arXiv subjects

Kees van Deemter

Publications and source records attributed to Kees van Deemter.

26 records · Page 2Linked to original sources

arXiv2021

Lessons from Computational Modelling of Reference Production in Mandarin and English

Referring expression generation (REG) algorithms offer computational models of the production of referring expressions. In earlier work, a corpus of referring expressions (REs) in Mandarin was introduced. In the present paper, we annotate this corpus, evaluate classic REG algorithms on it, and compare the results with earlier results on the evaluation of REG for English referring expressions. Next, we offer an in-depth analysis of the corpus, focusing on issues that arise from the grammar of Mandarin. We discuss shortcomings of previous REG evaluations that came to light during our investigation and we highlight some surprising results. Perhaps most strikingly, we found a much higher proportion of under-specified expressions than previous studies had suggested, not just in Mandarin but in English as well.

cs.CL↗

arXiv2021

What can Neural Referential Form Selectors Learn?

Despite achieving encouraging results, neural Referring Expression Generation models are often thought to lack transparency. We probed neural Referential Form Selection (RFS) models to find out to what extent the linguistic features influencing the RE form are learnt and captured by state-of-the-art RFS models. The results of 8 probing tasks show that all the defined features were learnt to some extent. The probing tasks pertaining to referential status and syntactic position exhibited the highest performance. The lowest performance was achieved by the probing models designed to predict discourse structure properties beyond the sentence level.

cs.CL↗

arXiv2020

A Text Reassembling Approach to Natural Language Generation

Recent years have seen a number of proposals for performing Natural Language Generation (NLG) based in large part on statistical techniques. Despite having many attractive features, we argue that these existing approaches nonetheless have some important drawbacks, sometimes because the approach in question is not fully statistical (i.e., relies on a certain amount of handcrafting), sometimes because the approach in question lacks transparency. Focussing on some of the key NLG tasks (namely Content Selection, Lexical Choice, and Linguistic Realisation), we propose a novel approach, called the Text Reassembling approach to NLG (TRG), which approaches the ideal of a purely statistical approach very closely, and which is at the same time highly transparent. We evaluate the TRG approach and discuss how TRG may be extended to deal with other NLG tasks, such as Document Structuring, and Aggregation. We discuss the strengths and limitations of TRG, concluding that the method may hold particular promise for domain experts who want to build an NLG system despite having little expertise in linguistics and NLG.

cs.CL↗

arXiv2020

What do you mean, BERT? Assessing BERT as a Distributional Semantics Model

Contextualized word embeddings, i.e. vector representations for words in context, are naturally seen as an extension of previous noncontextual distributional semantic models. In this work, we focus on BERT, a deep neural network that produces contextualized embeddings and has set the state-of-the-art in several semantic tasks, and study the semantic coherence of its embedding space. While showing a tendency towards coherence, BERT does not fully live up to the natural expectations for a semantic vector space. In particular, we find that the position of the sentence in which a word occurs, while having no meaning correlates, leaves a noticeable trace on the word embeddings and disturbs similarity relationships.

cs.CL↗

arXiv2018

Meteorologists and Students: A resource for language grounding of geographical descriptors

We present a data resource which can be useful for research purposes on language grounding tasks in the context of geographical referring expression generation. The resource is composed of two data sets that encompass 25 different geographical descriptors and a set of associated graphical representations, drawn as polygons on a map by two groups of human subjects: teenage students and expert meteorologists.

cs.CL↗

arXiv2017

An Empirical Approach for Modeling Fuzzy Geographical Descriptors

We present a novel heuristic approach that defines fuzzy geographical descriptors using data gathered from a survey with human subjects. The participants were asked to provide graphical interpretations of the descriptors `north' and `south' for the Galician region (Spain). Based on these interpretations, our approach builds fuzzy descriptors that are able to compute membership degrees for geographical locations. We evaluated our approach in terms of efficiency and precision. The fuzzy descriptors are meant to be used as the cornerstones of a geographical referring expression generation algorithm that is able to linguistically characterize geographical locations and regions. This work is also part of a general research effort that intends to establish a methodology which reunites the empirical studies traditionally practiced in data-to-text and the use of fuzzy sets to model imprecision and vagueness in words and expressions for text generation purposes.

cs.AI↗

arXiv2003

Towards Automated Generation of Scripted Dialogue: Some Time-Honoured Strategies

The main aim of this paper is to introduce automated generation of scripted dialogue as a worthwhile topic of investigation. In particular the fact that scripted dialogue involves two layers of communication, i.e., uni-directional communication between the author and the audience of a scripted dialogue and bi-directional pretended communication between the characters featuring in the dialogue, is argued to raise some interesting issues. Our hope is that the combined study of the two layers will forge links between research in text generation and dialogue processing. The paper presents a first attempt at creating such links by studying three types of strategies for the automated generation of scripted dialogue. The strategies are derived from examples of human-authored and naturally occurring dialogue.

cs.CL↗

arXiv2003

Dialogue as Discourse: Controlling Global Properties of Scripted Dialogue

This paper explains why scripted dialogue shares some crucial properties with discourse. In particular, when scripted dialogues are generated by a Natural Language Generation system, the generator can apply revision strategies that cannot normally be used when the dialogue results from an interaction between autonomous agents (i.e., when the dialogue is not scripted). The paper explains that the relevant revision operators are best applied at the level of a dialogue plan and discusses how the generator may decide when to apply a given revision operator.

cs.CL↗