Search Results for author: Kees Van Deemter

Found 47 papers, 6 papers with code

Towards Generating Effective Explanations of Logical Formulas: Challenges and Strategies

no code implementations ACL (NL4XAI, INLG) 2020 Alexandra Mayn, Kees Van Deemter

While the problem of natural language generation from logical formulas has a long tradition, thus far little attention has been paid to ensuring that the generated explanations are optimally effective for the user.

Text Generation

Chinese Long and Short Form Choice Exploiting Neural Network Language Modeling Approaches

no code implementations CCL 2020 Lin Li, Kees Van Deemter, Denis Paperno

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.

Language Modelling Natural Language Understanding

Using BERT for choosing classifiers in Mandarin

no code implementations INLG (ACL) 2021 Jani Järnfors, Guanyi Chen, Kees Van Deemter, Rint Sybesma

Choosing the most suitable classifier in a linguistic context is a well-known problem in the production of Mandarin and many other languages.

Gradations of Error Severity in Automatic Image Descriptions

no code implementations INLG (ACL) 2020 Emiel van Miltenburg, Wei-Ting Lu, Emiel Krahmer, Albert Gatt, Guanyi Chen, Lin Li, Kees Van Deemter

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.

Computational Interpretations of Recency for the Choice of Referring Expressions in Discourse

no code implementations EMNLP (CODI) 2020 Fahime Same, Kees Van Deemter

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.

Referring Expression

Computational Modelling of Plurality and Definiteness in Chinese Noun Phrases

1 code implementation7 Mar 2024 Yuqi Liu, Guanyi Chen, Kees Van Deemter

In this paper, we focus on the omission of the plurality and definiteness markers in Chinese noun phrases (NPs) to investigate the predictability of their intended meaning given the contexts.

Intrinsic Task-based Evaluation for Referring Expression Generation

no code implementations12 Feb 2024 Guanyi Chen, Fahime Same, Kees Van Deemter

Recently, a human evaluation study of Referring Expression Generation (REG) models had an unexpected conclusion: on \textsc{webnlg}, Referring Expressions (REs) generated by the state-of-the-art neural models were not only indistinguishable from the REs in \textsc{webnlg} but also from the REs generated by a simple rule-based system.

Referring Expression Referring expression generation +1

The Pitfalls of Defining Hallucination

no code implementations15 Jan 2024 Kees Van Deemter

To substantiate this claim, I examine current classifications of hallucination and omission in Data-text NLG, and I propose a logic-based synthesis of these classfications.

Hallucination nlg evaluation +1

Models of reference production: How do they withstand the test of time?

1 code implementation27 Jul 2023 Fahime Same, Guanyi Chen, Kees Van Deemter

We conclude that GREC can no longer be regarded as offering a reliable assessment of models' ability to mimic human reference production, because the results are highly impacted by the choice of corpus and evaluation metrics.

feature selection

Does ChatGPT have Theory of Mind?

no code implementations23 May 2023 Bart Holterman, Kees Van Deemter

Theory of Mind (ToM) is the ability to understand human thinking and decision-making, an ability that plays a crucial role in social interaction between people, including linguistic communication.

Decision Making

Interpreting Vision and Language Generative Models with Semantic Visual Priors

no code implementations28 Apr 2023 Michele Cafagna, Lina M. Rojas-Barahona, Kees Van Deemter, Albert Gatt

When applied to Image-to-text models, interpretability methods often provide token-by-token explanations namely, they compute a visual explanation for each token of the generated sequence.

HL Dataset: Visually-grounded Description of Scenes, Actions and Rationales

1 code implementation23 Feb 2023 Michele Cafagna, Kees Van Deemter, Albert Gatt

We present the High-Level Dataset a dataset extending 14997 images from the COCO dataset, aligned with a new set of 134, 973 human-annotated (high-level) captions collected along three axes: scenes, actions, and rationales.

Common Sense Reasoning Vocal Bursts Intensity Prediction

Assessing Neural Referential Form Selectors on a Realistic Multilingual Dataset

no code implementations10 Oct 2022 Guanyi Chen, Fahime Same, Kees Van Deemter

Previous work on Neural Referring Expression Generation (REG) all uses WebNLG, an English dataset that has been shown to reflect a very limited range of referring expression (RE) use.

Referring Expression Referring expression generation

Understanding the Use of Quantifiers in Mandarin

no code implementations24 Sep 2022 Guanyi Chen, Kees Van Deemter

We introduce a corpus of short texts in Mandarin, in which quantified expressions figure prominently.

The Role of Explanatory Value in Natural Language Processing

no code implementations13 Sep 2022 Kees Van Deemter

A key aim of science is explanation, yet the idea of explaining language phenomena has taken a backseat in mainstream Natural Language Processing (NLP) and many other areas of Artificial Intelligence.

What Vision-Language Models `See' when they See Scenes

no code implementations15 Sep 2021 Michele Cafagna, Kees Van Deemter, Albert Gatt

Images can be described in terms of the objects they contain, or in terms of the types of scene or place that they instantiate.

Object

What can Neural Referential Form Selectors Learn?

no code implementations INLG (ACL) 2021 Guanyi Chen, Fahime Same, Kees Van Deemter

Despite achieving encouraging results, neural Referring Expression Generation models are often thought to lack transparency.

Position Referring Expression +2

A Linguistic Perspective on Reference: Choosing a Feature Set for Generating Referring Expressions in Context

no code implementations COLING 2020 Fahime Same, Kees Van Deemter

This paper reports on a structured evaluation of feature-based Machine Learning algorithms for selecting the form of a referring expression in discourse context.

Feature Importance Referring Expression

Lessons from Computational Modelling of Reference Production in Mandarin and English

no code implementations INLG (ACL) 2020 Guanyi Chen, Kees Van Deemter

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.

Referring Expression Referring expression generation

A Text Reassembling Approach to Natural Language Generation

no code implementations16 May 2020 Xiao Li, Kees Van Deemter, Chenghua Lin

Recent years have seen a number of proposals for performing Natural Language Generation (NLG) based in large part on statistical techniques.

Text Generation

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

no code implementations13 Nov 2019 Timothee Mickus, Denis Paperno, Mathieu Constant, Kees Van Deemter

Contextualized word embeddings, i. e. vector representations for words in context, are naturally seen as an extension of previous noncontextual distributional semantic models.

Position Sentence +1

QTUNA: A Corpus for Understanding How Speakers Use Quantification

1 code implementation WS 2019 Guanyi Chen, Kees Van Deemter, Silvia Pagliaro, Louk Smalbil, Chenghua Lin

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.

Text Generation

Choosing between Long and Short Word Forms in Mandarin

no code implementations WS 2019 Lin Li, Kees Van Deemter, Denis Paperno, Jingyu Fan

Between 80{\%} and 90{\%} of all Chinese words have long and short form such as 老虎/虎 (lao-hu/hu , tiger) (Duanmu:2013).

Generating Quantified Descriptions of Abstract Visual Scenes

no code implementations WS 2019 Guanyi Chen, Kees Van Deemter, Chenghua Lin

Quantified expressions have always taken up a central position in formal theories of meaning and language use.

Position Text Generation

SimpleNLG-ZH: a Linguistic Realisation Engine for Mandarin

1 code implementation WS 2018 Guanyi Chen, Kees Van Deemter, Chenghua Lin

We introduce SimpleNLG-ZH, a realisation engine for Mandarin that follows the software design paradigm of SimpleNLG (Gatt and Reiter, 2009).

Morphological Inflection Text Generation

Statistical NLG for Generating the Content and Form of Referring Expressions

no code implementations WS 2018 Xiao Li, Kees Van Deemter, Chenghua Lin

This paper argues that a new generic approach to statistical NLG can be made to perform Referring Expression Generation (REG) successfully.

Attribute Referring Expression +2

Generating Summaries of Sets of Consumer Products: Learning from Experiments

no code implementations WS 2018 Kittipitch Kuptavanich, Ehud Reiter, Kees Van Deemter, Advaith Siddharthan

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.

Text Generation

Modelling Pro-drop with the Rational Speech Acts Model

no code implementations WS 2018 Guanyi Chen, Kees Van Deemter, Chenghua Lin

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).

Coreference Resolution Machine Translation +1

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

no code implementations WS 2018 Alejandro Ramos-Soto, Ehud Reiter, Kees Van Deemter, Jose M. Alonso, Albert Gatt

We present a data resource which can be useful for research purposes on language grounding tasks in the context of geographical referring expression generation.

Referring Expression Referring expression generation

Investigating the content and form of referring expressions in Mandarin: introducing the Mtuna corpus

no code implementations WS 2017 Kees van Deemter, Le Sun, Rint Sybesma, Xiao Li, Bo Chen, Muyun Yang

East Asian languages are thought to handle reference differently from languages such as English, particularly in terms of the marking of definiteness and number.

Text Generation

An Empirical Approach for Modeling Fuzzy Geographical Descriptors

no code implementations30 Mar 2017 Alejandro Ramos-Soto, Jose M. Alonso, Ehud Reiter, Kees Van Deemter, Albert Gatt

We present a novel heuristic approach that defines fuzzy geographical descriptors using data gathered from a survey with human subjects.

Referring Expression Referring expression generation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.