This work presents our efforts to reproduce the results of the human
eva...
This paper describes the systems submitted by team6 for ChatEval, the DS...
Hallucinations in text generation occur when the system produces text th...
Instructions-tuned Large Language Models (LLMs) gained recently huge
pop...
Heterogenity of data-to-text generation datasets limits the research on
...
We present MooseNet, a trainable speech metric that predicts listeners' ...
Pretrained language models (PLMs) for data-to-text (D2T) generation can ...
We present a novel architecture for explainable modeling of task-oriente...
We introduce AARGH, an end-to-end task-oriented dialog system combining
...
We present a novel approach to generating scripts by using agents with
d...
In data-to-text (D2T) generation, training on in-domain data leads to
ov...
One of the most challenging aspects of current single-document news
summ...
We observe a severe under-reporting of the different kinds of errors tha...
We present AGGGEN (pronounced 'again'), a data-to-text model which
re-in...
The MultiWOZ dataset (Budzianowski et al.,2018) is frequently used for
b...
We present the first version of a system for interactive generation of
t...
Attention-based pre-trained language models such as GPT-2 brought
consid...
We introduce GEM, a living benchmark for natural language Generation (NL...
A major challenge in evaluating data-to-text (D2T) generation is measuri...
We present a novel approach to data-to-text generation based on iterativ...
While recent neural sequence-to-sequence models have greatly improved th...
We introduce an approach to multilingual speech synthesis which uses the...
We present THEaiTRE, a starting project aimed at automatic generation of...
Neural natural language generation (NNLG) systems are known for their
pa...
We present the first dataset targeted at end-to-end NLG in Czech in the
...
We present a recurrent neural network based system for automatic quality...
We present the first complete spoken dialogue system driven by a
multi-d...
This paper provides a detailed summary of the first shared task on End-t...
The overall objective of 'social' dialogue systems is to support engagin...
In this work, we investigate the task of textual response generation in ...
Multimodal search-based dialogue is a challenging new task: It extends
v...
This paper summarises the experimental setup and results of the first sh...
We present three enhancements to existing encoder-decoder models for
ope...
Human evaluation for natural language generation (NLG) often suffers fro...
Open-domain social dialogue is one of the long-standing goals of Artific...
Traditional automatic evaluation measures for natural language generatio...
The majority of NLG evaluation relies on automatic metrics, such as BLEU...
We argue that there are currently two major bottlenecks to the commercia...
This paper describes the E2E data, a new dataset for training end-to-end...
We present a novel natural language generation system for spoken dialogu...
We present a natural language generator based on the sequence-to-sequenc...