41 |
Manual Clustering and Spatial Arrangement of Verbs for Multilingual Evaluation and Typology Analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
42 |
A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters ...
|
|
|
|
BASE
|
|
Show details
|
|
43 |
Verb Knowledge Injection for Multilingual Event Processing ...
|
|
|
|
BASE
|
|
Show details
|
|
44 |
Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity ...
|
|
|
|
BASE
|
|
Show details
|
|
45 |
Probing Pretrained Language Models for Lexical Semantics ...
|
|
|
|
BASE
|
|
Show details
|
|
46 |
The Secret is in the Spectra: Predicting Cross-lingual Task Performance with Spectral Similarity Measures ...
|
|
|
|
BASE
|
|
Show details
|
|
47 |
SemEval-2020 Task 2: Predicting Multilingual and Cross-Lingual (Graded) Lexical Entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
48 |
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity ...
|
|
|
|
BASE
|
|
Show details
|
|
49 |
Cross-lingual semantic specialization via lexical relation induction ...
|
|
|
|
BASE
|
|
Show details
|
|
50 |
Adversarial propagation and zero-shot cross-lingual transfer of word vector specialization ...
|
|
|
|
BASE
|
|
Show details
|
|
51 |
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity ...
|
|
|
|
BASE
|
|
Show details
|
|
52 |
SemEval-2020 Task 2: Predicting Multilingual and Cross-Lingual (Graded) Lexical Entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
53 |
Do we really need fully unsupervised cross-lingual embeddings? ...
|
|
|
|
BASE
|
|
Show details
|
|
54 |
Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity ...
|
|
|
|
BASE
|
|
Show details
|
|
55 |
Probing Pretrained Language Models for Lexical Semantics ...
|
|
|
|
Abstract:
The success of large pretrained language models (LMs) such as BERT and RoBERTa has sparked interest in probing their representations, in order to unveil what types of knowledge they implicitly capture. While prior research focused on morphosyntactic, semantic, and world knowledge, it remains unclear to which extent LMs also derive lexical type-level knowledge from words in context. In this work, we present a systematic empirical analysis across six typologically diverse languages and five different lexical tasks, addressing the following questions: 1) How do different lexical knowledge extraction strategies (monolingual versus multilingual source LM, out-of-context versus in-context encoding, inclusion of special tokens, and layer-wise averaging) impact performance? How consistent are the observed effects across tasks and languages? 2) Is lexical knowledge stored in few parameters, or is it scattered throughout the network? 3) How do these representations fare against traditional static word vectors in ...
|
|
URL: https://dx.doi.org/10.17863/cam.62212 https://www.repository.cam.ac.uk/handle/1810/315105
|
|
BASE
|
|
Hide details
|
|
56 |
Classification-Based Self-Learning for Weakly Supervised Bilingual Lexicon Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
57 |
On the relation between linguistic typology and (limitations of) multilingual language modeling ...
|
|
|
|
BASE
|
|
Show details
|
|
58 |
Improving Bilingual Lexicon Induction with Unsupervised Post-Processing of Monolingual Word Vector Spaces ...
|
|
|
|
BASE
|
|
Show details
|
|
59 |
The Secret is in the Spectra: Predicting Cross-Lingual Task Performance with Spectral Similarity Measures ...
|
|
|
|
BASE
|
|
Show details
|
|
60 |
Spatial multi-arrangement for clustering and multi-way similarity dataset construction ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|