Search Results for author:
Found 10 papers, 5 papers with code
Identifying the Importance of Content Overlap for Better Cross-lingual Embedding Mappings
In this work, we analyze the performance and properties of cross-lingual word embedding models created by mapping-based alignment methods.
ProsperAMnet at FinCausal 2020, Task 1 & 2: Modeling causality in financial texts using multi-headed transformers
This paper introduces our efforts at the FinCasual shared task for modeling causality in financial utterances.
Codenames as a Game of Co-occurrence Counting
This is a hard challenge even with today’s advanced language technology methods. In our study, we create spymaster agents using four types of relatedness measures that require only a raw text corpus to produce.
Quasi-Multitask Learning: an Efficient Surrogate for Obtaining Model Ensembles
We propose the technique of quasi-multitask learning (Q-MTL), a simple and easy to implement modification of standard multitask learning, in which the tasks to be modeled are identical.
Combating the Curse of Multilinguality in Cross-Lingual WSD by Aligning Sparse Contextualized Word Representations
In this paper, we advocate for using large pre-trained monolingual language models in cross lingual zero-shot word sense disambiguation (WSD) coupled with a contextualized mapping mechanism.
Masked Latent Semantic Modeling: an Efficient Pre-training Alternative to Masked Language Modeling
In this paper, we propose an alternative to the classic masked language modeling (MLM) pre-training paradigm, where the objective is altered from the reconstruction of the exact identity of randomly selected masked subwords to the prediction of their latent semantic properties.
Massively Multilingual Sparse Word Representations
Finally, we are releasing our multilingual sparse word representations for the 27 typologically diverse set of languages that we conducted our various experiments on.
Frustratingly easy quasi-multitask learning
We propose the technique of quasi-multitask learning (Q-MTL), a simple and easy to implement modification of standard multitask learning, in which the tasks to be modeled are identical.
Sparse Coding of Neural Word Embeddings for Multilingual Sequence Labeling
In this paper we propose and carefully evaluate a sequence labeling framework which solely utilizes sparse indicator features derived from dense distributed word representations.
