422 citations
- National University of SingaporeSG17 papers
- Nanyang Technological UniversitySG9 papers
- Singapore University of Technology and DesignSG9 papers
- Agency for Science, Technology and ResearchSG6 papers
- Institute of High Performance ComputingSG4 papers
- Peking UniversityCN4 papers
- University of Electronic Science and Technology of ChinaCN4 papers
- University of KentGB4 papers
- University of MazandaranIR4 papers
- Aix-Marseille UniversitéFR3 papers
- Indian Institute of Technology PalakkadIN3 papers
- Laboratoire Parole et LangageFR3 papers
4 papers · 1 filter
Better and Worse with Scale: How Contextual Entrainment Diverges with Model Size
Dikshant Kukreja, Kshitij Sah, Gautam Gupta +5
Larger language models become simultaneously better and worse at handling contextual information -- better at ignoring false claims, worse at ignoring irrelevant tokens. We formali…
A Rank-Based Similarity Metric for Word Embeddings
Enrico Santus, Hongmin Wang, Emmanuele Chersoni +1
Word Embeddings have recently imposed themselves as a standard for representing word meaning in NLP. Semantic similarity between word pairs has become the most common evaluation be…
Is Structure Necessary for Modeling Argument Expectations in Distributional Semantics?
Emmanuele Chersoni, Enrico Santus, Philippe Blache +1
Despite the number of NLP studies dedicated to thematic fit estimation, little attention has been paid to the related task of composing and updating verb argument expectations. The…
Measuring Thematic Fit with Distributional Feature Overlap
Enrico Santus, Emmanuele Chersoni, Alessandro Lenci +1
In this paper, we introduce a new distributional method for modeling predicate-argument thematic fit judgments. We use a syntax-based DSM to build a prototypical representation of…