24 citations · 82 across the 20 of their papers we have counts for
20 papers
RNR: Teaching Large Language Models to Follow Roles and Rules
Kuan Wang, Alexander Bukharin, Haoming Jiang +9
Instruction fine-tuning (IFT) elicits instruction following capabilities and steers the behavior of large language models (LLMs) via supervised learning. However, existing models t…
Multimodal Prompt Learning for Product Title Generation with Extremely Limited Labels
Bang Yang, Fenglin Liu, Zheng Li +4
Generating an informative and attractive title for the product is a crucial task for e-commerce. Most existing works follow the standard multimodal natural language generation appr…
Knowledge Graph Reasoning over Entities and Numerical Values
Jiaxin Bai, Chen Luo, Zheng Li +3
A complex logic query in a knowledge graph refers to a query expressed in logic form that conveys a complex meaning, such as where did the Canadian Turing award winner graduate fro…
Graph Reasoning for Question Answering with Triplet Retrieval
Shiyang Li, Yifan Gao, Haoming Jiang +5
Answering complex questions often requires reasoning over knowledge graphs (KGs). State-of-the-art methods often utilize entities in questions to retrieve local subgraphs, which ar…
Short Text Pre-training with Extended Token Classification for E-commerce Query Understanding
Haoming Jiang, Tianyu Cao, Zheng Li +6
E-commerce query understanding is the process of inferring the shopping intent of customers by extracting semantic meaning from their search queries. The recent progress of pre-tra…
Context-Aware Query Rewriting for Improving Users' Search Experience on E-commerce Websites
Simiao Zuo, Qingyu Yin, Haoming Jiang +4
E-commerce queries are often short and ambiguous. Consequently, query understanding often uses query rewriting to disambiguate user-input queries. While using e-commerce search too…
DiP-GNN: Discriminative Pre-Training of Graph Neural Networks
Simiao Zuo, Haoming Jiang, Qingyu Yin +3
Graph neural network (GNN) pre-training methods have been proposed to enhance the power of GNNs. Specifically, a GNN is first pre-trained on a large-scale unlabeled graph and then…
Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training
Yifan Gao, Qingyu Yin, Zheng Li +5
Keyphrase generation is the task of automatically predicting keyphrases given a piece of long text. Despite its recent flourishing, keyphrase generation on non-English languages ha…
SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models
Jingfeng Yang, Haoming Jiang, Qingyu Yin +3
Recent research showed promising results on combining pretrained language models (LMs) with canonical utterance for few-shot semantic parsing. The canonical utterance is often leng…
CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data
Rui Feng, Chen Luo, Qingyu Yin +3
User sessions empower many search and recommendation tasks on a daily basis. Such session data are semi-structured, which encode heterogeneous relations between queries and product…
RETE: Retrieval-Enhanced Temporal Event Forecasting on Unified Query Product Evolutionary Graph
Ruijie Wang, Zheng Li, Danqing Zhang +4
With the increasing demands on e-commerce platforms, numerous user action history is emerging. Those enriched action records are vital to understand users' interests and intents. R…
Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification
Qi Shi, Yu Zhang, Qingyu Yin +1
Table-based fact verification task aims to verify whether the given statement is supported by the given semi-structured table. Symbolic reasoning with logical operations plays a cr…
Multiple Structural Priors Guided Self Attention Network for Language Understanding
Le Qi, Yu Zhang, Qingyu Yin +1
Self attention networks (SANs) have been widely utilized in recent NLP studies. Unlike CNNs or RNNs, standard SANs are usually position-independent, and thus are incapable of captu…
XTQA: Span-Level Explanations of the Textbook Question Answering
Jie Ma, Qi Chai, Jun Liu +3
Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams. We a…
Keyphrase Extraction with Span-based Feature Representations
Funan Mu, Zhenting Yu, LiFeng Wang +7
Keyphrases are capable of providing semantic metadata characterizing documents and producing an overview of the content of a document. Since keyphrase extraction is able to facilit…
Towards Explainable NLP: A Generative Explanation Framework for Text Classification
Hui Liu, Qingyu Yin, William Yang Wang
Building explainable systems is a critical problem in the field of Natural Language Processing (NLP), since most machine learning models provide no explanations for the predictions…
Deep Reinforcement Learning for Chinese Zero pronoun Resolution
Qingyu Yin, Yu Zhang, Weinan Zhang +2
Deep neural network models for Chinese zero pronoun resolution learn semantic information for zero pronoun and candidate antecedents, but tend to be short-sighted---they often make…
Generating and Exploiting Large-scale Pseudo Training Data for Zero Pronoun Resolution
Ting Liu, Yiming Cui, Qingyu Yin +3
Most existing approaches for zero pronoun resolution are heavily relying on annotated data, which is often released by shared task organizers. Therefore, the lack of annotated data…
Neural Recovery Machine for Chinese Dropped Pronoun
Wei-Nan Zhang, Ting Liu, Qingyu Yin +1
Dropped pronouns (DPs) are ubiquitous in pro-drop languages like Chinese, Japanese etc. Previous work mainly focused on painstakingly exploring the empirical features for DPs recov…
A Deep Neural Network for Chinese Zero Pronoun Resolution
Qingyu Yin, Weinan Zhang, Yu Zhang +1
Existing approaches for Chinese zero pronoun resolution overlook semantic information. This is because zero pronouns have no descriptive information, which results in difficulty in…