DE eng

Search in the Catalogues and Directories

Hits 1 – 16 of 16

1
Dependency Patterns of Complex Sentences and Semantic Disambiguation for Abstract Meaning Representation Parsing ...
BASE
Show details
2
One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasets ...
BASE
Show details
3
Modeling Sense Structure in Word Usage Graphs with the Weighted Stochastic Block Model ...
BASE
Show details
4
InFillmore: Frame-Guided Language Generation with Bidirectional Context ...
BASE
Show details
5
Overcoming Poor Word Embeddings with Word Definitions ...
BASE
Show details
6
Learning Embeddings for Rare Words Leveraging Internet Search Engine and Spatial Location Relationships ...
BASE
Show details
7
Evaluating Universal Dependency Parser Recovery of Predicate Argument Structure via CompChain Analysis ...
BASE
Show details
8
ParsFEVER : a Dataset for Farsi Fact Extraction and Verification ...
BASE
Show details
9
Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge ...
BASE
Show details
10
Script Parsing with Hierarchical Sequence Modelling ...
BASE
Show details
11
Teach the Rules, Provide the Facts: Targeted Relational-knowledge Enhancement for Textual Inference ...
BASE
Show details
12
Multilingual Neural Semantic Parsing for Low-Resourced Languages ...
BASE
Show details
13
Inducing Language-Agnostic Multilingual Representations ...
Abstract: Cross-lingual representations have the potential to make NLP techniques available to the vast majority of languages in the world. However, they currently require large pretraining corpora or access to typologically similar languages. In this work, we address these obstacles by removing language identity signals from multilingual embeddings. We examine three approaches for this: (i) re-aligning the vector spaces of target languages (all together) to a pivot source language; (ii) removing language-specific means and variances, which yields better discriminativeness of embeddings as a by-product; and (iii) increasing input similarity across languages by removing morphological contractions and sentence reordering. We evaluate on XNLI and reference-free MT across 19 typologically diverse languages. Our findings expose the limitations of these approaches -- unlike vector normalization, vector space re-alignment and text normalization do not achieve consistent gains across encoders and languages. Due to the ...
Keyword: Computational Linguistics; Data Management System; FOS Languages and literature; Linguistics; Natural Language Processing; Semantics; Translation Studies
URL: https://underline.io/lecture/29780-inducing-language-agnostic-multilingual-representations
https://dx.doi.org/10.48448/158a-7m34
BASE
Hide details
14
Denoising Word Embeddings by Averaging in a Shared Space ...
BASE
Show details
15
Evaluating a Joint Training Approach for Learning Cross-lingual Embeddings with Sub-word Information without Parallel Corpora on Lower-resource Languages ...
BASE
Show details
16
Can Transformer Langauge Models Predict Psychometric Properties? ...
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
16
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern