Share This Author
The E2E Dataset: New Challenges For End-to-End Generation
The E2E dataset poses new challenges: (1) its human reference texts show more lexical richness and syntactic variation, including discourse phenomena; (2) generating from this set requires content selection, which promises more natural, varied and less template-like system utterances.
Why We Need New Evaluation Metrics for NLG
A wide range of metrics are investigated, including state-of-the-art word-based and novel grammar-based ones, and it is demonstrated that they only weakly reflect human judgements of system outputs as generated by data-driven, end-to-end NLG.
Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings
We present a natural language generator based on the sequence-to-sequence approach that can be trained to produce natural language strings as well as deep syntax dependency trees from input dialogue…
Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
Findings of the E2E NLG Challenge
This paper summarises the experimental setup and results of the first shared task on end-to-end (E2E) natural language generation (NLG) in spoken dialogue systems, and compares 62 systems submitted by 17 institutions, covering a wide range of approaches, including machine learning architectures.
CzEng 1.6: Enlarged Czech-English Parallel Corpus with Processing Tools Dockered
The complete annotation pipeline as a virtual machine in the Docker virtualization toolkit is released, equipped with automatic annotation at a deep syntactic level of representation and alternatively in Universal Dependencies.
Semantic Noise Matters for Neural Natural Language Generation
The impact of semantic noise on state-of-the-art NNLG models which implement different semantic control mechanisms is shown and it is found that cleaned data can improve semantic correctness by up to 97%, while maintaining fluency.
The Joy of Parallelism with CzEng 1.0
Key properties of the released resource including the distribution of text domains, the corpus data formats, and a toolkit to handle the provided rich annotation are described, including the procedure of the rich annotation (incl. co-reference resolution) and of the automatic filtering.
RankME: Reliable Human Ratings for Natural Language Generation
This work presents a novel rank-based magnitude estimation method (RankME), which combines the use of continuous scales and relative assessments, and shows that RankME significantly improves the reliability and consistency of human ratings compared to traditional evaluation methods.
Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity
A measure of coherence is introduced as the GloVe embedding similarity between the dialogue context and the generated response to improve coherence and diversity in encoder-decoder models for open-domain conversational agents.