An NLP Assistant for Clide
This report describes an NLP assistant for the collaborative development environment Clide, that supports the development of NLP applications by providing easy access to some common NLP data structures. The assistant visualizes text fragments and their dependencies by displaying the semantic graph of a sentence, the coreference chain of a paragraph and mined triples that are extracted from a paragraph's semantic graphs and linked using its coreference chain. Using this information and a logic programming library, we create an NLP database which is used by a series of queries to mine the triples. The algorithm is tested by translating a natural language text describing a graph to an actual graph that is shown as an annotation in the text editor.
Code (0)
등록된 구현이 없습니다.
Tasks
SentenceSimilar Papers 제목 키워드 기반
Autoformalizing Euclidean Geometry
Autoformalization involves automatically translating informal math into formal theorems and proofs that are machine-verifiable. Euclidean geometry provides an interesting and controllable domain for studying autoformaliz…
MathFrom Direction to Magnitude: How Multimodal Instruction-Tuning Reorganizes the Geometric Encoding of Identity-Specifying Prompts in Transformer Hidden States
We investigate whether identity-specifying system prompts produce statistically distinguishable geometric fingerprints in the hidden-state trajectories of four open-weight transformer language models spanning four post-t…
Human Action Forecasting by Learning Task Grammars
For effective human-robot interaction, it is important that a robotic assistant can forecast the next action a human will consider in a given task. Unfortunately, real-world tasks are often very long, complex, and repeti…
Action RecognitionTemporal Action LocalizationVirtual Mouse And Assistant: A Technological Revolution Of Artificial Intelligence
The purpose of this paper is to enhance the performance of the virtual assistant. So, what exactly is a virtual assistant. Application software, often called virtual assistants, also known as AI assistants or digital ass…
SchedulingFrom Gaze to Guidance: Interpreting and Adapting to Users' Cognitive Needs with Multimodal Gaze-Aware AI Assistants
Current LLM assistants are powerful at answering questions, but they have limited access to the behavioral context that reveals when and where a user is struggling. We present a gaze-grounded multimodal LLM assistant tha…