Titlebook: Natural Language Processing and Chinese Computing; 13th National CCF Co Derek F. Wong,Zhongyu Wei,Muyun Yang Conference proceedings 2025 Th

有助于

CRAB

MCFC: A Momentum-Driven Clicked Feature Compressed Pre-trained Language Model for Information Retries and compress the dispersed knowledge together at the query granularity, named Multi-Instance Information Integration. Meanwhile, more relevant detection between queries and documents is eager in coarse clicked data background, we leverage a momentum-driven adjusting mechanism to refine the text re

胆大

Integrating Syntax Tree and Graph Neural Network for Conversational Question Answering over Heteroges and predicts node scores of the word nodes in the tree. This is based on the node’s entity information and its relevance to the current question within the neighborhood. A graph neural network that includes entity-level attention is used to complete the extraction of the question entities. Experim

Clumsy

PqE: Zero-Shot Document Expansion for Dense Retrieval with Large Language Modelsecall@1k metric by 4% points, surpassing the performance of the BM25 algorithm. Even for contriever., fine-tuned on the massive dataset MS-MARCO, and BGE, trained on hundreds of millions of query-document pairs, PqE boosts their Recall@1k metrics on the TREC DL dataset by 1 to 2% points. Notably, on

Ablation

abysmal

IRATE

Structure and Behavior Dual-Graph Reasoning with Integrated Key-Clue Parsing for Multi-party Dialogut, which significantly reduces the burden on the model and enhances the accuracy of our model. The experiments on the benchmark dataset show that our approach yields stable and substantial improvements, and outperforms the state-of-the-art methods.

笨拙的你

Enhancing Emotional Support Conversation with Cognitive Chain-of-Thought Reasoningrain enhanced machine supporters with CoT reasoning ability. Extensive automatic and human evaluations show that, CogChain not only improves the machine supporter’s performance for in-domain seen scenarios but also enhances its generalizability to out-of-domain unseen scenarios, demonstrating the im

Derogate

A Simple and Effective Span Interaction Modeling Method for Enhancing Multiple Span Question Answeriments demonstrate that baselines, on MultiSpanQA, incorporating our strategy achieved an improvement in EM F1 ranging from 2.88 to 11.27, achieving state-of-the-art (SOTA) results at equivalent model scales.

谷物