Demo Data from SIGIR 2026 / reviewers in the wild / expert
David Golub
dblp:25/183
· DBLP profile ↗
5ranked-venue papers
2as first author
0since 2021 · last 2020
—ORCID · none
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 4 · 1 first-authorGraphics, computer vision, multimedia, augmented reality and games · 1 · 1 first-authorHuman-computer interaction and ubiquitous computing · 1
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
4 papers |
Question answering and dialogue systems · 43% Language models and text generation · 32% Transfer learning and domain adaptation · 23% | |
| Human-computer interaction and pervasive computing
1 paper |
Human-robot interaction · 100% |
Topics — the 5 heaviest of 7, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Natural language and speech › Language models and text generation › text generation › multi-agent text generation
cooperative text generation |
0.3 | 1 | 2018 | Learning to Write with Cooperative Discriminators · ACL (1) 2018 |
Machine learning › Transfer learning and domain adaptation
cross-domain transfer |
0.3 | 1 | 2017 | Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension · EMNLP 2017 |
Natural language and speech › Question answering and dialogue systems
machine reading comprehension |
0.3 | 1 | 2017 | Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension · EMNLP 2017 |
Natural language and speech › Question answering and dialogue systems
knowledge base question answering |
0.2 | 1 | 2016 | Character-Level Question Answering with Attention · EMNLP 2016 |
Robotics › Robot navigation and mapping
sensorimotor integration |
0.0 | 1 | 2009 | Incorporating active vision into the body schema · HRI 2009 |
Methods — techniques the papers use, named apart from their topics
two-stage synthesis network · 0.3pre-trained model · 0.3character-level encoder-decoder · 0.2attention · 0.2
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2020 | Leveraging Pretrained Image Classifiers for Language-Based SegmentationabstractCurrent semantic segmentation models cannot easily generalize to new object classes unseen during train time: they require additional annotated images and retraining. We propose a novel segmentation model that injects visual priors into semantic segmentation architectures, allowing them to segment out new target labels without retraining. As visual priors, we use the activations of pretrained image classifiers, which provide noisy indications of the spatial location of both the target object and distractor objects in the scene. We leverage language semantics to obtain these activations for a target label unseen by the classifier. Further experiments show that the visual priors obtained via language semantics for both relevant and distracting objects are key to our performance. David Golub, Ahmed El-Kishky, Roberto Martin Martin |
WACV | 1 |
| 2018 | Learning to Write with Cooperative DiscriminatorsabstractAri Holtzman, Jan Buys, Maxwell Forbes, Antoine Bosselut, David Golub, Yejin Choi. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018. Ari Holtzman, Jan Buys, Maxwell Forbes, Antoine Bosselut, David Golub, Yejin Choi 0001 |
ACL (1) | 5 |
| 2017 | Two-Stage Synthesis Networks for Transfer Learning in Machine ComprehensionabstractWe develop a technique for transfer learning in machine comprehension (MC) using a novel two-stage synthesis network (SynNet).Given a high-performing MC model in one domain, our technique aims to answer questions about documents in another domain, where we use no labeled data of question-answer pairs.Using the proposed SynNet with a pretrained model on the SQuAD dataset, we achieve an F1 measure of 46.6% on the challenging NewsQA dataset, approaching performance of in-domain models (F1 measure of 50.0%) and outperforming the out-ofdomain baseline by 7.6%, without use of provided annotations. 1 David Golub, Po-Sen Huang, Xiaodong He 0001, Li Deng 0001 |
EMNLP | 1 |
| 2016 | Character-Level Question Answering with AttentionabstractWe show that a character-level encoderdecoder framework can be successfully applied to question answering with a structured knowledge base.We use our model for singlerelation question answering and demonstrate the effectiveness of our approach on the Sim-pleQuestions dataset (Bordes et al., 2015), where we improve state-of-the-art accuracy from 63.9% to 70.9%, without use of ensembles.Importantly, our character-level model has 16x fewer parameters than an equivalent word-level model, can be learned with significantly less data compared to previous work, which relies on data augmentation, and is robust to new entities in testing. 1 Xiaodong He 0001, David Golub |
EMNLP | 2 |
| 2009 | Incorporating active vision into the body schemaabstractNo abstract available. Justin W. Hart, Eleanor R. Avrunin, David Golub, Brian Scassellati, Steven W. Zucker |
HRI | 3 |