10.1k citations
- Google (United States)US161 papers
- Google (United Kingdom)GB73 papers
- University of OxfordGB33 papers
- Massachusetts Institute of TechnologyUS25 papers
- University College LondonGB25 papers
- University of AlbertaCA19 papers
- Imperial College LondonGB18 papers
- University of CambridgeGB16 papers
- McGill UniversityCA15 papers
- Stanford UniversityUS15 papers
- University of TorontoCA15 papers
- University of California, BerkeleyUS14 papers
6 papers · 2 filters
CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling
Ning Miao, Hao Zhou, Lili Mou +2
In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements. Existing languag…
Systematic Generalization: What Is Required and Can It Be Learned?
Dzmitry Bahdanau, Shikhar Murty, Michael Noukhovitch +3
Numerous models for grounded language understanding have been recently proposed, including (i) generic models that can be easily adapted to any given task and (ii) intuitively appe…
Learning to Discover, Ground and Use Words with Segmental Neural Language Models
Kazuya Kawakami, Chris Dyer, Phil Blunsom
We propose a segmental neural language model that combines the generalization power of neural networks with the ability to discover word-like units that are latent in unsegmented c…
Syntactic Scaffolds for Semantic Structures
Swabha Swayamdipta, Sam Thomson, Kenton Lee +3
We introduce the syntactic scaffold, an approach to incorporating syntactic information into semantic tasks. Syntactic scaffolds avoid expensive syntactic processing at runtime, on…
Evaluating Theory of Mind in Question Answering
Aida Nematzadeh, Kaylee Burns, Erin Grant +2
We propose a new dataset for evaluating question answering models with respect to their capacity to reason about beliefs. Our tasks are inspired by theory-of-mind experiments that…
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Alex Wang, Amanpreet Singh, Julian Michael +3
For natural language understanding (NLU) technology to be maximally useful, both practically and as a scientific object of study, it must be general: it must be able to process lan…