Y Bizzoni, TS Juzek, C España-Bonet… - Proceedings of the …, 2020 - aclanthology.org
Translationese is a phenomenon present in human translations, simultaneous interpreting, and even machine translations. Some translationese features tend to appear in …
When generating natural language from neural probabilistic models, high probability does not always coincide with high quality: It has often been observed that mode-seeking …
Human languages evolve to make communication more efficient. But efficiency creates trade- offs: what is efficient for speakers is not always efficient for comprehenders. How do …
Abstract Language models based on artificial neural networks increasingly capture key aspects of how humans process sentences. Most notably, model-based surprisals predict …
Z Lei, Y Zhang, Y Xiong, S Chen - Advances in Neural …, 2024 - proceedings.neurips.cc
Vision-based emergent communication (EC) aims to learn to communicate through sketches and demystify the evolution of human communication. Ironically, previous works neglect …
Recent advances in large language models (LLM) have enabled richer social simulations, allowing for the study of various social phenomena. However, most recent work has used a …
The idea that ambiguity can be productive in data science remains controversial. Efforts to make scientific publications and data intelligible to computers generally assume that …
CR Twomey, G Roberts… - Proceedings of the …, 2021 - National Acad Sciences
Names for colors vary widely across languages, but color categories are remarkably consistent. Shared mechanisms of color perception help explain consistent partitions of …
Human languages are replete with ambiguity. This is most evident in homophony––where two or more words sound the same, but carry distinct meanings. For example, the wordform …