activity
20172021
most citedLearning Rare Word Representations using Semantic Bridging

4 citations · 6 across the 4 of their papers we have counts for

collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2023

StrAE: Autoencoding for Pre-Trained Embeddings using Explicit Structure

Mattia Opper, Victor Prokhorov, N. Siddharth

This work presents StrAE: a Structured Autoencoder framework that through strict adherence to explicit structure, and use of a novel contrastive objective over tree-structured repr…

cs.CL20211 cited

Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasets

Lan Zhang, Victor Prokhorov, Ehsan Shareghi

To highlight the challenges of achieving representation disentanglement for text domain in an unsupervised setting, in this paper we select a representative set of successfully app…

cs.CL2020

Learning Sparse Sentence Encoding without Supervision: An Exploration of Sparsity in Variational Autoencoders

Victor Prokhorov, Yingzhen Li, Ehsan Shareghi +1

It has been long known that sparsity is an effective inductive bias for learning efficient representation of data in vectors with fixed dimensionality, and it has been explored in…

cs.CL20191 cited

On the Importance of the Kullback-Leibler Divergence Term in Variational Autoencoders for Text Generation

Victor Prokhorov, Ehsan Shareghi, Yingzhen Li +2

Variational Autoencoders (VAEs) are known to suffer from learning uninformative latent representation of the input due to issues such as approximated posterior collapse, or entangl…

cs.CL2019

Generating Knowledge Graph Paths from Textual Definitions using Sequence-to-Sequence Models

Victor Prokhorov, Mohammad Taher Pilehvar, Nigel Collier

We present a novel method for mapping unrestricted text to knowledge graph entities by framing the task as a sequence-to-sequence problem. Specifically, given the encoded state of…

cs.CL2018

Unseen Word Representation by Aligning Heterogeneous Lexical Semantic Spaces

Victor Prokhorov, Mohammad Taher Pilehvar, Dimitri Kartsaklis +2

Word embedding techniques heavily rely on the abundance of training data for individual words. Given the Zipfian distribution of words in natural language texts, a large number of…