Name
Abstract | ||
|---|---|---|
The way humans define words is a powerful way of representing them. In this work, we propose to measure word similarity by comparing the overlap in their definition. This highlights linguistic phenomena thatare complementary to the information extracted from standard context-based representation learning techniques. To acquire a large amount of word definitionsin a cost-efficient manner, we designed a simple interactive word game, Word Sheriff. As a byproduct of game play, it generates short word sequences that can beused to uniquely identify words. These sequences can not only be used to evaluate the quality of word representations, but it could ultimately give an alternative way of learning them, as it overcomes someof the limitations of the distributional hypothesis. Moreover, inspecting player behaviour reveals interesting aspects about human strategies and knowledge acquisitionbeyond those of simple word association games, due to the conversational nature of the game. Lastly, we outline avision of a communicative evaluation setting, where systems are evaluated based on how well a given representation allows a system to communicate with human and computer players. |
Year | Venue | Field |
|---|---|---|
2016 | RepEval@ACL | Word lists by frequency,Computer science,Natural language processing,Word Association,Artificial intelligence,Measure word,Feature learning,Knowledge acquisition |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Iuliana-Elena Parasca | 1 | 0 | 0.34 |
| Andreas Lukas Rauter | 2 | 0 | 0.34 |
| Jack Roper | 3 | 0 | 0.34 |
| Aleksandar Rusinov | 4 | 0 | 0.34 |
| Guillaume Bouchard | 5 | 433 | 39.20 |
| Sebastian Riedel | 6 | 1625 | 103.73 |
| Pontus Stenetorp | 7 | 336 | 26.40 |