Challenges in building intelligent open-domain dialog systems

M Huang, X Zhu, J Gao - ACM Transactions on Information Systems …, 2020‏ - dl.acm.org
There is a resurgent interest in develo** intelligent open-domain dialog systems due to
the availability of large amounts of conversational data and the recent progress on neural …

Adversarial example generation with syntactically controlled paraphrase networks

M Iyyer, J Wieting, K Gimpel, L Zettlemoyer - arxiv preprint arxiv …, 2018‏ - arxiv.org
We propose syntactically controlled paraphrase networks (SCPNs) and use them to
generate adversarial examples. Given a sentence and a target syntactic form (eg, a …

What makes a good conversation? how controllable attributes affect human judgments

A See, S Roller, D Kiela, J Weston - arxiv preprint arxiv:1902.08654, 2019‏ - arxiv.org
A good conversation requires balance--between simplicity and detail; staying on topic and
changing it; asking questions and answering them. Although dialogue agents are commonly …

Polite dialogue generation without parallel data

T Niu, M Bansal - Transactions of the Association for Computational …, 2018‏ - direct.mit.edu
Stylistic dialogue response generation, with valuable applications in personality-based
conversational agents, is a challenging task because the response needs to be fluent …

Towards controllable story generation

N Peng, M Ghazvininejad, J May… - Proceedings of the First …, 2018‏ - aclanthology.org
We present a general framework of analyzing existing story corpora to generate controllable
and creative new stories. The proposed framework needs little manual annotation to achieve …

I like fish, especially dolphins: Addressing contradictions in dialogue modeling

Y Nie, M Williamson, M Bansal, D Kiela… - arxiv preprint arxiv …, 2020‏ - arxiv.org
To quantify how well natural language understanding models can capture consistency in a
general conversation, we introduce the DialoguE COntradiction DEtection task (DECODE) …

Neural syntactic preordering for controlled paraphrase generation

T Goyal, G Durrett - arxiv preprint arxiv:2005.02013, 2020‏ - arxiv.org
Paraphrasing natural language sentences is a multifaceted process: it might involve
replacing individual words or short phrases, local rearrangement of content, or high-level …

People's Perceptions Toward Bias and Related Concepts in Large Language Models: A Systematic Review

L Wang, M Song, R Rezapour, BC Kwon… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Large language models (LLMs) have brought breakthroughs in tasks including translation,
summarization, information retrieval, and language generation, gaining growing interest in …

Response generation by context-aware prototype editing

Y Wu, F Wei, S Huang, Y Wang, Z Li, M Zhou - Proceedings of the AAAI …, 2019‏ - aaai.org
Open domain response generation has achieved remarkable progress in recent years, but
sometimes yields short and uninformative responses. We propose a new paradigm …

Generating more interesting responses in neural conversation models with distributional constraints

A Baheti, A Ritter, J Li, B Dolan - arxiv preprint arxiv:1809.01215, 2018‏ - arxiv.org
Neural conversation models tend to generate safe, generic responses for most inputs. This
is due to the limitations of likelihood-based decoding objectives in generation tasks with …