Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Miguel Ballesteros

Miguel Ballesteros

A Bag of Tricks for Dialogue Summarization


Sep 16, 2021
Muhammad Khalifa, Miguel Ballesteros, Kathleen McKeown

Figure 1 for A Bag of Tricks for Dialogue Summarization
Figure 2 for A Bag of Tricks for Dialogue Summarization
Figure 3 for A Bag of Tricks for Dialogue Summarization
Figure 4 for A Bag of Tricks for Dialogue Summarization
* EMNLP 2021 - short paper 
  Access Paper or Ask Questions

How much pretraining data do language models need to learn syntax?


Sep 09, 2021
Laura Pérez-Mayos, Miguel Ballesteros, Leo Wanner

Figure 1 for How much pretraining data do language models need to learn syntax?
Figure 2 for How much pretraining data do language models need to learn syntax?
Figure 3 for How much pretraining data do language models need to learn syntax?
Figure 4 for How much pretraining data do language models need to learn syntax?
* To be published in proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021) 
  Access Paper or Ask Questions

Sequential Cross-Document Coreference Resolution


Apr 17, 2021
Emily Allaway, Shuai Wang, Miguel Ballesteros

Figure 1 for Sequential Cross-Document Coreference Resolution
Figure 2 for Sequential Cross-Document Coreference Resolution
Figure 3 for Sequential Cross-Document Coreference Resolution
Figure 4 for Sequential Cross-Document Coreference Resolution

  Access Paper or Ask Questions

On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations


Feb 10, 2021
Laura Pérez-Mayos, Roberto Carlini, Miguel Ballesteros, Leo Wanner

Figure 1 for On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations
Figure 2 for On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations
Figure 3 for On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations
Figure 4 for On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations

  Access Paper or Ask Questions

Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings


Jan 26, 2021
Kailash Karthik Saravanakumar, Miguel Ballesteros, Muthu Kumar Chandrasekaran, Kathleen McKeown

Figure 1 for Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings
Figure 2 for Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings
Figure 3 for Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings
Figure 4 for Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings
* To appear in Proceedings of The 16th Conference of the European Chapter of the Association for Computational Linguistics 
  Access Paper or Ask Questions

To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging


Oct 27, 2020
Kasturi Bhattacharjee, Miguel Ballesteros, Rishita Anubhai, Smaranda Muresan, Jie Ma, Faisal Ladhak, Yaser Al-Onaizan

Figure 1 for To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging
Figure 2 for To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging
Figure 3 for To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging
Figure 4 for To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging
* Accepted in the Proceedings of 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)(https://2020.emnlp.org/papers/main) 
  Access Paper or Ask Questions

Linking Entities to Unseen Knowledge Bases with Arbitrary Schemas


Oct 21, 2020
Yogarshi Vyas, Miguel Ballesteros

Figure 1 for Linking Entities to Unseen Knowledge Bases with Arbitrary Schemas
Figure 2 for Linking Entities to Unseen Knowledge Bases with Arbitrary Schemas
Figure 3 for Linking Entities to Unseen Knowledge Bases with Arbitrary Schemas
Figure 4 for Linking Entities to Unseen Knowledge Bases with Arbitrary Schemas

  Access Paper or Ask Questions

Transition-based Parsing with Stack-Transformers


Oct 20, 2020
Ramon Fernandez Astudillo, Miguel Ballesteros, Tahira Naseem, Austin Blodgett, Radu Florian

Figure 1 for Transition-based Parsing with Stack-Transformers
Figure 2 for Transition-based Parsing with Stack-Transformers
Figure 3 for Transition-based Parsing with Stack-Transformers
Figure 4 for Transition-based Parsing with Stack-Transformers
* Accepted to Findings of EMNLP2020, open review https://openreview.net/forum?id=b36spsuUAde, code https://github.com/IBM/transition-amr-parser 
  Access Paper or Ask Questions

Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models


Oct 12, 2020
Ethan Wilcox, Peng Qian, Richard Futrell, Ryosuke Kohita, Roger Levy, Miguel Ballesteros

Figure 1 for Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models
Figure 2 for Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models
Figure 3 for Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models
Figure 4 for Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models
* To appear at EMNLP 2020 
  Access Paper or Ask Questions

Resource-Enhanced Neural Model for Event Argument Extraction


Oct 06, 2020
Jie Ma, Shuai Wang, Rishita Anubhai, Miguel Ballesteros, Yaser Al-Onaizan

Figure 1 for Resource-Enhanced Neural Model for Event Argument Extraction
Figure 2 for Resource-Enhanced Neural Model for Event Argument Extraction
Figure 3 for Resource-Enhanced Neural Model for Event Argument Extraction
Figure 4 for Resource-Enhanced Neural Model for Event Argument Extraction
* Findings of EMNLP 2020 
  Access Paper or Ask Questions

Severing the Edge Between Before and After: Neural Architectures for Temporal Ordering of Events


Apr 08, 2020
Miguel Ballesteros, Rishita Anubhai, Shuai Wang, Nima Pourdamghani, Yogarshi Vyas, Jie Ma, Parminder Bhatia, Kathleen McKeown, Yaser Al-Onaizan

Figure 1 for Severing the Edge Between Before and After: Neural Architectures for Temporal Ordering of Events

  Access Paper or Ask Questions

Transition-Based Dependency Parsing using Perceptron Learner


Jan 28, 2020
Rahul Radhakrishnan Iyer, Miguel Ballesteros, Chris Dyer, Robert Frederking

Figure 1 for Transition-Based Dependency Parsing using Perceptron Learner
Figure 2 for Transition-Based Dependency Parsing using Perceptron Learner
Figure 3 for Transition-Based Dependency Parsing using Perceptron Learner
Figure 4 for Transition-Based Dependency Parsing using Perceptron Learner
* This was part of an assignment at my graduate course at LTI. This does not offer any major novelties 
  Access Paper or Ask Questions

Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning


May 31, 2019
Tahira Naseem, Abhishek Shah, Hui Wan, Radu Florian, Salim Roukos, Miguel Ballesteros

Figure 1 for Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning
* Accepted as short paper at ACL 2019 
  Access Paper or Ask Questions

Structural Supervision Improves Learning of Non-Local Grammatical Dependencies


Apr 06, 2019
Ethan Wilcox, Peng Qian, Richard Futrell, Miguel Ballesteros, Roger Levy

Figure 1 for Structural Supervision Improves Learning of Non-Local Grammatical Dependencies
Figure 2 for Structural Supervision Improves Learning of Non-Local Grammatical Dependencies
Figure 3 for Structural Supervision Improves Learning of Non-Local Grammatical Dependencies
Figure 4 for Structural Supervision Improves Learning of Non-Local Grammatical Dependencies
* To appear: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 
  Access Paper or Ask Questions

Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State


Mar 08, 2019
Richard Futrell, Ethan Wilcox, Takashi Morita, Peng Qian, Miguel Ballesteros, Roger Levy

Figure 1 for Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State
Figure 2 for Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State
Figure 3 for Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State
Figure 4 for Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State
* Accepted to NAACL 2019. Not yet edited into the camera-ready version 
  Access Paper or Ask Questions

Recursive Subtree Composition in LSTM-Based Dependency Parsing


Feb 26, 2019
Miryam de Lhoneux, Miguel Ballesteros, Joakim Nivre

Figure 1 for Recursive Subtree Composition in LSTM-Based Dependency Parsing
Figure 2 for Recursive Subtree Composition in LSTM-Based Dependency Parsing
Figure 3 for Recursive Subtree Composition in LSTM-Based Dependency Parsing
Figure 4 for Recursive Subtree Composition in LSTM-Based Dependency Parsing
* Accepted at NAACL 2019 
  Access Paper or Ask Questions

Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs


Jul 05, 2018
Swabha Swayamdipta, Miguel Ballesteros, Chris Dyer, Noah A. Smith

Figure 1 for Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs
Figure 2 for Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs
Figure 3 for Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs
Figure 4 for Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs
* Proceedings of CoNLL 2016; 13 pages, 5 figures 
  Access Paper or Ask Questions

Multilingual Neural Machine Translation with Task-Specific Attention


Jun 08, 2018
Graeme Blackwood, Miguel Ballesteros, Todd Ward

Figure 1 for Multilingual Neural Machine Translation with Task-Specific Attention
Figure 2 for Multilingual Neural Machine Translation with Task-Specific Attention
Figure 3 for Multilingual Neural Machine Translation with Task-Specific Attention
Figure 4 for Multilingual Neural Machine Translation with Task-Specific Attention
* COLING 2018 
  Access Paper or Ask Questions

Scheduled Multi-Task Learning: From Syntax to Translation


Apr 24, 2018
Eliyahu Kiperwasser, Miguel Ballesteros

* Transactions of the Association for Computational Linguistics, 6:225-240 (2018) 
  Access Paper or Ask Questions

Multimodal Emoji Prediction


Apr 17, 2018
Francesco Barbieri, Miguel Ballesteros, Francesco Ronzano, Horacio Saggion

Figure 1 for Multimodal Emoji Prediction
Figure 2 for Multimodal Emoji Prediction
Figure 3 for Multimodal Emoji Prediction
Figure 4 for Multimodal Emoji Prediction
* NAACL 2018 (short) 
  Access Paper or Ask Questions

Pieces of Eight: 8-bit Neural Machine Translation


Apr 13, 2018
Jerry Quinn, Miguel Ballesteros

Figure 1 for Pieces of Eight: 8-bit Neural Machine Translation
Figure 2 for Pieces of Eight: 8-bit Neural Machine Translation
Figure 3 for Pieces of Eight: 8-bit Neural Machine Translation
Figure 4 for Pieces of Eight: 8-bit Neural Machine Translation
* To appear at NAACL 2018 Industry Track 
  Access Paper or Ask Questions

AMR Parsing using Stack-LSTMs


Aug 02, 2017
Miguel Ballesteros, Yaser Al-Onaizan

Figure 1 for AMR Parsing using Stack-LSTMs
Figure 2 for AMR Parsing using Stack-LSTMs
Figure 3 for AMR Parsing using Stack-LSTMs
* EMNLP 2017 
  Access Paper or Ask Questions

Are Emojis Predictable?


Feb 24, 2017
Francesco Barbieri, Miguel Ballesteros, Horacio Saggion

Figure 1 for Are Emojis Predictable?
Figure 2 for Are Emojis Predictable?
Figure 3 for Are Emojis Predictable?
Figure 4 for Are Emojis Predictable?
* To appear at EACL 2017 
  Access Paper or Ask Questions

DyNet: The Dynamic Neural Network Toolkit


Jan 15, 2017
Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, Kevin Duh, Manaal Faruqui, Cynthia Gan, Dan Garrette, Yangfeng Ji, Lingpeng Kong, Adhiguna Kuncoro, Gaurav Kumar, Chaitanya Malaviya, Paul Michel, Yusuke Oda, Matthew Richardson, Naomi Saphra, Swabha Swayamdipta, Pengcheng Yin

Figure 1 for DyNet: The Dynamic Neural Network Toolkit
Figure 2 for DyNet: The Dynamic Neural Network Toolkit
Figure 3 for DyNet: The Dynamic Neural Network Toolkit
Figure 4 for DyNet: The Dynamic Neural Network Toolkit
* 33 pages 
  Access Paper or Ask Questions

What Do Recurrent Neural Network Grammars Learn About Syntax?


Jan 10, 2017
Adhiguna Kuncoro, Miguel Ballesteros, Lingpeng Kong, Chris Dyer, Graham Neubig, Noah A. Smith

Figure 1 for What Do Recurrent Neural Network Grammars Learn About Syntax?
Figure 2 for What Do Recurrent Neural Network Grammars Learn About Syntax?
Figure 3 for What Do Recurrent Neural Network Grammars Learn About Syntax?
Figure 4 for What Do Recurrent Neural Network Grammars Learn About Syntax?
* 10 pages. To appear in EACL 2017, Valencia, Spain 
  Access Paper or Ask Questions

Recurrent Neural Network Grammars


Oct 12, 2016
Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, Noah A. Smith

Figure 1 for Recurrent Neural Network Grammars
Figure 2 for Recurrent Neural Network Grammars
Figure 3 for Recurrent Neural Network Grammars
Figure 4 for Recurrent Neural Network Grammars
* Proceedings of NAACL 2016 (contains corrigendum) 
  Access Paper or Ask Questions

Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser


Sep 24, 2016
Adhiguna Kuncoro, Miguel Ballesteros, Lingpeng Kong, Chris Dyer, Noah A. Smith

Figure 1 for Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser
Figure 2 for Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser
Figure 3 for Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser
Figure 4 for Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser
* 10 pages. To appear at EMNLP 2016 
  Access Paper or Ask Questions

Training with Exploration Improves a Greedy Stack-LSTM Parser


Sep 13, 2016
Miguel Ballesteros, Yoav Goldberg, Chris Dyer, Noah A. Smith

Figure 1 for Training with Exploration Improves a Greedy Stack-LSTM Parser
* In proceedings of EMNLP 2016 
  Access Paper or Ask Questions