 Interactive Text GenerationConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation
in Natural Language GenerationInternational Conference on Learning Representations (ICLR), 2023 |
 DC-MBR: Distributional Cooling for Minimum Bayesian Risk DecodingInternational Conference on Language Resources and Evaluation (LREC), 2022 |
 Monotonic segmental attention for automatic speech recognitionSpoken Language Technology Workshop (SLT), 2022 |
 A Continuum of Generation Tasks for Investigating Length Bias and
Degenerate RepetitionBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP), 2022 |
 The Tail Wagging the Dog: Dataset Construction Biases of Social Bias
BenchmarksAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 CTC Alignments Improve Autoregressive TranslationConference of the European Chapter of the Association for Computational Linguistics (EACL), 2022 |
 PEER: A Collaborative Language ModelInternational Conference on Learning Representations (ICLR), 2022 |
 Exploring Length Generalization in Large Language ModelsNeural Information Processing Systems (NeurIPS), 2022 |
 So Different Yet So Alike! Constrained Unsupervised Text Style TransferAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Quality-Aware Decoding for Neural Machine TranslationNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 Patrick Fernandes António Farinhas Ricardo Rei José G. C. de Souza Perez Ogayo Graham Neubig Marcely Zanon Boito |
 Jam or Cream First? Modeling Ambiguity in Neural Machine Translation
with SCONESNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 On the Role of Pre-trained Language Models in Word Ordering: A Case
Study with BARTInternational Conference on Computational Linguistics (COLING), 2022 |
 A Call for Clarity in Beam Search: How It Works and When It StopsInternational Conference on Language Resources and Evaluation (LREC), 2022 |
 Uncertainty Determines the Adequacy of the Mode and the Tractability of
Decoding in Sequence-to-Sequence ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 On Decoding Strategies for Neural Text GeneratorsTransactions of the Association for Computational Linguistics (TACL), 2022 |
 Sequence-to-Sequence Knowledge Graph Completion and Question AnsweringAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Pretrained Language Models for Text Generation: A SurveyACM Computing Surveys (ACM CSUR), 2022 |
 Distilling the Knowledge of Large-scale Generative Models into Retrieval
Models for Efficient Open-domain ConversationConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural
Machine TranslationConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 What Do You Get When You Cross Beam Search with Nucleus Sampling?First Workshop on Insights from Negative Results in NLP (Insights), 2021 |
 VAD-free Streaming Hybrid CTC/Attention ASR for Unsegmented RecordingInterspeech (Interspeech), 2021 |
 Digging Errors in NMT: Evaluating and Understanding Model Errors from
Partial Hypothesis SpaceConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Automatic Document Sketching: Generating Drafts from Analogous TextsFindings (Findings), 2021 |
 Language Model Evaluation Beyond PerplexityAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 |
 Searchable Hidden Intermediates for End-to-End Models of Decomposable
Sequence TasksNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 Constrained Language Models Yield Few-Shot Semantic ParsersConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Smoothing and Shrinking the Sparse Seq2Seq Search SpaceNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 Ben Peters André F. T. Martins |
 Searching for Search Errors in Neural Morphological InflectionConference of the European Chapter of the Association for Computational Linguistics (EACL), 2021 |
 Incremental Beam Manipulation for Natural Language GenerationConference of the European Chapter of the Association for Computational Linguistics (EACL), 2021 |
 How Can We Know When Language Models Know? On the Calibration of
Language Models for Question AnsweringTransactions of the Association for Computational Linguistics (TACL), 2020 |
 On Long-Tailed Phenomena in Neural Machine TranslationFindings (Findings), 2020 |
 If beam search is the answer, what was the question?Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020 |
 Task-Oriented Dialogue as Dataflow SynthesisTransactions of the Association for Computational Linguistics (TACL), 2020 |
 Best-First Beam SearchTransactions of the Association for Computational Linguistics (TACL), 2020 |
