AAAI 2019 accepted papers on Large language models
66 of the 1,147 papers accepted at AAAI 2019 (5.8%) are on Large language models, compared with 6.3% at AAAI 2018. They fall into 6 topics.
See AAAI 2019 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Language, safety and interpretability · 28 papers
- Interpreting Deep Models for Text Analysis via Optimization and Regularization Methods (41 citations)
- Violence Rating Prediction from Movie Scripts (33 citations)
- Character n-Gram Embeddings to Improve RNN Language Models (23 citations)
- Gradient-Based Inference for Networks with Output Constraints (23 citations)
- Unsupervised Bilingual Lexicon Induction from Mono-Lingual Multimodal Data (11 citations)
- A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Context
- An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Loss
- Analyzing Compositionality-Sensitivity of NLI Models
- CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling
- Deep Cascade Multi-Task Learning for Slot Filling in Online Shopping Assistant
- Deep Short Text Classification with Knowledge Powered Attention
- Dictionary-Guided Editing Networks for Paraphrase Generation
and 16 more in the interactive map.
Retrieval and knowledge · 21 papers
- ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning (830 citations)
- Declarative Question Answering over Knowledge Bases Containing Natural Language Text with Answer Set Programming (26 citations)
- Ontology-Based Query Answering for Probabilistic Temporal Data (17 citations)
- Complexity of Inconsistency-Tolerant Query Answering in Datalog+/– under Cardinality-Based Repairs (14 citations)
- Ontology-Mediated Query Answering over Log-Linear Probabilistic Data (14 citations)
- Relaxing and Restraining Queries for OBDA (2 citations)
- Text Assisted Insight Ranking Using Context-Aware Memory Network
- A Deep Cascade Model for Multi-Document Reading Comprehension
- A Deep Sequential Model for Discourse Parsing on Multi-Party Dialogues
- A Pattern-Based Approach to Recognizing Time Expressions
- Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference
- End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis
and 9 more in the interactive map.
Agents, code and math · 8 papers
- DeepFuzz: Automatic Generation of Syntax Valid C Programs for Fuzz Testing (108 citations)
- Argumentation for Explainable Scheduling (67 citations)
- Automatic Code Review by Learning the Revision of Source Code (55 citations)
- Deep Reinforcement Learning for Syntactic Error Repair in Student Programs (55 citations)
- Reasoning over Assumption-Based Argumentation Frameworks via Direct Answer Set Programming Encodings (9 citations)
- Simulation-Based Approach to Efficient Commonsense Reasoning in Very Large Knowledge Bases (2 citations)
- Challenges in the Automatic Analysis of Students’ Diagnostic Reasoning
- Plan-and-Write: Towards Better Automatic Storytelling
AI and society · 6 papers
- Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff (319 citations)
- Reverse-Engineering Satire, or “Paper on Computational Humor Accepted despite Making Serious Advances” (36 citations)
- A Study of Educational Data Mining: Evidence from a Thai University (13 citations)
- Learning to Address Health Inequality in the United States with a Bayesian Decision Network (8 citations)
- ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks
- Understanding Actors and Evaluating Personae with Gaussian Embeddings
