85 citations · 446 across the 40 of their papers we have counts for
8 papers · 1 filter
Getting the Most out of Simile Recognition
Xiaoyue Wang, Linfeng Song, Xin Liu +2
Simile recognition involves two subtasks: simile sentence classification that discriminates whether a sentence contains simile, and simile component extraction that locates the cor…
Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing
Wenyue Hua, Lifeng Jin, Linfeng Song +3
Pretrained natural language processing (NLP) models have achieved high overall performance, but they still make systematic errors. Instead of manual error analysis, research on sli…
Cross-domain Generalization for AMR Parsing
Xuefeng Bai, Seng Yang, Leyang Cui +2
Abstract Meaning Representation (AMR) parsing aims to predict an AMR graph from textual input. Recently, there has been notable growth in AMR parsing performance. However, most exi…
Learning a Grammar Inducer from Massive Uncurated Instructional Videos
Songyang Zhang, Linfeng Song, Lifeng Jin +4
Video-aided grammar induction aims to leverage video information for finding more accurate syntactic grammars for accompanying text. While previous work focuses on building systems…
Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play
Qi Liu, Zihuiwen Ye, Tao Yu +2
The task of context-dependent text-to-SQL aims to convert multi-turn user utterances to formal SQL queries. This is a challenging task due to both the scarcity of training data fro…
Semantic-based Pre-training for Dialogue Understanding
Xuefeng Bai, Linfeng Song, Yue Zhang
Pre-trained language models have made great progress on dialogue tasks. However, these models are typically trained on surface dialogue text, thus are proven to be weak in understa…
Hierarchical Context Tagging for Utterance Rewriting
Lisa Jin, Linfeng Song, Lifeng Jin +2
Utterance rewriting aims to recover coreferences and omitted information from the latest turn of a multi-turn dialogue. Recently, methods that tag rather than linearly generate seq…
An Empirical Study of Retrieval-enhanced Graph Neural Networks
Dingmin Wang, Shengchao Liu, Hanchen Wang +5
Graph Neural Networks (GNNs) are effective tools for graph representation learning. Most GNNs rely on a recursive neighborhood aggregation scheme, named message passing, thereby th…