Papers by Vassilis Plachouras

4 papers
A Comparison of Two Paraphrase Models for Taxonomy Augmentation (N18-2)

Copied to clipboard

Challenge: a taxonomy is often used to look up concepts in text documents.
Approach: They compare two state-of-the-art paraphrase models with a paraphrase dataset . they find that paraphrasing is a viable method to augment taxonomies with more terms .
Outcome: The proposed model outperforms the previous model on the risk domain.
How Decoding Strategies Affect the Verifiability of Generated Text (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in pre-trained language models have generated text of an increasingly high quality.
Approach: They propose a decoding strategy that produces less repetitive and more verifiable text.
Outcome: The proposed method produces less repetitive and more verifiable text than previously used decoding strategies.
KILT: a Benchmark for Knowledge Intensive Language Tasks (2021.naacl-main)

Copied to clipboard

Challenge: Existing models for knowledge-intensive language tasks require access to large, external knowledge sources.
Approach: They propose a benchmark for knowledge-intensive language tasks (KILT) they test a shared dense vector index coupled with a seq2seq model to generate disambiguated text.
Outcome: The proposed model outperforms tailor-made approaches on fact checking, open-domain question answering and dialog by generating disambiguated text.
attr2vec: Jointly Learning Word and Contextual Attribute Embeddings with Factorization Machines (N18-1)

Copied to clipboard

Challenge: popular word embeddings are used to learn vector representations from the context of words.
Approach: They propose a framework for jointly learning embeddings for words and contextual attributes based on factorization machines.
Outcome: The proposed framework improves on a text classification task compared to learning embeddings independently.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations