paper-with-me

홈 › Papers

Towards a continuous modeling of natural language domains

2016-10-28 · WS 2016 11 · Sebastian Ruder, Parsa Ghaffari, John G. Breslin

Humans continuously adapt their style and language to a variety of domains. However, a reliable definition of `domain' has eluded researchers thus far. Additionally, the notion of discrete domains stands in contrast to the multiplicity of heterogeneous domains that humans navigate, many of which overlap. In order to better understand the change and variation of human language, we draw on research in domain adaptation and extend the notion of discrete domains to the continuous spectrum. We propose representation learning-based models that can adapt to continuous domains and detail how these can be used to investigate variation in language. To this end, we propose to use dialogue modeling as a test bed due to its proximity to language modeling and its social component.

📄 PDF Abstract BibTeX arXiv:1610.09158

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationLanguage ModelingLanguage ModellingNavigateRepresentation Learning

Similar Papers 제목 키워드 기반

CALM: Continuous Adaptive Learning for Language Modeling

2020-04-08 · Kristjan Arumae, Parminder Bhatia

Training large language representation models has become a standard in the natural language processing community. This allows for fine tuning on any number of specific tasks, however, these large high capacity models can…

Continual LearningLanguage ModelingLanguage Modelling

Latent Diffusion for Language Generation

2022-12-19 · NeurIPS 2023 11 · Justin Lovelace, Varsha Kishore, Chao Wan, Eliot Shekhtman 외

Diffusion models have achieved great success in modeling continuous data modalities such as images, audio, and video, but have seen limited use in discrete domains such as language. Recent attempts to adapt diffusion to …

DecoderText Generation

Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletions

2025-11-12 · Lukas Billera, Hedwig Nora Nordlinder, Jack Collier Ryder, Anton Oresten 외 arxiv

Diffusion and flow matching approaches to generative modeling have shown promise in domains where the state space is continuous, such as image generation or protein folding & design, and discrete, exemplified by diffusio…

Image Generation

Learning Mutational Semantics

2020-12-01 · NeurIPS 2020 12 · Brian Hie, Ellen Zhong, Bryan Bryson, Bonnie Berger

In many natural domains, changing a small part of an entity can transform its semantics; for example, a single word change can alter the meaning of a sentence, or a single amino acid change can mutate a viral protein to …

Sentencevalid

Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains

2024-02-06 · Junhong Shen, Neil Tenenholtz, James Brian Hall, David Alvarez-Melis 외

Large Language Models (LLMs) have demonstrated remarkable proficiency in understanding and generating natural language. However, their capabilities wane in highly specialized domains underrepresented in the pretraining c…

TAGZero-shot Generalization