Search Results for author:
Found 24 papers, 3 papers with code
Disentangling continuous and discrete linguistic signals in transformer-based sentence embeddings
We explore whether we can compress transformer-based sentence embeddings into a representation that separates different linguistic signals -- in particular, information relevant to subject-verb agreement and verb alternations.
Grammatical information in BERT sentence embeddings as two-dimensional arrays
Next, we show that various architectures can detect patterns in these two-dimensional reshaped sentence embeddings and successfully learn a model based on smaller amounts of simpler training data, which performs well on more complex test data.
Blackbird language matrices (BLM), a new task for rule-like generalization in neural networks: Motivations and Formal Specifications
In this paper, we provide the formal specification for the task and the generative process of its datasets.
Blackbird's language matrices (BLMs): a new benchmark to investigate disentangled generalisation in neural networks
Current successes of machine learning architectures are based on computationally expensive algorithms and prohibitively large amounts of data.
Word associations and the distance properties of context-aware word embeddings
While they do show asymmetry of similarities, their asymmetries do not map those of human association norms.
Multi-Adversarial Learning for Cross-Lingual Word Embeddings
Generative adversarial networks (GANs) have succeeded in inducing cross-lingual word embeddings -- maps of matching words across languages -- without supervision.
Bilingual Lexicon Induction
Cross-Lingual Word Embeddings
+1
Syntactic Parsing in Humans and Machines
To process the syntactic structures of a language in ways that are compatible with human expectations, we need computational representations of lexical and syntactic properties that form the basis of human knowledge of words and sentences.
Cross-Lingual Word Embeddings and the Structure of the Human Bilingual Lexicon
Research on the bilingual lexicon has uncovered fascinating interactions between the lexicons of the native language and of the second language in bilingual speakers.
Probing Word and Sentence Embeddings for Long-distance Dependencies Effects in French and English
We extend the work to sentence embeddings and to new languages.
Weakly-Supervised Concept-based Adversarial Learning for Cross-lingual Word Embeddings
Distributed representations of words which map each word to a continuous vector have proven useful in capturing important linguistic information not only in a single language but also across different languages.
Vectorial Semantic Spaces Do Not Encode Human Judgments of Intervention Similarity
We present results that show, under exhaustive and precise conditions, that one kind of word embeddings and the similarity spaces they define do not encode the properties of intervention similarity in long-distance dependencies, and that therefore they fail to represent this core linguistic notion.
CLCL (Geneva) DINN Parser: a Neural Network Dependency Parser Ten Years Later
This paper describes the University of Geneva{'}s submission to the CoNLL 2017 shared task Multilingual Parsing from Raw Text to Universal Dependencies (listed as the CLCL (Geneva) entry).
Modifications of Machine Translation Evaluation Metrics by Using Word Embeddings
Traditional machine translation evaluation metrics such as BLEU and WER have been widely used, but these metrics have poor correlations with human judgements because they badly represent word similarity and impose strict identity matching.
Multi-lingual Dependency Parsing Evaluation: a Large-scale Analysis of Word Order Properties using Artificial Data
We propose a method to evaluate the effects of word order of a language on dependency parsing performance, while controlling for confounding treebank properties.
