliveira¹

2017

Proceedings of the Workshop on Computational Creativity in Natural Language Generation (CC-NLG 2017)

Self Cite

View full text Add to dashboard Cite

O Poeta Artificial is a bot that tweets poems, in Portuguese, inspired by the latest Twitter trends. Built on top of PoeTryMe, a poetry generation platform, so far it had only produced poems based on a set of keywords in tweets about a trend. This paper presents recently implemented features for increasing the connection between the produced text and the target trend through the reutilisation and production of new text fragments, for highlighting the trend, paraphrasing text by Twitter users, or based on extracted or inferred semantic relations.

show abstract

“…Cosine of averaged token vectors, i.e., as in Section 4.2, computed with the following word embeddings: NILC word2vec-CBOW (300-sized), NILC GloVe (300-sized), fastText.cc [29], Numberbatch [36], and PT-LKB [37] (5).…”

mentioning

confidence: 99%

Developing Amaia: A Conversational Agent for Helping Portuguese Entrepreneurs—An Extensive Exploration of Question-Matching Approaches for Portuguese

et al. 2020

Self Cite

View full text Add to dashboard Cite

This paper describes how we tackled the development of Amaia, a conversational agent for Portuguese entrepreneurs. After introducing the domain corpus used as Amaia’s Knowledge Base (KB), we make an extensive comparison of approaches for automatically matching user requests with Frequently Asked Questions (FAQs) in the KB, covering Information Retrieval (IR), approaches based on static and contextual word embeddings, and a model of Semantic Textual Similarity (STS) trained for Portuguese, which achieved the best performance. We further describe how we decreased the model’s complexity and improved scalability, with minimal impact on performance. In the end, Amaia combines an IR library and an STS model with reduced features. Towards a more human-like behavior, Amaia can also answer out-of-domain questions, based on a second corpus integrated in the KB. Such interactions are identified with a text classifier, also described in the paper.

show abstract

Learning Word Embeddings from Portuguese Lexical-Semantic Knowledge Bases

Cited by 5 publications

References 11 publications

Semantic Textual Similarity: In Defense of Wordnet-Based Methods

Semantic Textual Similarity: In Defense of Wordnet-Based Methods

O Poeta Artificial 2.0: Increasing Meaningfulness in a Poetry Generation Twitter bot

Developing Amaia: A Conversational Agent for Helping Portuguese Entrepreneurs—An Extensive Exploration of Question-Matching Approaches for Portuguese

Contact Info

Product

Resources

About