Search Results for author:
Found 10 papers, 2 papers with code
Enhancing Document Ranking with Task-adaptive Training and Segmented Token Recovery Mechanism
In this paper, we propose a new ranking model DR-BERT, which improves the Document Retrieval (DR) task by a task-adaptive training process and a Segmented Token Recovery Mechanism (STRM).
GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model
Currently, the reduction in the parameter scale of large-scale pre-trained language models (PLMs) through knowledge distillation has greatly facilitated their widespread deployment on various devices.
Multi-task Transformer with Relation-attention and Type-attention for Named Entity Recognition
There are three types of NER tasks, including flat, nested and discontinuous entity recognition.
Inflected Forms Are Redundant in Question Generation Models
Secondly, we propose to adapt QG as a combination of the following actions in the encode-decoder framework: generating a question word, copying a word from the source sequence or generating a word transformation type.
CLOWER: A Pre-trained Language Model with Contrastive Learning over Word and Character Representations
However, most current models use Chinese characters as inputs and are not able to encode semantic information contained in Chinese words.
VIRT: Improving Representation-based Models for Text Matching through Virtual Interaction
With the booming of pre-trained transformers, representation-based models based on Siamese transformer encoders have become mainstream techniques for efficient text matching.
BCORLE($\lambda$): An Offline Reinforcement Learning and Evaluation Framework for Coupons Allocation in E-commerce Market
Further, a novel offline reinforcement learning method and an off-policy evaluation algorithm are proposed for policy learning and policy evaluation, respectively.
TITA: A Two-stage Interaction and Topic-Aware Text Matching Model
To tackle this problem, we define a three-level relevance in keyword-document matching task: topic-aware relevance, partially-relevance and irrelevance.
Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval
Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models.
A Topic Augmented Text Generation Model: Joint Learning of Semantics and Structural Features
This model captures structural features by a sequential variational autoencoder component and leverages a topic modeling component based on Gaussian distribution to enhance the recognition of text semantics.
