Search Results for author:
Found 18 papers, 4 papers with code
CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge Graphs
Although paths of user interests shift in knowledge graphs (KGs) can benefit conversational recommender systems (CRS), explicit reasoning on KGs has not been well considered in CRS, due to the complex of high-order and incomplete paths.
Ranked #2 on
Text Generation
on ReDial
CR-GIS: Improving Conversational Recommendation via Goal-aware Interest Sequence Modeling
In CRS, implicit patterns of user interest sequence guide the smooth transition of dialog utterances to the goal item.
TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph
We design a global reinforcement learning with the planned paths to flexibly adjust the local response generation model towards the global target.
Mind vs. Mouth: On Measuring Re-judge Inconsistency of Social Bias in Large Language Models
We propose that this re-judge inconsistency can be similar to the inconsistency between human's unaware implicit social bias and their aware explicit social bias.
Syntax-Aware Complex-Valued Neural Machine Translation
The experimental results demonstrate that the proposed method can bring significant improvements in BLEU scores on two datasets.
Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Persona
We design a Contrastive Latent Variable-based model (CLV) that clusters the dense persona descriptions into sparse categories, which are combined with the history query to generate personalized responses.
Constructing Holistic Measures for Social Biases in Masked Language Models
In this paper, the log-likelihoods of stereotype bias and anti-stereotype bias samples output by MLMs are considered Gaussian distributions.
Empathetic Response Generation via Emotion Cause Transition Graph
Empathetic dialogue is a human-like behavior that requires the perception of both affective factors (e. g., emotion status) and cognitive factors (e. g., cause of the emotion).
Mining Effective Features Using Quantum Entropy for Humor Recognition
Humor recognition has been extensively studied with different methods in the past years.
Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation
Towards human-like dialogue systems, current emotional dialogue approaches jointly model emotion and semantics with a unified neural network.
Aligning Recommendation and Conversation via Dual Imitation
Human conversations of recommendation naturally involve the shift of interests which can align the recommendation actions and conversation process to make accurate recommendations with rich explanations.
Label-Based Diversity Measure Among Hidden Units of Deep Neural Networks: A Regularization Method
In this paper, from an information theoretic perspective, we introduce a new definition of redundancy to describe the diversity of hidden units under supervised learning settings by formalizing the effect of hidden layers on the generalization capacity as the mutual information.
Interpretable Network Structure for Modeling Contextual Dependency
Then, we show that the lower bound of such a separation rank can reveal the quantitative relation between the network structure (e. g. depth/width) and the modeling ability for the contextual dependency.
A Tensorized Transformer for Language Modeling
In this paper, based on the ideas of tensor decomposition and parameters sharing, we propose a novel self-attention model (namely Multi-linear attention) with Block-Term Tensor Decomposition (BTD).
A Position-aware Bidirectional Attention Network for Aspect-level Sentiment Analysis
PBAN not only concentrates on the position information of aspect terms, but also mutually models the relation between aspect term and sentence by employing bidirectional attention mechanism.
Aspect-Based Sentiment Analysis (ABSA)
Feature Engineering
+2
A Confident Information First Principle for Parametric Reduction and Model Selection of Boltzmann Machines
We then revisit Boltzmann machines (BM) from a model selection perspective and theoretically show that both the fully visible BM (VBM) and the BM with hidden units can be derived from the general binary multivariate distribution using the CIF principle.
Understanding Boltzmann Machine and Deep Learning via A Confident Information First Principle
Typical dimensionality reduction methods focus on directly reducing the number of random variables while retaining maximal variations in the data.
