Papers by Ryan Culkin

4 papers
Multi-Sentence Argument Linking (2020.acl-main)

Copied to clipboard

Challenge: Existing datasets for cross-sentence linking are small, resulting in a lack of a model for argument linking.
Approach: They propose a document-level model for finding argument spans that fill an event’s roles by combining semantic role labeling and coreference resolution.
Outcome: The proposed model is able to connect arguments in sentence-level role labeling and coreference resolution on 9,124 annotated events across 139 types.
Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting (N19-1)

Copied to clipboard

Challenge: Lexically-constrained sequence decoding allows for explicit positive or negative phrase-based constraints to be placed on target output strings in machine translation or monolingual text rewriting tasks.
Approach: They propose a vectorized dynamic beam allocation algorithm which extends work in lexically-constrained decoding to work with batching.
Outcome: The proposed method improves on natural language inference, question answering and machine translation tasks by fivefold .
Neural-Davidsonian Semantic Proto-role Labeling (D18-1)

Copied to clipboard

Challenge: Existing models for semantic proto-role labeling are based on a bidirectional LSTM encoding strategy.
Approach: They propose a neural model for semantic proto-role labeling using a bidirectional LSTM encoding strategy that is adapted for the task.
Outcome: The proposed model achieves state-of-the-art in a sentence with a LSTM encoder and a decoder.
Iterative Paraphrastic Augmentation with Discriminative Span Alignment (2021.tacl-1)

Copied to clipboard

Challenge: Existing datasets can be expanded or created using a small, manually produced seed corpus.
Approach: They propose a paraphrastic augmentation strategy based on sentence-level lexically constrained paraphrases and discriminative span alignment.
Outcome: The proposed approach allows for the large-scale expansion of existing datasets or the rapid creation of new datasets using a small, manually produced seed corpus.

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