Abstract | ||
---|---|---|
Semantic specialization methods fine-tune distributional word vectors using lexical knowledge from external resources (e.g., WordNet) to accentuate a particular relation between words. However, such post-processing methods suffer from limited coverage as they affect only vectors of words seen in the external resources. We present the first post-processing method that specializes vectors of all vocabulary words - including those unseen in the resources - for the asymmetric relation of lexical entailment (LE) (i.e., hyponymy-hypernymy relation). Leveraging a partially LE-specialized distributional space, our POSTLE (i.e., post-specialization for LE) model learns an explicit global specialization function, allowing for specialization of vectors of unseen words, as well as word vectors from other languages via cross-lingual transfer. We capture the function as a deep feed-forward neural network: its objective re-scales vector norms to reflect the concept hierarchy while simultaneously attracting hyponymy-hypernymy pairs to better reflect semantic similarity. An extended model variant augments the basic architecture with an adversarial discriminator. We demonstrate the usefulness and versatility of POS-TLE models with different input distributional spaces in different scenarios (monolingual LE and zero-shot cross-lingual LE transfer) and tasks (binary and graded LE). We report consistent gains over state-of-the-art LE-specialization methods, and successfully LE-specialize word vectors for languages without any external lexical knowledge. |
Year | DOI | Venue |
---|---|---|
2019 | 10.18653/v1/w19-4310 | 4TH WORKSHOP ON REPRESENTATION LEARNING FOR NLP (REPL4NLP-2019) |
Field | DocType | Citations |
Logical consequence,Computer science,Natural language processing,Artificial intelligence | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Aishwarya Kamath | 1 | 0 | 0.34 |
Jonas Pfeiffer | 2 | 0 | 0.68 |
Edoardo Maria Ponti | 3 | 0 | 0.34 |
Goran Glavaš | 4 | 139 | 31.85 |
Ivan Vulic | 5 | 462 | 52.59 |