The concrete distribution: A continuous relaxation of discrete random variables

CJ Maddison, A Mnih, YW Teh - ar** natural language utterances into structured meaning
representations. In this work, we propose a structure-aware neural architecture which …

Emergence of language with multi-agent games: Learning to communicate with sequences of symbols

S Havrylov, I Titov - Advances in neural information …, 2017 - proceedings.neurips.cc
Learning to communicate through interaction, rather than relying on explicit supervision, is
often considered a prerequisite for develo** a general AI. We study a setting where two …

Generating responses with a specific emotion in dialog

Z Song, X Zheng, L Liu, M Xu… - Proceedings of the 57th …, 2019 - aclanthology.org
It is desirable for dialog systems to have capability to express specific emotions during a
conversation, which has a direct, quantifiable impact on improvement of their usability and …

Spoc: Search-based pseudocode to code

S Kulal, P Pasupat, K Chandra, M Lee… - Advances in …, 2019 - proceedings.neurips.cc
We consider the task of map** pseudocode to executable code, assuming a one-to-one
correspondence between lines of pseudocode and lines of code. Given test cases as a …

Latent intention dialogue models

TH Wen, Y Miao, P Blunsom… - … Conference on Machine …, 2017 - proceedings.mlr.press
Develo** a dialogue agent that is capable of making autonomous decisions and
communicating by natural language is one of the long-term goals of machine learning …

Coupling large language models with logic programming for robust and general reasoning from text

Z Yang, A Ishay, J Lee - arxiv preprint arxiv:2307.07696, 2023 - arxiv.org
While large language models (LLMs), such as GPT-3, appear to be robust and general, their
reasoning ability is not at a level to compete with the best models trained for specific natural …

Structvae: Tree-structured latent variable models for semi-supervised semantic parsing

P Yin, C Zhou, J He, G Neubig - arxiv preprint arxiv:1806.07832, 2018 - arxiv.org
Semantic parsing is the task of transducing natural language (NL) utterances into formal
meaning representations (MRs), commonly represented as tree structures. Annotating NL …