Search Results for author:
Found 6 papers, 6 papers with code
From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression
Prompt compression has been proposed to alleviate these issues, but it faces challenges in (i) capturing the global context and (ii) training the compressor effectively.
MARS: Matching Attribute-aware Representations for Text-based Sequential Recommendation
MARS extracts detailed user and item representations through attribute-aware text encoding, capturing diverse user intents with multiple attribute-aware representations.
GLEN: Generative Retrieval via Lexical Index Learning
For training, GLEN effectively exploits a dynamic lexical identifier using a two-phase index learning strategy, enabling it to learn meaningful lexical identifiers and relevance signals between queries and documents.
ConQueR: Contextualized Query Reduction using Search Logs
One extracts core terms from an original query at the term level, and the other determines whether a sub-query is a suitable reduction for the original query at the sequence level.
SpaDE: Improving Sparse Representations using a Dual Document Encoder for First-stage Retrieval
Sparse document representations have been widely used to retrieve relevant documents via exact lexical matching.
MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories
Automated metaphor detection is a challenging task to identify metaphorical expressions of words in a sentence.
