Papers by Pedro Henrique Martins

4 papers
Joint Learning of Named Entity Recognition and Entity Linking (P19-2)

Copied to clipboard

Challenge: Named entity recognition and entity linking are two fundamentally related tasks . most approaches focus on the mention detection part, assuming the correct mentions have been detected .
Approach: They perform joint learning of named entity recognition and entity linking to leverage their relatedness.
Outcome: The proposed model achieves competitive results with the state-of-the-art in both NER and EL tasks.
∞-former: Infinite Memory Transformer (2022.acl-long)

Copied to clipboard

Challenge: Several efficient transformers have been proposed, but they all have a finite memory capacity and are forced to drop old information.
Approach: They propose an unbounded long-term memory extension that extends the vanilla transformer by using a continuous-space attention mechanism to attend over the long-time memory.
Outcome: The proposed model can model arbitrarily long contexts while keeping the computation budget fixed.
Sparse Text Generation (2020.emnlp-main)

Copied to clipboard

Challenge: Current text generators require sampling from a modified softmax to avoid degenerate text . entmax sampling creates a mismatch between training and testing conditions .
Approach: They propose to use entmax transformation to train and sample from a sparse language model to avoid degenerate text.
Outcome: The proposed model improves fluency and consistency, fewer repetitions, and n-gram diversity closer to human text.
Chunk-based Nearest Neighbor Machine Translation (2022.emnlp-main)

Copied to clipboard

Challenge: Semi-parametric models augment generation with retrieval, but require expensive retrieval operation for every generated token.
Approach: They propose a semi-parametric model which augments generation with retrieval by retrieving tokens from a datastore.
Outcome: The proposed model can retrieve chunks of tokens from the datastore, instead of a single token, with a low decoding speed.

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