paper-with-me

홈 › Papers

Context or No Context? A preliminary exploration of human-in-the-loop approach for Incremental Temporal Summarization in meetings

2021-11-01 · EMNLP (newsum) 2021 11 · Nicole Beckage, Shachi H Kumar, Saurav Sahay, Ramesh Manuvinakurike

Incremental meeting temporal summarization, summarizing relevant information of partial multi-party meeting dialogue, is emerging as the next challenge in summarization research. Here we examine the extent to which human abstractive summaries of the preceding increments (context) can be combined with extractive meeting dialogue to generate abstractive summaries. We find that previous context improves ROUGE scores. Our findings further suggest that contexts begin to outweigh the dialogue. Using keyphrase extraction and semantic role labeling (SRL), we find that SRL captures relevant information without overwhelming the the model architecture. By compressing the previous contexts by ~70%, we achieve better ROUGE scores over our baseline models. Collectively, these results suggest that context matters, as does the way in which context is presented to the model.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Keyphrase ExtractionSemantic Role Labeling

Similar Papers 제목 키워드 기반

Towards A Human-in-the-Loop LLM Approach to Collaborative Discourse Analysis

2024-05-06 · Clayton Cohn, Caitlin Snyder, Justin Montenegro, Gautam Biswas

LLMs have demonstrated proficiency in contextualizing their outputs using human input, often matching or beating human-level performance on a variety of tasks. However, LLMs have not yet been used to characterize synergi…

Prompt Engineering

MCP-Diag: A Deterministic, Protocol-Driven Architecture for AI-Native Network Diagnostics

2026-01-30 · Devansh Lodha, Mohit Panchal, Sameer G. Kulkarni arxiv

The integration of Large Language Models (LLMs) into network operations (AIOps) is hindered by two fundamental challenges: the stochastic grounding problem, where LLMs struggle to reliably parse unstructured, vendor-spec…

Culturally Adaptive Explainable LLM Assessment for Multilingual Information Disorder: A Human-in-the-Loop Approach

2026-03-28 · Maziar Kianimoghadam Jouneghani arxiv

Recognizing information disorder is difficult because judgments about manipulation depend on cultural and linguistic context. Yet current Large Language Models (LLMs) often behave as monocultural, English-centric "black …

severity prediction

Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent

2024-10-15 · Bo Chen, Xiaoyu Li, YIngyu Liang, Zhenmei Shi 외

In-context learning has been recognized as a key factor in the success of Large Language Models (LLMs). It refers to the model's ability to learn patterns on the fly from provided in-context examples in the prompt during…

In-Context Learning

Design of Experiments for Stochastic Contextual Linear Bandits

2021-07-21 · NeurIPS 2021 12 · Andrea Zanette, Kefan Dong, Jonathan Lee, Emma Brunskill

In the stochastic linear contextual bandit setting there exist several minimax procedures for exploration with policies that are reactive to the data being acquired. In practice, there can be a significant engineering ov…