no code implementations • COLING 2022 • Fei-Tzin Lee, Miguel Ballesteros, Feng Nan, Kathleen McKeown
Large pretrained language models offer powerful generation capabilities, but cannot be reliably controlled at a sub-sentential level.
no code implementations • 21 Mar 2023 • Ming Shen, Jie Ma, Shuai Wang, Yogarshi Vyas, Kalpit Dixit, Miguel Ballesteros, Yassine Benajiba
Opinion summarization provides an important solution for summarizing opinions expressed among a large number of reviews.
Natural Language Inference Unsupervised Opinion Summarization
no code implementations • 23 Feb 2023 • Katerina Margatina, Shuai Wang, Yogarshi Vyas, Neha Anna John, Yassine Benajiba, Miguel Ballesteros
Temporal concept drift refers to the problem of data changing over time.
no code implementations • 9 Nov 2022 • Hardy Hardy, Miguel Ballesteros, Faisal Ladhak, Muhammad Khalifa, Vittorio Castelli, Kathleen McKeown
Summarizing novel chapters is a difficult task due to the input length and the fact that sentences that appear in the desired summaries draw content from multiple places throughout the chapter.
no code implementations • 12 Oct 2022 • Siddharth Varia, Shuai Wang, Kishaloy Halder, Robert Vacareanu, Miguel Ballesteros, Yassine Benajiba, Neha Anna John, Rishita Anubhai, Smaranda Muresan, Dan Roth
Aspect-based Sentiment Analysis (ABSA) is a fine-grained sentiment analysis task which involves four elements from user-generated texts: aspect term, aspect category, opinion term, and sentiment polarity.
no code implementations • 11 Oct 2022 • Muhammad Khalifa, Yogarshi Vyas, Shuai Wang, Graham Horwood, Sunil Mallya, Miguel Ballesteros
The standard classification setting where categories are fixed during both training and testing falls short in dynamic environments where new document categories could potentially emerge.
no code implementations • NAACL 2022 • Vishakh Padmakumar, Leonard Lausen, Miguel Ballesteros, Sheng Zha, He He, George Karypis
Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks.
1 code implementation • Findings (ACL) 2022 • Jie Ma, Miguel Ballesteros, Srikanth Doss, Rishita Anubhai, Sunil Mallya, Yaser Al-Onaizan, Dan Roth
We study the problem of few shot learning for named entity recognition.
no code implementations • EMNLP 2021 • Muhammad Khalifa, Miguel Ballesteros, Kathleen McKeown
Dialogue summarization comes with its own peculiar challenges as opposed to news or scientific articles summarization.
no code implementations • EMNLP 2021 • Laura Pérez-Mayos, Miguel Ballesteros, Leo Wanner
This calls for a study of the impact of pretraining data size on the knowledge of the models.
no code implementations • EMNLP 2021 • Emily Allaway, Shuai Wang, Miguel Ballesteros
Relating entities and events in text is a key component of natural language understanding.
coreference-resolution Cross Document Coreference Resolution +1
no code implementations • EACL 2021 • Laura Pérez-Mayos, Roberto Carlini, Miguel Ballesteros, Leo Wanner
The adaptation of pretrained language models to solve supervised tasks has become a baseline in NLP, and many recent works have focused on studying how linguistic information is encoded in the pretrained sentence representations.
no code implementations • EACL 2021 • Kailash Karthik Saravanakumar, Miguel Ballesteros, Muthu Kumar Chandrasekaran, Kathleen McKeown
We propose a method for online news stream clustering that is a variant of the non-parametric streaming K-means algorithm.
no code implementations • EMNLP 2020 • Kasturi Bhattacharjee, Miguel Ballesteros, Rishita Anubhai, Smaranda Muresan, Jie Ma, Faisal Ladhak, Yaser Al-Onaizan
Leveraging large amounts of unlabeled data using Transformer-like architectures, like BERT, has gained popularity in recent times owing to their effectiveness in learning general representations that can then be further fine-tuned for downstream tasks to much success.
no code implementations • NAACL 2021 • Yogarshi Vyas, Miguel Ballesteros
In entity linking, mentions of named entities in raw text are disambiguated against a knowledge base (KB).
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Ramon Fernandez Astudillo, Miguel Ballesteros, Tahira Naseem, Austin Blodgett, Radu Florian
Modeling the parser state is key to good performance in transition-based parsing.
Ranked #15 on AMR Parsing on LDC2017T10
no code implementations • EMNLP 2020 • Ethan Wilcox, Peng Qian, Richard Futrell, Ryosuke Kohita, Roger Levy, Miguel Ballesteros
Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Jie Ma, Shuai Wang, Rishita Anubhai, Miguel Ballesteros, Yaser Al-Onaizan
(2) Capturing the long-range dependency, specifically, the connection between an event trigger and a distant event argument.
no code implementations • 1 Jul 2020 • Miguel Ballesteros, Tristan Benoist, Martin Fraas, Jürg Fröhlich
The phenomenon that a quantum particle propagating in a detector, such as a Wilson cloud chamber, leaves a track close to a classical trajectory is analyzed.
Mathematical Physics Mathematical Physics Quantum Physics
no code implementations • EMNLP 2020 • Miguel Ballesteros, Rishita Anubhai, Shuai Wang, Nima Pourdamghani, Yogarshi Vyas, Jie Ma, Parminder Bhatia, Kathleen McKeown, Yaser Al-Onaizan
In this paper, we propose a neural architecture and a set of training methods for ordering events by predicting temporal relations.
no code implementations • 22 Jan 2020 • Rahul Radhakrishnan Iyer, Miguel Ballesteros, Chris Dyer, Robert Frederking
Syntactic parsing using dependency structures has become a standard technique in natural language processing with many different parsing models, in particular data-driven models that can be trained on syntactically annotated corpora.
no code implementations • ACL 2019 • Tahira Naseem, Abhishek Shah, Hui Wan, Radu Florian, Salim Roukos, Miguel Ballesteros
Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs.
Ranked #20 on AMR Parsing on LDC2017T10
2 code implementations • NAACL 2019 • Richard Futrell, Ethan Wilcox, Takashi Morita, Peng Qian, Miguel Ballesteros, Roger Levy
We deploy the methods of controlled psycholinguistic experimentation to shed light on the extent to which the behavior of neural network language models reflects incremental representations of syntactic state.
no code implementations • NAACL 2019 • Ethan Wilcox, Peng Qian, Richard Futrell, Miguel Ballesteros, Roger Levy
State-of-the-art LSTM language models trained on large corpora learn sequential contingencies in impressive detail and have been shown to acquire a number of non-local grammatical dependencies with some success.
1 code implementation • NAACL 2019 • Miryam de Lhoneux, Miguel Ballesteros, Joakim Nivre
When ablating the forward LSTM, performance drops less dramatically and composition recovers a substantial part of the gap, indicating that a forward LSTM and composition capture similar information.
no code implementations • CONLL 2018 • Hui Wan, Tahira Naseem, Young-suk Lee, Vittorio Castelli, Miguel Ballesteros
This paper presents the IBM Research AI submission to the CoNLL 2018 Shared Task on Parsing Universal Dependencies.
no code implementations • COLING 2018 • Graeme Blackwood, Miguel Ballesteros, Todd Ward
Multilingual machine translation addresses the task of translating between multiple source and target languages.
no code implementations • SEMEVAL 2018 • Francesco Barbieri, Jose Camacho-Collados, Francesco Ronzano, Luis Espinosa-Anke, Miguel Ballesteros, Valerio Basile, Viviana Patti, Horacio Saggion
This paper describes the results of the first Shared Task on Multilingual Emoji Prediction, organized as part of SemEval 2018.
no code implementations • TACL 2018 • Eliyahu Kiperwasser, Miguel Ballesteros
Neural encoder-decoder models of machine translation have achieved impressive results, while learning linguistic knowledge of both the source and target languages in an implicit end-to-end manner.
no code implementations • NAACL 2018 • Jerry Quinn, Miguel Ballesteros
Neural machine translation has achieved levels of fluency and adequacy that would have been surprising a short time ago.
1 code implementation • NAACL 2018 • Francesco Barbieri, Miguel Ballesteros, Francesco Ronzano, Horacio Saggion
Emojis are small images that are commonly included in social media text messages.
no code implementations • WS 2017 • Francesco Barbieri, Luis Espinosa-Anke, Miguel Ballesteros, Juan Soler-Company, Horacio Saggion
Videogame streaming platforms have become a paramount example of noisy user-generated text.
no code implementations • WS 2017 • Miguel Ballesteros, Xavier Carreras
We present a neural transition-based parser for spinal trees, a dependency representation of constituent trees.
no code implementations • EMNLP 2017 • Miguel Ballesteros, Yaser Al-Onaizan
We present a transition-based AMR parser that directly generates AMR parses from plain text.
Ranked #11 on AMR Parsing on LDC2014T12
no code implementations • CL 2017 • Miguel Ballesteros, Chris Dyer, Yoav Goldberg, Noah A. Smith
During training, dynamic oracles alternate between sampling parser states from the training data and from the model as it is being learned, making the model more robust to the kinds of errors that will be made at test time.
3 code implementations • EACL 2017 • Francesco Barbieri, Miguel Ballesteros, Horacio Saggion
Emojis are ideograms which are naturally combined with plain text to visually complement or condense the meaning of a message.
4 code implementations • 15 Jan 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
In the static declaration strategy that is used in toolkits like Theano, CNTK, and TensorFlow, the user first defines a computation graph (a symbolic representation of the computation), and then examples are fed into an engine that executes this computation and computes its derivatives.
1 code implementation • EACL 2017 • Adhiguna Kuncoro, Miguel Ballesteros, Lingpeng Kong, Chris Dyer, Graham Neubig, Noah A. Smith
We investigate what information they learn, from a linguistic perspective, through various ablations to the model and the data, and by augmenting the model with an attention mechanism (GA-RNNG) to enable closer inspection.
Ranked #19 on Constituency Parsing on Penn Treebank
1 code implementation • EMNLP 2016 • Adhiguna Kuncoro, Miguel Ballesteros, Lingpeng Kong, Chris Dyer, Noah A. Smith
We introduce two first-order graph-based dependency parsers achieving a new state of the art.
Ranked #18 on Dependency Parsing on Penn Treebank
1 code implementation • CONLL 2016 • Swabha Swayamdipta, Miguel Ballesteros, Chris Dyer, Noah A. Smith
We present a transition-based parser that jointly produces syntactic and semantic dependencies.
no code implementations • 21 Mar 2016 • Bernd Bohnet, Miguel Ballesteros, Ryan Mcdonald, Joakim Nivre
Experiments on five languages show that feature selection can result in more compact models as well as higher accuracy under all conditions, but also that a dynamic ordering works better than a static ordering and that joint systems benefit more than standalone taggers.
no code implementations • 11 Mar 2016 • Miguel Ballesteros, Yoav Goldberg, Chris Dyer, Noah A. Smith
We adapt the greedy Stack-LSTM dependency parser of Dyer et al. (2015) to support a training-with-exploration procedure using dynamic oracles(Goldberg and Nivre, 2013) instead of cross-entropy minimization.
Ranked #2 on Chinese Dependency Parsing on Chinese Pennbank
42 code implementations • NAACL 2016 • Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, Chris Dyer
State-of-the-art named entity recognition systems rely heavily on hand-crafted features and domain-specific knowledge in order to learn effectively from the small, supervised training corpora that are available.
Ranked #8 on Named Entity Recognition (NER) on CoNLL++
6 code implementations • NAACL 2016 • Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, Noah A. Smith
We introduce recurrent neural network grammars, probabilistic models of sentences with explicit phrase structure.
Ranked #24 on Constituency Parsing on Penn Treebank
1 code implementation • TACL 2016 • Waleed Ammar, George Mulcaire, Miguel Ballesteros, Chris Dyer, Noah A. Smith
We train one multilingual model for dependency parsing and use it to parse sentences in several languages.
1 code implementation • EMNLP 2015 • Miguel Ballesteros, Chris Dyer, Noah A. Smith
We present extensions to a continuous-state dependency parsing method that makes it applicable to morphologically rich languages.
7 code implementations • IJCNLP 2015 • Chris Dyer, Miguel Ballesteros, Wang Ling, Austin Matthews, Noah A. Smith
We propose a technique for learning representations of parser states in transition-based dependency parsers.
no code implementations • LREC 2012 • Miguel Ballesteros, Joakim Nivre
Freely available statistical parsers often require careful optimization to produce state-of-the-art results, which can be a non-trivial task especially for application developers who are not interested in parsing research for its own sake.