Search Results for author: Claire Gardent

Found 71 papers, 13 papers with code

Gathering Information and Engaging the User ComBot: A Task-Based, Serendipitous Dialog Model for Patient-Doctor Interactions

no code implementations NAACL (NLPMC) 2021 Anna Liednikova, Philippe Jolivet, Alexandre Durand-Salmon, Claire Gardent

We focus on dialog models in the context of clinical studies where the goal is to help gather, in addition to the close information collected based on a questionnaire, serendipitous information that is medically relevant.

Controllable Sentence Simplification via Operation Classification

1 code implementation Findings (NAACL) 2022 Liam Cripwell, Joël Legrand, Claire Gardent

Different types of transformations have been used to model sentence simplification ranging from mainly local operations such as phrasal or lexical rewriting, deletion and re-ordering to the more global affecting the whole input sentence such as sentence rephrasing, copying and splitting.

Classification Sentence

The Natural Language Pipeline, Neural Text Generation and Explainability

no code implementations ACL (NL4XAI, INLG) 2020 Juliette Faille, Albert Gatt, Claire Gardent

End-to-end encoder-decoder approaches to data-to-text generation are often black boxes whose predictions are difficult to explain.

Data-to-Text Generation

Generating Questions from Wikidata Triples

no code implementations LREC 2022 Kelvin Han, Thiago castro Ferreira, Claire Gardent

Question generation from knowledge bases (or knowledge base question generation, KBQG) is the task of generating questions from structured database information, typically in the form of triples representing facts.

Knowledge Base Question Answering Question Generation +1

Generating Biographies on Wikipedia: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographies

no code implementations ACL 2022 Angela Fan, Claire Gardent

To assess the impact of available web evidence on the output text, we compare the performance of our approach when generating biographies about women (for which less information is available on the web) vs. biographies generally.

Retrieval

Entity-Based Semantic Adequacy for Data-to-Text Generation

no code implementations Findings (EMNLP) 2021 Juliette Faille, Albert Gatt, Claire Gardent

While powerful pre-trained language models have improved the fluency of text generation models, semantic adequacy -the ability to generate text that is semantically faithful to the input- remains an unsolved issue.

Data-to-Text Generation

Automatic and Human-AI Interactive Text Generation

no code implementations5 Oct 2023 Yao Dou, Philippe Laban, Claire Gardent, Wei Xu

In this tutorial, we focus on text-to-text generation, a class of natural language generation (NLG) tasks, that takes a piece of text as input and then generates a revision that is improved according to some specific criteria (e. g., readability or linguistic styles), while largely retaining the original meaning and the length of the text.

Paraphrase Generation Style Transfer +2

KGConv, a Conversational Corpus grounded in Wikidata

no code implementations29 Aug 2023 Quentin Brabant, Gwenole Lecorve, Lina M. Rojas-Barahona, Claire Gardent

We present KGConv, a large, conversational corpus of 71k conversations where each question-answer pair is grounded in a Wikidata fact.

Knowledge Graphs Question Answering +3

Context-Aware Document Simplification

1 code implementation10 May 2023 Liam Cripwell, Joël Legrand, Claire Gardent

To date, most work on text simplification has focused on sentence-level inputs.

Sentence Text Simplification

Joint Representations of Text and Knowledge Graphs for Retrieval and Evaluation

no code implementations28 Feb 2023 Teven Le Scao, Claire Gardent

A key feature of neural models is that they can produce semantic vector representations of objects (texts, images, speech, etc.)

Data Augmentation Knowledge Graphs +1

Generating Full Length Wikipedia Biographies: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographies

no code implementations12 Apr 2022 Angela Fan, Claire Gardent

To assess the impact of available web evidence on the output text, we compare the performance of our approach when generating biographies about women (for which less information is available on the web) vs. biographies generally.

Retrieval

Multilingual AMR-to-Text Generation

no code implementations EMNLP 2020 Angela Fan, Claire Gardent

Generating text from structured data is challenging because it requires bridging the gap between (i) structure and natural language (NL) and (ii) semantically underspecified input and fully specified NL output.

AMR-to-Text Generation Text Generation

Augmenting Transformers with KNN-Based Composite Memory for Dialogue

no code implementations27 Apr 2020 Angela Fan, Claire Gardent, Chloe Braud, Antoine Bordes

Various machine learning tasks can benefit from access to external information of different modalities, such as text and images.

Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs

1 code implementation29 Jan 2020 Leonardo F. R. Ribeiro, Yue Zhang, Claire Gardent, Iryna Gurevych

Recent graph-to-text models generate text from graph-based data using either global or local aggregation to learn node representations.

Graph-to-Sequence KG-to-Text Generation +1

Quality of syntactic implication of RL-based sentence summarization

no code implementations11 Dec 2019 Hoa T. Le, Christophe Cerisara, Claire Gardent

Work on summarization has explored both reinforcement learning (RL) optimization using ROUGE as a reward and syntax-aware models, such as models those input is enriched with part-of-speech (POS)-tags and dependency information.

POS Reinforcement Learning (RL) +2

LORIA / Lorraine University at Multilingual Surface Realisation 2019

no code implementations WS 2019 Anastasia Shimorina, Claire Gardent

This paper presents the LORIA / Lorraine University submission at the Multilingual Surface Realisation shared task 2019 for the shallow track.

Surface Realisation Using Full Delexicalisation

no code implementations IJCNLP 2019 Anastasia Shimorina, Claire Gardent

Surface realisation (SR) maps a meaning representation to a sentence and can be viewed as consisting of three subtasks: word ordering, morphological inflection and contraction generation (e. g., clitic attachment in Portuguese or elision in French).

Morphological Inflection Sentence

Revisiting the Binary Linearization Technique for Surface Realization

no code implementations WS 2019 Yevgeniy Puzikov, Claire Gardent, Ido Dagan, Iryna Gurevych

End-to-end neural approaches have achieved state-of-the-art performance in many natural language processing (NLP) tasks.

Decision Making

Generating Text from Anonymised Structures

no code implementations WS 2019 Emilie Colin, Claire Gardent

Surface realisation (SR) consists in generating a text from a meaning representations (MR).

Text Generation

Augmenting Transformers with KNN-Based Composite Memory

no code implementations25 Sep 2019 Angela Fan, Claire Gardent, Chloe Braud, Antoine Bordes

Various machine learning tasks can benefit from access to external information of different modalities, such as text and images.

Enhancing AMR-to-Text Generation with Dual Graph Representations

1 code implementation IJCNLP 2019 Leonardo F. R. Ribeiro, Claire Gardent, Iryna Gurevych

Generating text from graph-based data, such as Abstract Meaning Representation (AMR), is a challenging task due to the inherent difficulty in how to properly encode the structure of a graph with labeled edges.

AMR-to-Text Generation Data-to-Text Generation +1

Creating a Corpus for Russian Data-to-Text Generation Using Neural Machine Translation and Post-Editing

1 code implementation WS 2019 Anastasia Shimorina, Elena Khasanova, Claire Gardent

In this paper, we propose an approach for semi-automatically creating a data-to-text (D2T) corpus for Russian that can be used to learn a D2T natural language generation model.

Data-to-Text Generation Machine Translation +1

Handling Rare Items in Data-to-Text Generation

2 code implementations WS 2018 Anastasia Shimorina, Claire Gardent

Neural approaches to data-to-text generation generally handle rare input items using either delexicalisation or a copy mechanism.

KG-to-Text Generation

Generating Syntactic Paraphrases

no code implementations EMNLP 2018 Emilie Colin, Claire Gardent

We study the automatic generation of syntactic paraphrases using four different models for generation: data-to-text generation, text-to-text generation, text reduction and text expansion, We derive training data for each of these tasks from the WebNLG dataset and we show (i) that conditioning generation on syntactic constraints effectively permits the generation of syntactically distinct paraphrases for the same input and (ii) that exploiting different types of input (data, text or data+text) further increases the number of distinct paraphrases that can be generated for a given input.

Data-to-Text Generation Machine Translation +4

Symbolic Priors for RNN-based Semantic Parsing

1 code implementation20 Sep 2018 Chunyang Xiao, Marc Dymetman, Claire Gardent

Seq2seq models based on Recurrent Neural Networks (RNNs) have recently received a lot of attention in the domain of Semantic Parsing for Question Answering.

Question Answering Semantic Parsing

Deep Learning Approaches to Text Production

no code implementations NAACL 2018 Claire Gardent, Shashi Narayan

Each text production task raises a slightly different communication goal (e. g, how to take the dialogue context into account when producing a dialogue turn; how to detect and merge relevant information when summarising a text; or how to produce a well-formed text that correctly capture the information contained in some input data in the case of data-to-text generation).

Data-to-Text Generation Machine Translation +4

Split and Rephrase

2 code implementations EMNLP 2017 Shashi Narayan, Claire Gardent, Shay B. Cohen, Anastasia Shimorina

We propose a new sentence simplification task (Split-and-Rephrase) where the aim is to split a complex sentence into a meaning preserving sequence of shorter sentences.

Machine Translation Sentence +2

Creating Training Corpora for NLG Micro-Planners

no code implementations ACL 2017 Claire Gardent, Anastasia Shimorina, Shashi Narayan, Laura Perez-Beltrachini

In this paper, we present a novel framework for semi-automatically creating linguistically challenging micro-planning data-to-text corpora from existing Knowledge Bases.

Data-to-Text Generation Referring Expression +3

Analysing Data-To-Text Generation Benchmarks

no code implementations WS 2017 Laura Perez-Beltrachini, Claire Gardent

Recently, several data-sets associating data to text have been created to train data-to-text surface realisers.

Data-to-Text Generation

A Statistical, Grammar-Based Approach to Microplanning

no code implementations CL 2017 Claire Gardent, Laura Perez-Beltrachini

Although there has been much work in recent years on data-driven natural language generation, little attention has been paid to the fine-grained interactions that arise during microplanning between aggregation, surface realization, and sentence segmentation.

Sentence Sentence segmentation +1

Building RDF Content for Data-to-Text Generation

no code implementations COLING 2016 Laura Perez-Beltrachini, Rania Sayed, Claire Gardent

In Natural Language Generation (NLG), one important limitation is the lack of common benchmarks on which to train, evaluate and compare data-to-text generators.

Data-to-Text Generation

Representation of linguistic and domain knowledge for second language learning in virtual worlds

no code implementations LREC 2012 Alex Denis, re, Ingrid Falk, Claire Gardent, Laura Perez-Beltrachini

There has been much debate, both theoretical and practical, on how to link ontologies and lexicons in natural language processing (NLP) applications.

Text Generation

Building and Exploiting a Corpus of Dialog Interactions between French Speaking Virtual and Human Agents

no code implementations LREC 2012 Lina M. Rojas-Barahona, Alej Lorenzo, ra, Claire Gardent

We describe the acquisition of a dialog corpus for French based on multi-task human-machine interactions in a serious game setting.

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