Sara Mendes

Enriching wordnets with new relations and with event and argument structures

This paper argues that wordnets, being concept-based computational lexica, should include information on event and argument structures. This general approach is relevant both for allowing computational grammars to cope with a number of different lexical semantics phenomena, as well as for enabling inference applications to obtain finer-grained results. We also propose new relations in order to adequately model non explicit information and cross-part-of-speech relations.

Reading Between the Lines: Overcoming Data Sparsity for Accurate Classification of Lexical Relationships

The lexical semantic relationships between word pairs are key features for many NLP tasks. Most approaches for automatically classifying related word pairs are hindered by data sparsity because of their need to observe two words co-occurring in order to detect the lexical relation holding between them. Even when mining very large corpora, not every related word pair co-occurs. Using novel representations based on graphs and word embeddings, we present two systems that are able to predict relations between words, even when these are never found in the same sentence in a given corpus. In two experiments, we demonstrate superior performance of both approaches over the state of the art, achieving significant gains in recall.

Modeling Adjectives in Computational Relational Lexica

In this paper we propose a small set of lexical conceptual relations which allow to encode adjectives in computational relational lexica in a principled and integrated way. Our main motivation comes from the fact that adjectives and certain classes of verbs, related in a way or another with adjectives, do not have a satisfactory representation in this kind of lexica. This is due to a great extent to the heterogeneity of their semantic and syntactic properties. We sustain that such properties are mostly derived from the relations holding between adjectives and other POS. Accordingly, our proposal is mainly concerned with the specification of appropriate cross-POS relations to encode adjectives in lexica of the type considered here.

Encoding event and argument structures in wordnets

In this paper we propose the codification of argument and event structures in wordnets, providing information on selection properties, semantic incorporation phenomena and internal properties of events, in what we claimto be an affordable procedure. We propose an explicit expression of argument structure, including default and shadow arguments, through three new relations and a new order feature. As synsets in wordnets are associated to a given POS, information on the selection properties of lexical items is added. We show that the systematic encoding of event structure information, through five new features at synset level, besides providing the grounds for describing the order of arguments, enriches the descriptive power of these resources. In doing so, we crucially contribute to making wordnets rich and structured repositories of lexical semantic information, that allow for the extraction of argument and event structures of lexical items, thus enhancing their usability in NLP systems.

Portuguese Controlled Language: Coping with Ambiguity

This paper focuses on strategies to avoid lexical related ambiguity, induced by polysemy or by syntactic function effects, in the context of a system to control Portuguese as a source language for machine translation. This system, which is being developed under wider scope ongoing research, involves two main components - a controlled language for Portuguese and a tool to evaluate the conformity of texts with the controlled language. In a subsidiary way, it also makes use of the Portuguese WordNet (WordNet.PT).

Lexical-conceptual relations as qualia role encoders

In this paper we show how wordnets can be used for building computational lexica that support generative processes accounting for phenomena such as the creation of meaning in context. We propose the integration of qualia information in wordnets through the association of lexical-conceptual relations to qualia roles, in what is a simple and low cost procedure, as it makes use of information already encoded in wordnets. This association between lexical-conceptual relations and qualia aspects allows us to describe the qualia structure of lexical items in a consistent way, without any loss of information and with the advantage of identifying the semantic predicates that can be values of qualia roles.