Search Results for author:
Found 27 papers, 14 papers with code
Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficiently
Through this process, it teaches the DR model how to retrieve relevant documents from the entire corpus instead of how to rerank a potentially biased sample of documents.
Optimizing Dense Retrieval Model Training with Hard Negatives
ADORE replaces the widely-adopted static hard negative sampling method with a dynamic one to directly optimize the ranking performance.
Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance
Compared with previous DR models that use brute-force search, JPQ almost matches the best retrieval performance with 30x compression on index size.
Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval
However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor search (NNS) in vector space.
KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems
The progress of recommender systems is hampered mainly by evaluation as it requires real-time interactions between humans and systems, which is too laborious and expensive.
RepBERT: Contextualized Text Embeddings for First-Stage Retrieval
Although exact term match between queries and documents is the dominant method to perform first-stage retrieval, we propose a different approach, called RepBERT, to represent documents and queries with fixed-length contextualized embeddings.
Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval
By making the REM and DAMs disentangled, DDR enables a flexible training paradigm in which REM is trained with supervision once and DAMs are trained with unsupervised data.
Neural Logic Reasoning
Both reasoning and generalization ability are important for prediction tasks such as recommender systems, where reasoning provides strong connection between user history and target items for accurate prediction, and generalization helps the model to draw a robust user portrait over noisy inputs.
Constructing Tree-based Index for Efficient and Effective Dense Retrieval
Unfortunately, while ANN can improve the efficiency of DR models, it usually comes with a significant price on retrieval performance.
CoSearchAgent: A Lightweight Collaborative Search Agent with Large Language Models
Hence, to better support the research in collaborative search, in this demo, we propose CoSearchAgent, a lightweight collaborative search agent powered by LLMs.
An Integrated Data Processing Framework for Pretraining Foundation Models
The ability of the foundation models heavily relies on large-scale, diverse, and high-quality pretraining data.
Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models
For example, representation-based retrieval models perform almost as well as interaction-based retrieval models in terms of interpolation but not extrapolation.
POSSCORE: A Simple Yet Effective Evaluation of Conversational Search with Part of Speech Labelling
Conversational search systems, such as Google Assistant and Microsoft Cortana, provide a new search paradigm where users are allowed, via natural language dialogues, to communicate with search systems.
Unbiased Learning to Rank: Online or Offline?
While their definitions of \textit{unbiasness} are different, these two types of ULTR algorithms share the same goal -- to find the best models that rank documents based on their intrinsic relevance or utility.
THUIR@COLIEE-2020: Leveraging Semantic Understanding and Exact Matching for Legal Case Retrieval and Entailment
We participated in the two case law tasks, i. e., the legal case retrieval task and the legal case entailment task.
Interpreting Dense Retrieval as Mixture of Topics
Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success.
Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy
To this end, we contribute to advance the study of the proactive dialogue policy to a more natural and challenging setting, i. e., interacting dynamically with users.
PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning
Furthermore, we introduce a novel paradigm named Personalized Training with Distilled Execution (PTDE), wherein agent-personalized global information is distilled into the agent's local information.
An Intent Taxonomy of Legal Case Retrieval
Through a laboratory user study, we reveal significant differences in user behavior and satisfaction under different search intents in legal case retrieval.
CoAScore: Chain-of-Aspects Prompting for NLG Evaluation
Specifically, for a given aspect to evaluate, we first prompt the LLM to generate a chain of aspects that are relevant to the target aspect and could be useful for the evaluation.
Session-level Normalization and Click-through Data Enhancement for Session-based Evaluation
Besides, it infers session-level relevance labels based on implicit feedback.
USimAgent: Large Language Models for Simulating Search Users
However, the potential of using LLMs in simulating search behaviors has not yet been fully explored.
An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models
Based on these findings, we then propose several simple document pruning methods to reduce the storage overhead and compare the effectiveness of different pruning methods on different late-interaction models.
MA4DIV: Multi-Agent Reinforcement Learning for Search Result Diversification
The objective of search result diversification (SRD) is to ensure that selected documents cover as many different subtopics as possible.
Leveraging Large Language Models for Relevance Judgments in Legal Case Retrieval
Nonetheless, the method of employing a general large language model for reliable relevance judgments in legal case retrieval is yet to be thoroughly explored.
Scaling Laws For Dense Retrieval
In this study, we investigate whether the performance of dense retrieval models follows the scaling law as other neural models.
Investigating the Robustness of Counterfactual Learning to Rank Models: A Reproducibility Study
Counterfactual learning to rank (CLTR) has attracted extensive attention in the IR community for its ability to leverage massive logged user interaction data to train ranking models.
