Search Results for author:
Found 9 papers, 3 papers with code
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
We construct the DACO dataset, containing (1) 440 databases (of tabular data) collected from real-world scenarios, (2) ~2k query-answer pairs that can serve as weak supervision for model training, and (3) a concentrated but high-quality test set with human refined annotations that serves as our main evaluation benchmark.
Improving Generalization of Alignment with Human Preferences through Group Invariant Learning
In this work, we propose a novel approach that can learn a consistent policy via RL across various data groups or domains.
Secrets of RLHF in Large Language Models Part I: PPO
Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model.
Deep Video Demoireing via Compact Invertible Dyadic Decomposition
Removing moire patterns from videos recorded on screens or complex textures is known as video demoireing.
Two-Level Supervised Contrastive Learning for Response Selection in Multi-Turn Dialogue
We further develop a new method for supervised contrastive learning, referred to as two-level supervised contrastive learning, and employ the method in response selection in multi-turn dialogue.
Ranked #2 on
Conversational Response Selection
on E-commerce
Spelling Error Correction with Soft-Masked BERT
A state-of-the-art method for the task selects a character from a list of candidates for correction (including non-correction) at each position of the sentence on the basis of BERT, the language representation model.
Part-of-Speech Tagging for Twitter with Adversarial Neural Networks
In this work, we study the problem of part-of-speech tagging for Tweets.
Ranked #3 on
Part-Of-Speech Tagging
on Ritter
Hashtag Recommendation Using End-To-End Memory Networks with Hierarchical Attention
By incorporating the hierarchical attention mechanism, the relative improvement in the proposed method over the state-of-the-art method is around 67. 9{\%} in the F1-score.
Query Answering with Inconsistent Existential Rules under Stable Model Semantics
Surprisingly, for R-acyclic existential rules with R-stratified or guarded existential rules with stratified negations, both the data complexity and combined complexity of query answering under the rule {repair semantics} remain the same as that under the conventional query answering semantics.
