257 citations · 469 across the 45 of their papers we have counts for
7 papers · 1 filter
Generating Math Word Problems from Equations with Topic Controlling and Commonsense Enforcement
Tianyang Cao, Shuang Zeng, Songge Zhao +2
Recent years have seen significant advancement in text generation tasks with the help of neural language models. However, there exists a challenging task: generating math problem t…
Coarse-to-Fine Entity Representations for Document-level Relation Extraction
Damai Dai, Jing Ren, Shuang Zeng +2
Document-level Relation Extraction (RE) requires extracting relations expressed within and across sentences. Recent works show that graph-based methods, usually constructing a docu…
An Empirical Study on Model-agnostic Debiasing Strategies for Robust Natural Language Inference
Tianyu Liu, Xin Zheng, Xiaoan Ding +2
The prior work on natural language inference (NLI) debiasing mainly targets at one or few known biases while not necessarily making the models more robust. In this paper, we focus…
Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference
Xiaoan Ding, Tianyu Liu, Baobao Chang +2
While discriminative neural network classifiers are generally preferred, recent work has shown advantages of generative classifiers in term of data efficiency and robustness. In th…
Double Graph Based Reasoning for Document-level Relation Extraction
Shuang Zeng, Runxin Xu, Baobao Chang +1
Document-level relation extraction aims to extract relations among entities within a document. Different from sentence-level relation extraction, it requires reasoning over multipl…
Inductively Representing Out-of-Knowledge-Graph Entities by Optimal Estimation Under Translational Assumptions
Damai Dai, Hua Zheng, Fuli Luo +3
Conventional Knowledge Graph Completion (KGC) assumes that all test entities appear during training. However, in real-world scenarios, Knowledge Graphs (KG) evolve fast with out-of…
HypoNLI: Exploring the Artificial Patterns of Hypothesis-only Bias in Natural Language Inference
Tianyu Liu, Xin Zheng, Baobao Chang +1
Many recent studies have shown that for models trained on datasets for natural language inference (NLI), it is possible to make correct predictions by merely looking at the hypothe…