Search Results for author:
Found 15 papers, 11 papers with code
Encoding and Fusing Semantic Connection and Linguistic Evidence for Implicit Discourse Relation Recognition
Prior studies use one attention mechanism to improve contextual semantic representation learning for implicit discourse relation recognition (IDRR).
ConnPrompt: Connective-cloze Prompt Learning for Implicit Discourse Relation Recognition
As the first trial of using this new paradigm for IDRR, this paper develops a Connective-cloze Prompt (ConnPrompt) to transform the relation prediction task as a connective-cloze task.
One Backpropagation in Two Tower Recommendation Models
In this paper, we challenge such an equal training assumption and propose a novel one backpropagation updating strategy, which keeps the normal gradient backpropagation for the item encoding tower, but cuts off the backpropagation for the user encoding tower.
Adaptive Prompt Learning with Distilled Connective Knowledge for Implicit Discourse Relation Recognition
Implicit discourse relation recognition (IDRR) aims at recognizing the discourse relation between two text segments without an explicit connective.
Debiased Pairwise Learning from Positive-Unlabeled Implicit Feedback
Learning contrastive representations from pairwise comparisons has achieved remarkable success in various fields, such as natural language processing, computer vision, and information retrieval.
DAPrompt: Deterministic Assumption Prompt Learning for Event Causality Identification
We use the probabilities of predicted events to evaluate the assumption rationality for the final event causality decision.
Reducing Popularity Bias in Recommender Systems through AUC-Optimal Negative Sampling
To achieve this win-win situation, we propose to intervene in model training through negative sampling thereby modifying model predictions.
TEPrompt: Task Enlightenment Prompt Learning for Implicit Discourse Relation Recognition
Although an auxiliary task is not used to directly output final prediction, we argue that during the joint training some of its learned features can be useful to boost the main task.
Prompt Learning for News Recommendation
Some recent \textit{news recommendation} (NR) methods introduce a Pre-trained Language Model (PLM) to encode news representation by following the vanilla pre-train and fine-tune paradigm with carefully-designed recommendation-specific neural networks and objective functions.
Bayesian Self-Supervised Contrastive Learning
Recent years have witnessed many successful applications of contrastive learning in diverse domains, yet its self-supervised version still remains many exciting challenges.
Bi-Directional Iterative Prompt-Tuning for Event Argument Extraction
Recently, prompt-tuning has attracted growing interests in event argument extraction (EAE).
VRKG4Rec: Virtual Relational Knowledge Graphs for Recommendation
Recent studies regard items as entities of a knowledge graph and leverage graph neural networks to assist item encoding, yet by considering each relation type individually.
Bayesian Negative Sampling for Recommendation
Although previous studies have proposed some approaches to sample informative instances, few has been done to discriminating false negative from true negative for unbiased negative sampling.
A Survey of Implicit Discourse Relation Recognition
As sentences are normally consist of multiple text segments, correct understanding of the theme of a discourse should take into consideration of the relations in between text segments.
Graph Spring Network and Informative Anchor Selection for Session-based Recommendation
In this paper, we propose a strategy that first selects some informative item anchors and then encode items' potential relations to such anchors.
