Search Results for author:
Found 73 papers, 13 papers with code
The Natural Language Pipeline, Neural Text Generation and Explainability
End-to-end encoder-decoder approaches to data-to-text generation are often black boxes whose predictions are difficult to explain.
Controllable Sentence Simplification via Operation Classification
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.
Gathering Information and Engaging the User ComBot: A Task-Based, Serendipitous Dialog Model for Patient-Doctor Interactions
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.
A General Benchmarking Framework for Text Generation
The RDF-to-text task has recently gained substantial attention due to the continuous growth of RDF knowledge graphs in number and size.
Discourse-Based Sentence Splitting
Sentence splitting involves the segmentation of a sentence into two or more shorter sentences.
Generating Biographies on Wikipedia: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographies
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.
The 2020 Bilingual, Bi-Directional WebNLG+ Shared Task: Overview and Evaluation Results (WebNLG+ 2020)
WebNLG+ offers two challenges: (i) mapping sets of RDF triples to English or Russian text (generation) and (ii) converting English or Russian text to sets of RDF triples (semantic parsing).
Entity-Based Semantic Adequacy for Data-to-Text Generation
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.
Generating Questions from Wikidata Triples
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.
Question Generation in Knowledge-Driven Dialog: Explainability and Evaluation
We explore question generation in the context of knowledge-grounded dialogs focusing on explainability and evaluation.
Evaluating Document Simplification: On the Importance of Separately Assessing Simplicity and Meaning Preservation
In this paper, we focus on the evaluation of document-level text simplification and compare existing models using distinct metrics for meaning preservation and simplification.
Simplicity Level Estimate (SLE): A Learned Reference-Less Metric for Sentence Simplification
Automatic evaluation for sentence simplification remains a challenging problem.
Automatic and Human-AI Interactive Text Generation
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.
KGConv, a Conversational Corpus grounded in Wikidata
We present KGConv, a large, conversational corpus of 71k conversations where each question-answer pair is grounded in a Wikidata fact.
Context-Aware Document Simplification
To date, most work on text simplification has focused on sentence-level inputs.
Joint Representations of Text and Knowledge Graphs for Retrieval and Evaluation
A key feature of neural models is that they can produce semantic vector representations of objects (texts, images, speech, etc.)
Active Learning and Multi-label Classification for Ellipsis and Coreference Detection in Conversational Question-Answering
In human conversations, ellipsis and coreference are commonly occurring linguistic phenomena.
Generating Full Length Wikipedia Biographies: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographies
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.
Learning Health-Bots from Training Data that was Automatically Created using Paraphrase Detection and Expert Knowledge
Not only does it allow for the semi-automatic creation of large quantities of training data.
Multilingual AMR-to-Text Generation
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.
Augmenting Transformers with KNN-Based Composite Memory for Dialogue
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
Recent graph-to-text models generate text from graph-based data using either global or local aggregation to learn node representations.
Ranked #1 on
Graph-to-Sequence
on WebNLG
Quality of syntactic implication of RL-based sentence summarization
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.
LORIA / Lorraine University at Multilingual Surface Realisation 2019
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
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).
Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs
Query-based open-domain NLP tasks require information synthesis from long and diverse web results.
Ranked #4 on
Open-Domain Question Answering
on ELI5
Revisiting the Binary Linearization Technique for Surface Realization
End-to-end neural approaches have achieved state-of-the-art performance in many natural language processing (NLP) tasks.
Generating Text from Anonymised Structures
Surface realisation (SR) consists in generating a text from a meaning representations (MR).
Augmenting Transformers with KNN-Based Composite Memory
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
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.
Ranked #11 on
AMR-to-Text Generation
on LDC2017T10
Creating a Corpus for Russian Data-to-Text Generation Using Neural Machine Translation and Post-Editing
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.
Handling Rare Items in Data-to-Text Generation
Neural approaches to data-to-text generation generally handle rare input items using either delexicalisation or a copy mechanism.
Ranked #5 on
KG-to-Text Generation
on WebNLG 2.0 (Constrained)
Generating Syntactic Paraphrases
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.
Symbolic Priors for RNN-based Semantic Parsing
Seq2seq models based on Recurrent Neural Networks (RNNs) have recently received a lot of attention in the domain of Semantic Parsing for Question Answering.
Deep Learning Approaches to Text Production
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).
The WebNLG Challenge: Generating Text from RDF Data
The WebNLG challenge consists in mapping sets of RDF triples to text.
Split and Rephrase
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.
Creating Training Corpora for NLG Micro-Planners
In this paper, we present a novel framework for semi-automatically creating linguistically challenging micro-planning data-to-text corpora from existing Knowledge Bases.
Analysing Data-To-Text Generation Benchmarks
Recently, several data-sets associating data to text have been created to train data-to-text surface realisers.
A Statistical, Grammar-Based Approach to Microplanning
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.
Building RDF Content for Data-to-Text Generation
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.
Unsupervised Sentence Simplification Using Deep Semantics
We present a novel approach to sentence simplification which departs from previous work in two main ways.
Ranked #2 on
Text Simplification
on PWKP / WikiSmall
Representation of linguistic and domain knowledge for second language learning in virtual worlds
There has been much debate, both theoretical and practical, on how to link ontologies and lexicons in natural language processing (NLP) applications.
Building and Exploiting a Corpus of Dialog Interactions between French Speaking Virtual and Human Agents
We describe the acquisition of a dialog corpus for French based on multi-task human-machine interactions in a serious game setting.
