Kees van Deemter

Also published as: Kees Van Deemter


2020

pdf bib
Chinese Long and Short Form Choice Exploiting Neural Network Language Modeling Approaches
Lin Li | Kees van Deemter | Denis Paperno
Proceedings of the 19th Chinese National Conference on Computational Linguistics

This paper presents our work in long and short form choice, a significant question of lexical choice, which plays an important role in many Natural Language Understanding tasks. Long and short form sharing at least one identical word meaning but with different number of syllables is a highly frequent linguistic phenomenon in Chinese like 老虎-虎(laohu-hu, tiger)

pdf bib
Lessons from Computational Modelling of Reference Production in Mandarin and English
Guanyi Chen | Kees van Deemter
Proceedings of the 13th International Conference on Natural Language Generation

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.

pdf bib
Gradations of Error Severity in Automatic Image Descriptions
Emiel van Miltenburg | Wei-Ting Lu | Emiel Krahmer | Albert Gatt | Guanyi Chen | Lin Li | Kees van Deemter
Proceedings of the 13th International Conference on Natural Language Generation

Earlier research has shown that evaluation metrics based on textual similarity (e.g., BLEU, CIDEr, Meteor) do not correlate well with human evaluation scores for automatically generated text. We carried out an experiment with Chinese speakers, where we systematically manipulated image descriptions to contain different kinds of errors. Because our manipulated descriptions form minimal pairs with the reference descriptions, we are able to assess the impact of different kinds of errors on the perceived quality of the descriptions. Our results show that different kinds of errors elicit significantly different evaluation scores, even though all erroneous descriptions differ in only one character from the reference descriptions. Evaluation metrics based solely on textual similarity are unable to capture these differences, which (at least partially) explains their poor correlation with human judgments. Our work provides the foundations for future work, where we aim to understand why different errors are seen as more or less severe.

pdf bib
Computational Interpretations of Recency for the Choice of Referring Expressions in Discourse
Fahime Same | Kees van Deemter
Proceedings of the First Workshop on Computational Approaches to Discourse

First, we discuss the most common linguistic perspectives on the concept of recency and propose a taxonomy of recency metrics employed in Machine Learning studies for choosing the form of referring expressions in discourse context. We then report on a Multi-Layer Perceptron study and a Sequential Forward Search experiment, followed by Bayes Factor analysis of the outcomes. The results suggest that recency metrics counting paragraphs and sentences contribute to referential choice prediction more than other recency-related metrics. Based on the results of our analysis, we argue that, sensitivity to discourse structure is important for recency metrics used in determining referring expression forms.

pdf bib
A Linguistic Perspective on Reference: Choosing a Feature Set for Generating Referring Expressions in Context
Fahime Same | Kees van Deemter
Proceedings of the 28th International Conference on Computational Linguistics

This paper reports on a structured evaluation of feature-based Machine Learning algorithms for selecting the form of a referring expression in discourse context. Based on this evaluation, we selected seven feature sets from the literature, amounting to 65 distinct linguistic features. The features were then grouped into 9 broad classes. After building Random Forest models, we used Feature Importance Ranking and Sequential Forward Search methods to assess the “importance” of the features. Combining the results of the two methods, we propose a consensus feature set. The 6 features in our consensus set come from 4 different classes, namely grammatical role, inherent features of the referent, antecedent form and recency.

pdf bib
What do you mean, BERT?
Timothee Mickus | Denis Paperno | Mathieu Constant | Kees van Deemter
Proceedings of the Society for Computation in Linguistics 2020

2019

pdf bib
Proceedings of the 12th International Conference on Natural Language Generation
Kees van Deemter | Chenghua Lin | Hiroya Takamura
Proceedings of the 12th International Conference on Natural Language Generation

pdf bib
Choosing between Long and Short Word Forms in Mandarin
Lin Li | Kees van Deemter | Denis Paperno | Jingyu Fan
Proceedings of the 12th International Conference on Natural Language Generation

Between 80% and 90% of all Chinese words have long and short form such as 老虎/虎 (lao-hu/hu , tiger) (Duanmu:2013). Consequently, the choice between long and short forms is a key problem for lexical choice across NLP and NLG. Following an earlier work on abbreviations in English (Mahowald et al, 2013), we bring a probabilistic perspective to these questions, using both a behavioral and a corpus-based approach. We hypothesized that there is a higher probability of choosing short form in supportive context than in neutral context in Mandarin. Consistent with our prediction, our findings revealed that predictability of contexts makes effect on speakers’ long and short form choice.

pdf bib
QTUNA: A Corpus for Understanding How Speakers Use Quantification
Guanyi Chen | Kees van Deemter | Silvia Pagliaro | Louk Smalbil | Chenghua Lin
Proceedings of the 12th International Conference on Natural Language Generation

A prominent strand of work in formal semantics investigates the ways in which human languages quantify over the elements of a set, as when we say “All A are B ”, “All except two A are B ”, “Only a few of the A are B ” and so on. Our aim is to build Natural Language Generation algorithms that mimic humans’ use of quantified expressions. To inform these algorithms, we conducted on a series of elicitation experiments in which human speakers were asked to perform a linguistic task that invites the use of quantified expressions. We discuss how these experiments were conducted and what corpora they gave rise to. We conduct an informal analysis of the corpora, and offer an initial assessment of the challenges that these corpora pose for Natural Language Generation. The dataset is available at: https://github.com/a-quei/qtuna.

pdf bib
Generating Quantified Descriptions of Abstract Visual Scenes
Guanyi Chen | Kees van Deemter | Chenghua Lin
Proceedings of the 12th International Conference on Natural Language Generation

Quantified expressions have always taken up a central position in formal theories of meaning and language use. Yet quantified expressions have so far attracted far less attention from the Natural Language Generation community than, for example, referring expressions. In an attempt to start redressing the balance, we investigate a recently developed corpus in which quantified expressions play a crucial role; the corpus is the result of a carefully controlled elicitation experiment, in which human participants were asked to describe visually presented scenes. Informed by an analysis of this corpus, we propose algorithms that produce computer-generated descriptions of a wider class of visual scenes, and we evaluate the descriptions generated by these algorithms in terms of their correctness, completeness, and human-likeness. We discuss what this exercise can teach us about the nature of quantification and about the challenges posed by the generation of quantified expressions.

2018

pdf bib
SimpleNLG-ZH: a Linguistic Realisation Engine for Mandarin
Guanyi Chen | Kees van Deemter | Chenghua Lin
Proceedings of the 11th International Conference on Natural Language Generation

We introduce SimpleNLG-ZH, a realisation engine for Mandarin that follows the software design paradigm of SimpleNLG (Gatt and Reiter, 2009). We explain the core grammar (morphology and syntax) and the lexicon of SimpleNLG-ZH, which is very different from English and other languages for which SimpleNLG engines have been built. The system was evaluated by regenerating expressions from a body of test sentences and a corpus of human-authored expressions. Human evaluation was conducted to estimate the quality of regenerated sentences.

pdf bib
Modelling Pro-drop with the Rational Speech Acts Model
Guanyi Chen | Kees van Deemter | Chenghua Lin
Proceedings of the 11th International Conference on Natural Language Generation

We extend the classic Referring Expressions Generation task by considering zero pronouns in “pro-drop” languages such as Chinese, modelling their use by means of the Bayesian Rational Speech Acts model (Frank and Goodman, 2012). By assuming that highly salient referents are most likely to be referred to by zero pronouns (i.e., pro-drop is more likely for salient referents than the less salient ones), the model offers an attractive explanation of a phenomenon not previously addressed probabilistically.

pdf bib
Generating Summaries of Sets of Consumer Products: Learning from Experiments
Kittipitch Kuptavanich | Ehud Reiter | Kees Van Deemter | Advaith Siddharthan
Proceedings of the 11th International Conference on Natural Language Generation

We explored the task of creating a textual summary describing a large set of objects characterised by a small number of features using an e-commerce dataset. When a set of consumer products is large and varied, it can be difficult for a consumer to understand how the products in the set differ; consequently, it can be challenging to choose the most suitable product from the set. To assist consumers, we generated high-level summaries of product sets. Two generation algorithms are presented, discussed, and evaluated with human users. Our evaluation results suggest a positive contribution to consumers’ understanding of the domain.

pdf bib
Meteorologists and Students: A resource for language grounding of geographical descriptors
Alejandro Ramos-Soto | Ehud Reiter | Kees van Deemter | Jose Alonso | Albert Gatt
Proceedings of the 11th International Conference on Natural Language Generation

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.

pdf bib
Statistical NLG for Generating the Content and Form of Referring Expressions
Xiao Li | Kees van Deemter | Chenghua Lin
Proceedings of the 11th International Conference on Natural Language Generation

This paper argues that a new generic approach to statistical NLG can be made to perform Referring Expression Generation (REG) successfully. The model does not only select attributes and values for referring to a target referent, but also performs Linguistic Realisation, generating an actual Noun Phrase. Our evaluations suggest that the attribute selection aspect of the algorithm exceeds classic REG algorithms, while the Noun Phrases generated are as similar to those in a previously developed corpus as were Noun Phrases produced by a new set of human speakers.

2017

pdf bib
Investigating the content and form of referring expressions in Mandarin: introducing the Mtuna corpus
Kees van Deemter | Le Sun | Rint Sybesma | Xiao Li | Bo Chen | Muyun Yang
Proceedings of the 10th International Conference on Natural Language Generation

East Asian languages are thought to handle reference differently from languages such as English, particularly in terms of the marking of definiteness and number. We present the first Data-Text corpus for Referring Expressions in Mandarin, and we use this corpus to test some initial hypotheses inspired by the theoretical linguistics literature. Our findings suggest that function words deserve more attention in Referring Expressions Generation than they have so far received, and they have a bearing on the debate about whether different languages make different trade-offs between clarity and brevity.

2016

pdf bib
Designing Algorithms for Referring with Proper Names
Kees van Deemter
Proceedings of the 9th International Natural Language Generation conference

pdf bib
Statistics-Based Lexical Choice for NLG from Quantitative Information
Xiao Li | Kees van Deemter | Chenghua Lin
Proceedings of the 9th International Natural Language Generation conference

2015

pdf bib
Ontology Authoring Inspired By Dialogue
Artemis Parvizi | Yuan Ren | Markel Vigo | Kees van Deemter | Chris Mellish | Jeff Z. Pan | Robert Stevens | Caroline Jay
Proceedings of the 1st Workshop on Language and Ontologies

2013

pdf bib
A Pilot Experiment in Knowledge Authoring as Dialogue
Artemis Parvizi | Caroline Jay | Christopher Mellish | Jeff Z. Pan | Yuan Ren | Robert Stevens | Kees van Deemter
Proceedings of the 10th International Conference on Computational Semantics (IWCS 2013) – Short Papers

pdf bib
Generation of Quantified Referring Expressions: Evidence from Experimental Data
Dale Barr | Kees van Deemter | Raquel Fernández
Proceedings of the 14th European Workshop on Natural Language Generation

pdf bib
Content Selection Challenge - University of Aberdeen Entry
Roman Kutlak | Chris Mellish | Kees van Deemter
Proceedings of the 14th European Workshop on Natural Language Generation

pdf bib
Generating Expressions that Refer to Visible Objects
Margaret Mitchell | Kees van Deemter | Ehud Reiter
Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2012

pdf bib
Computational Generation of Referring Expressions: A Survey
Emiel Krahmer | Kees van Deemter
Computational Linguistics, Volume 38, Issue 1 - March 2012

pdf bib
Blogging birds: Generating narratives about reintroduced species to promote public engagement
Advaith Siddharthan | Matthew Green | Kees van Deemter | Chris Mellish | René van der Wal
INLG 2012 Proceedings of the Seventh International Natural Language Generation Conference

2011

pdf bib
Two Approaches for Generating Size Modifiers
Margaret Mitchell | Kees van Deemter | Ehud Reiter
Proceedings of the 13th European Workshop on Natural Language Generation

pdf bib
Direction giving: an attempt to increase user engagement
Bob Duncan | Kees van Deemter
Proceedings of the 13th European Workshop on Natural Language Generation

2010

pdf bib
Natural Reference to Objects in a Visual Domain
Margaret Mitchell | Kees van Deemter | Ehud Reiter
Proceedings of the 6th International Natural Language Generation Conference

pdf bib
Charting the Potential of Description Logic for the Generation of Referring Expressions
Yuan Ren | Kees van Deemter | Jeff Z. Pan
Proceedings of the 6th International Natural Language Generation Conference

2009

pdf bib
A Hearer-Oriented Evaluation of Referring Expression Generation
Imtiaz Hussain Khan | Kees van Deemter | Graeme Ritchie | Albert Gatt | Alexandra A. Cleland
Proceedings of the 12th European Workshop on Natural Language Generation (ENLG 2009)

pdf bib
What Game Theory Can Do for NLG: The Case of Vague Language (Invited Talk)
Kees van Deemter
Proceedings of the 12th European Workshop on Natural Language Generation (ENLG 2009)

2008

pdf bib
Generation of Referring Expressions: Managing Structural Ambiguities
Imtiaz Hussain Khan | Kees van Deemter | Graeme Ritchie
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)

2007

pdf bib
Evaluating algorithms for the Generation of Referring Expressions using a balanced corpus
Albert Gatt | Ielka van der Sluis | Kees van Deemter
Proceedings of the Eleventh European Workshop on Natural Language Generation (ENLG 07)

pdf bib
Generating Referring Expressions: Making Referents Easy to Identify
Ivandré Paraboni | Kees van Deemter | Judith Masthoff
Computational Linguistics, Volume 33, Number 2, June 2007

pdf bib
Incremental Generation of Plural Descriptions: Similarity and Partitioning
Albert Gatt | Kees van Deemter
Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)

2006

pdf bib
Conceptual Coherence in the Generation of Referring Expressions
Albert Gatt | Kees van Deemter
Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions

pdf bib
Generating Referring Expressions that Involve Gradable Properties
Kees van Deemter
Computational Linguistics, Volume 32, Number 2, June 2006

pdf bib
Overspecified Reference in Hierarchical Domains: Measuring the Benefits for Readers
Ivandré Paraboni | Judith Masthoff | Kees van Deemter
Proceedings of the Fourth International Natural Language Generation Conference

pdf bib
The Clarity-Brevity Trade-off in Generating Referring Expressions
Imtiaz Hussain Khan | Graeme Ritchie | Kees van Deemter
Proceedings of the Fourth International Natural Language Generation Conference

pdf bib
Building a Semantically Transparent Corpus for the Generation of Referring Expressions.
Kees van Deemter | Ielka van der Sluis | Albert Gatt
Proceedings of the Fourth International Natural Language Generation Conference

2005

pdf bib
Squibs and Discussions: Real versus Template-Based Natural Language Generation: A False Opposition?
Kees van Deemter | Emiel Krahmer | Mariët Theune
Computational Linguistics, Volume 31, Number 1, March 2005

2002

pdf bib
Generating Referring Expressions: Boolean Extensions of the Incremental Algorithm
Kees van Deemter
Computational Linguistics, Volume 28, Number 1, March 2002

pdf bib
Generating Easy References: the Case of Document Deixis
Ivandre Paraboni | Kees van Deemter
Proceedings of the International Natural Language Generation Conference

2001

pdf bib
From RAGS to RICHES: Exploiting the Potential of a Flexible Generation Architecture
Lynne Cahill | John Carroll | Roger Evans | Daniel Paiva | Richard Power | Donia Scott | Kees van Deemter
Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics

pdf bib
Logical Form Equivalence: the Case of Referring Expressions Generation
Kees van Deemter | Magnús M. Halldórsson
Proceedings of the ACL 2001 Eighth European Workshop on Natural Language Generation (EWNLG)

2000

pdf bib
Coreference Annotation: Whither?
Rodger Kibble | Kees van Deemter
Proceedings of the Second International Conference on Language Resources and Evaluation (LREC’00)

pdf bib
On Coreferring: Coreference in MUC and Related Annotation Schemes
Kees van Deemter | Rodger Kibble
Computational Linguistics, Volume 26, Number 4, December 2000

pdf bib
Authoring Multimedia Documents using WYSIWYM Editing
Kees van Deemter | Richard Power
COLING 2000 Volume 1: The 18th International Conference on Computational Linguistics

pdf bib
Generating Vague Descriptions
Kees van Deemter
INLG’2000 Proceedings of the First International Conference on Natural Language Generation

1999

pdf bib
What is coreference, and what should coreference annotation be?
Kees van Deemter | Rodger Kibble
Coreference and Its Applications

1998

pdf bib
Coreference in Knowledge Editing
Kees van Deemter | Richard Power
The Computational Treatment of Nominals

1997

pdf bib
Context Modeling for Language and Speech Generation
Kees van Deemter
Interactive Spoken Dialog Systems: Bringing Speech and NLP Together in Real Applications

1990

pdf bib
Structured Meanings in Computational Linguistics
Kees van Deemter
COLING 1990 Volume 3: Papers presented to the 13th International Conference on Computational Linguistics