Article

Evaluating an LLM’s Performance in Annotating Discourse Strategies

2025-09-02

Abstract excerpt

<title>Abstract</title> <p>Manual annotation remains essential for identifying complex pragmatic and discourse-level features in corpus linguistics, particularly the functional components of speech acts. While part-of-speech and semantic tagging can be automated with high accuracy, annotating discourse strategies remains challenging due to their context-sensitive nature and lack of consistent lexical realizations...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: b0baeb09-2e50-512d-801e-2464bcaa3e4a
DOI: 10.21203/rs.3.rs-7246876/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Evaluating an LLM’s Performance in Annotating Discourse StrategiesDOI 10.21203/rs.3.rs-7246876/v1Read

Evaluating Large language models on Understanding Korean indirect Speech actsSemantic proximity Read

The role of pragmatic mechanisms in referential communication and categorization: An emergent communication modelSemantic proximity Read

Pragmatic Implicature Processing in ChatGPTSemantic proximity Read

A Categorical Archive of ChatGPT FailuresSemantic proximity Read

There is a power law of joint communicative effort and it reflects communicative workSemantic proximity Read

There is a power law of joint communicative effort and it reflects communicative workSemantic proximity Read

“We Need to Start Thinking Ahead”: The Impact of Social Context on Linguistic Norm AdherenceSemantic proximity Read

Using LLMs for Pre-Annotation of Emotional Manipulation Techniques in a Low-Resource Language Corpus: Are We There Yet?Semantic proximity Read

KM-Chat: A Large-Scale Synthetic Question-Answer Dataset for Open-Domain Conversational AISemantic proximity Read

Exploring Textual Semantics in Large Language ModelsSemantic proximity Read

Aligning syntactic structure to the dynamics of verbal communication: a pipeline for annotating syntactic phrases onto speech acousticsSemantic proximity Read

Conversations From Make-Believe: An Attentive Encoder–Decoder Chatbot Trained on Scripted DialogueSemantic proximity Read