We compiled a set of patterns that denote lexico-semantic relations in Portuguese, created templates where one argument is fixed and the other is replaced by a mask, and then used BERT for predicting the latter. For most relations and measures, when assessed in a test of lexico-semantic analogies, BERT predictions outperformed those of earlier methods computed from static word embeddings, either with a pattern alone or with a combination of patterns. There is still a large margin of progression, but this suggests that BERT can be used as a source of lexico-semantic knowledge in Portuguese
Semantic relations between words are key to building systems that aim to understand and manipulate l...
The identification of causal relations from text is a mature problem in Natural Language Processing....
Recent literature has highlighted the extent to which inflectional paradigms are organised into syst...
Two sentences can be related in many different ways. Distinct tasks in natural language processing a...
We explored transformer-based language models for ranking instances of Portuguese lexico-semantic re...
Models of word embeddings are often assessed when solving syntactic and semantic analogies. Among th...
In the last decade, several lexical-semantic knowledge bases (LKBs) were developed for Portuguese, b...
Semantic textual similarity (STS) measures how semantically similar two sentences are. In the contex...
Representing words with semantic distributions to create ML models is a widely used technique to per...
Identifying similar and related words is not only key in natural language understanding but also a s...
Having in mind both the importance that semantic information plays nowadays in natural language proc...
<p>The identification of semantic relationships, as expressed between named entities in text, is an ...
This paper relates data on lexical availability with data on textual frequency of proverbs in Europ...
This dissertation proposes a set of procedures for the computational processing of Portuguese. Five ...
Recognizing textual entailment comprises the task of determining semantic entailment relations betwe...
Semantic relations between words are key to building systems that aim to understand and manipulate l...
The identification of causal relations from text is a mature problem in Natural Language Processing....
Recent literature has highlighted the extent to which inflectional paradigms are organised into syst...
Two sentences can be related in many different ways. Distinct tasks in natural language processing a...
We explored transformer-based language models for ranking instances of Portuguese lexico-semantic re...
Models of word embeddings are often assessed when solving syntactic and semantic analogies. Among th...
In the last decade, several lexical-semantic knowledge bases (LKBs) were developed for Portuguese, b...
Semantic textual similarity (STS) measures how semantically similar two sentences are. In the contex...
Representing words with semantic distributions to create ML models is a widely used technique to per...
Identifying similar and related words is not only key in natural language understanding but also a s...
Having in mind both the importance that semantic information plays nowadays in natural language proc...
<p>The identification of semantic relationships, as expressed between named entities in text, is an ...
This paper relates data on lexical availability with data on textual frequency of proverbs in Europ...
This dissertation proposes a set of procedures for the computational processing of Portuguese. Five ...
Recognizing textual entailment comprises the task of determining semantic entailment relations betwe...
Semantic relations between words are key to building systems that aim to understand and manipulate l...
The identification of causal relations from text is a mature problem in Natural Language Processing....
Recent literature has highlighted the extent to which inflectional paradigms are organised into syst...