Search Results for author:
Found 34 papers, 13 papers with code
Multi-Domain Recommendation to Attract Users via Domain Preference Modeling
Targeting a platform that operates multiple service domains, we introduce a new task, Multi-Domain Recommendation to Attract Users (MDRAU), which recommends items from multiple ``unseen'' domains with which each user has not interacted yet, by using knowledge from the user's ``seen'' domains.
Exploring Language Model's Code Generation Ability with Auxiliary Functions
However, our analysis also reveals the model's underutilized behavior to call the auxiliary function, suggesting the future direction to enhance their implementation by eliciting the auxiliary function call ability encoded in the models.
Pearl: A Review-driven Persona-Knowledge Grounded Conversational Recommendation Dataset
Our experimental results demonstrate that utterances in PEARL include more specific user preferences, show expertise in the target domain, and provide recommendations more relevant to the dialogue context than those in prior datasets.
Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy
Document retrieval has greatly benefited from the advancements of large-scale pre-trained language models (PLMs).
Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering
Recent studies have investigated utilizing Knowledge Graphs (KGs) to enhance Quesetion Answering (QA) performance of Large Language Models (LLMs), yet structured KG verbalization remains challengin.
Ever-Evolving Memory by Blending and Refining the Past
To effectively construct memory, it is crucial to seamlessly connect past and present information, while also possessing the ability to forget obstructive information.
Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy
In the task of aspect sentiment quad prediction (ASQP), generative methods for predicting sentiment quads have shown promising results.
VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Models
The results suggest that VerifiNER can successfully verify errors from existing models as a model-agnostic approach.
COCOA: CBT-based Conversational Counseling Agent using Memory Specialized in Cognitive Distortions and Dynamic Prompt
The demand for conversational agents that provide mental health care is consistently increasing.
Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation
Motivated by these, we explore the impact of the inherent preference in LLMs on providing emotional support, and consequently, we observe that exhibiting high preference for specific strategies hinders effective emotional support, aggravating its robustness in predicting the appropriate strategy.
Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement
As the pioneer of persona expansion in multi-session settings, our framework facilitates better response generation via human-like persona refinement.
RDGCL: Reaction-Diffusion Graph Contrastive Learning for Recommendation
Contrastive learning (CL) has emerged as a promising technique for improving recommender systems, addressing the challenge of data sparsity by leveraging self-supervised signals from raw data.
Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales
Specifically, we address the clinical reasoning for disease diagnosis, where the LLM generates diagnostic rationales providing its insight on presented patient data and the reasoning path towards the diagnosis, namely Clinical Chain-of-Thought (Clinical CoT).
SCStory: Self-supervised and Continual Online Story Discovery
With a lightweight hierarchical embedding module that first learns sentence representations and then article representations, SCStory identifies story-relevant information of news articles and uses them to discover stories.
RTSUM: Relation Triple-based Interpretable Summarization with Multi-level Salience Visualization
In this paper, we present RTSUM, an unsupervised summarization framework that utilizes relation triples as the basic unit for summarization.
Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents
Hence, our focus is to facilitate such multi-hop reasoning over a dialogue context, namely dialogue chain-of-thought (CoT) reasoning.
Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding
Unsupervised discovery of stories with correlated news articles in real-time helps people digest massive news streams without expensive human annotations.
Evidentiality-aware Retrieval for Overcoming Abstractiveness in Open-Domain Question Answering
The long-standing goal of dense retrievers in abtractive open-domain question answering (ODQA) tasks is to learn to capture evidence passages among relevant passages for any given query, such that the reader produce factually correct outputs from evidence passages.
Distillation from Heterogeneous Models for Top-K Recommendation
Our work aims to transfer the ensemble knowledge of heterogeneous teachers to a lightweight student model using knowledge distillation (KD), to reduce the huge inference costs while retaining high accuracy.
Learning Topology-Specific Experts for Molecular Property Prediction
In this paper, motivated by this observation, we propose TopExpert to leverage topology-specific prediction models (referred to as experts), each of which is responsible for each molecular group sharing similar topological semantics.
Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generation
Topic taxonomies display hierarchical topic structures of a text corpus and provide topical knowledge to enhance various NLP applications.
Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning
In the end, we propose CLRCMD, a contrastive learning framework that optimizes RCMD of sentence pairs, which enhances the quality of sentence similarity and their interpretation.
Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering
ConCF constructs a multi-branch variant of a given target model by adding auxiliary heads, each of which is trained with heterogeneous objectives.
TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters
Topic taxonomies, which represent the latent topic (or category) structure of document collections, provide valuable knowledge of contents in many applications such as web search and information filtering.
Out-of-Category Document Identification Using Target-Category Names as Weak Supervision
To address this challenge, we introduce a new task referred to as out-of-category detection, which aims to distinguish the documents according to their semantic relevance to the inlier (or target) categories by using the category names as weak supervision.
Learnable Structural Semantic Readout for Graph Classification
By the help of a global readout operation that simply aggregates all node (or node-cluster) representations, existing GNN classifiers obtain a graph-level representation of an input graph and predict its class label using the representation.
Weakly Supervised Temporal Anomaly Segmentation with Dynamic Time Warping
Most recent studies on detecting and localizing temporal anomalies have mainly employed deep neural networks to learn the normal patterns of temporal data in an unsupervised manner.
OoMMix: Out-of-manifold Regularization in Contextual Embedding Space for Text Classification
Recent studies on neural networks with pre-trained weights (i. e., BERT) have mainly focused on a low-dimensional subspace, where the embedding vectors computed from input words (or their contexts) are located.
Out-of-Manifold Regularization in Contextual Embedding Space for Text Classification
Recent studies on neural networks with pre-trained weights (i. e., BERT) have mainly focused on a low-dimensional subspace, where the embedding vectors computed from input words (or their contexts) are located.
Bootstrapping User and Item Representations for One-Class Collaborative Filtering
To make the representations of positively-related users and items similar to each other while avoiding a collapsed solution, BUIR adopts two distinct encoder networks that learn from each other; the first encoder is trained to predict the output of the second encoder as its target, while the second encoder provides the consistent targets by slowly approximating the first encoder.
Multi-Class Data Description for Out-of-distribution Detection
The capability of reliably detecting out-of-distribution samples is one of the key factors in deploying a good classifier, as the test distribution always does not match with the training distribution in most real-world applications.
Learnable Dynamic Temporal Pooling for Time Series Classification
With the increase of available time series data, predicting their class labels has been one of the most important challenges in a wide range of disciplines.
One-class Classification Robust to Geometric Transformation
Recent studies on one-class classification have achieved a remarkable performance, by employing the self-supervised classifier that predicts the geometric transformation applied to in-class images.
Deep Generative Classifier for Out-of-distribution Sample Detection
The capability of reliably detecting out-of-distribution samples is one of the key factors in deploying a good classifier, as the test distribution always does not match with the training distribution in most real-world applications.
