no code implementations • 1 Jun 2009 • Shay Cohen, Noah A. Smith
We present a family of priors over probabilistic grammar weights, called the shared logistic normal distribution.
Ranked #4 on Unsupervised Dependency Parsing on Penn Treebank
Dependency Grammar Induction Unsupervised Dependency Parsing
no code implementations • NeurIPS 2010 • Noah A. Smith, Shay B. Cohen
Probabilistic grammars are generative statistical models that are useful for compositional and sequential structures.
no code implementations • 18 Oct 2012 • Jacob Eisenstein, Brendan O'Connor, Noah A. Smith, Eric P. Xing
Computer-mediated communication is driving fundamental changes in the nature of written language.
no code implementations • 6 May 2013 • David Bamman, Noah A. Smith
We consider the unsupervised alignment of the full text of a book with a human-written summary.
1 code implementation • WS 2013 • Nathan Schneider, Brendan O'Connor, Naomi Saphra, David Bamman, Manaal Faruqui, Noah A. Smith, Chris Dyer, Jason Baldridge
We introduce a framework for lightweight dependency syntax annotation.
no code implementations • 9 Oct 2013 • Dani Yogatama, Bryan R. Routledge, Noah A. Smith
We consider the scenario where the parameters of a probabilistic model are expected to vary over time.
no code implementations • 25 Oct 2013 • Shiladitya Sinha, Chris Dyer, Kevin Gimpel, Noah A. Smith
We study the relationship between social media output and National Football League (NFL) games, using a dataset containing messages from Twitter and NFL game statistics.
no code implementations • TACL 2014 • Dani Yogatama, Chong Wang, Bryan R. Routledge, Noah A. Smith, Eric P. Xing
We present a probabilistic language model that captures temporal dynamics and conditions on arbitrary non-linguistic context features.
no code implementations • TACL 2014 • David Bamman, Noah A. Smith
We present a method for discovering abstract event classes in biographies, based on a probabilistic latent-variable model.
no code implementations • TACL 2014 • Nathan Schneider, Emily Danchik, Chris Dyer, Noah A. Smith
We present a novel representation, evaluation measure, and supervised models for the task of identifying the multiword expressions (MWEs) in a sentence, resulting in a lexical semantic segmentation.
no code implementations • 16 Apr 2014 • Lingpeng Kong, Noah A. Smith
Stanford typed dependencies are a widely desired representation of natural language sentences, but parsing is one of the major computational bottlenecks in text analysis systems.
no code implementations • LREC 2014 • Nathan Schneider, Spencer Onuffer, Nora Kazour, Emily Danchik, Michael T. Mordowanec, Henrietta Conrad, Noah A. Smith
Multiword expressions (MWEs) are quite frequent in languages such as English, but their diversity, the scarcity of individual MWE types, and contextual ambiguity have presented obstacles to corpus-based studies and NLP systems addressing them as a class.
no code implementations • 8 Jun 2014 • Dani Yogatama, Manaal Faruqui, Chris Dyer, Noah A. Smith
We propose a new method for learning word representations using hierarchical regularization in sparse coding inspired by the linguistic study of word meanings.
no code implementations • 29 Sep 2014 • Yanchuan Sim, Bryan Routledge, Noah A. Smith
We explore the idea that authoring a piece of text is an act of maximizing one's expected utility.
1 code implementation • NeurIPS 2014 • Waleed Ammar, Chris Dyer, Noah A. Smith
We introduce a framework for unsupervised learning of structured predictors with overlapping, global features.
2 code implementations • HLT 2015 • Manaal Faruqui, Jesse Dodge, Sujay K. Jauhar, Chris Dyer, Eduard Hovy, Noah A. Smith
Vector space word representations are learned from distributional information of words in large corpora.
no code implementations • EMNLP 2015 • Dani Yogatama, Noah A. Smith
When applying machine learning to problems in NLP, there are many choices to make about how to represent input texts.
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.
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.
2 code implementations • 18 Nov 2015 • Lingpeng Kong, Chris Dyer, Noah A. Smith
Representations of the input segments (i. e., contiguous subsequences of the input) are computed by encoding their constituent tokens using bidirectional recurrent neural nets, and these "segment embeddings" are used to define compatibility scores with output labels.
no code implementations • 2 Dec 2015 • Philip Massey, Patrick Xia, David Bamman, Noah A. Smith
We present a dataset of manually annotated relationships between characters in literary texts, in order to support the training and evaluation of automatic methods for relation type prediction in this domain (Makazhanov et al., 2014; Kokkinakis, 2013) and the broader computational analysis of literary character (Elson et al., 2010; Bamman et al., 2014; Vala et al., 2015; Flekova and Gurevych, 2015).
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 • 5 Feb 2016 • Waleed Ammar, George Mulcaire, Yulia Tsvetkov, Guillaume Lample, Chris Dyer, Noah A. Smith
We introduce new methods for estimating and evaluating embeddings of words in more than fifty languages in a single shared embedding space.
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 #25 on Constituency Parsing on Penn Treebank
no code implementations • 1 Mar 2016 • Liang Lu, Lingpeng Kong, Chris Dyer, Noah A. Smith, Steve Renals
This model connects the segmental conditional random field (CRF) with a recurrent neural network (RNN) used for feature extraction.
Ranked #16 on Speech Recognition on TIMIT
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
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.
1 code implementation • WS 2016 • Aaron Jaech, George Mulcaire, Shobhit Hathi, Mari Ostendorf, Noah A. Smith
Social media messages' brevity and unconventional spelling pose a challenge to language identification.
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 #17 on Dependency Parsing on Penn Treebank
no code implementations • 28 Sep 2016 • Kazuya Kawakami, Chris Dyer, Bryan R. Routledge, Noah A. Smith
We present a neural network architecture to predict a point in color space from the sequence of characters in the color's name.
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 #20 on Constituency Parsing on Penn Treebank
1 code implementation • CONLL 2017 • Roy Schwartz, Maarten Sap, Ioannis Konstas, Li Zilles, Yejin Choi, Noah A. Smith
A writer's style depends not just on personal traits but also on her intent and mental state.
no code implementations • 21 Feb 2017 • Liang Lu, Lingpeng Kong, Chris Dyer, Noah A. Smith
Segmental conditional random fields (SCRFs) and connectionist temporal classification (CTC) are two sequence labeling methods used for end-to-end training of speech recognition models.
no code implementations • WS 2017 • Roy Schwartz, Maarten Sap, Ioannis Konstas, Leila Zilles, Yejin Choi, Noah A. Smith
This paper describes University of Washington NLP{'}s submission for the Linking Models of Lexical, Sentential and Discourse-level Semantics (LSDSem 2017) shared task{---}the Story Cloze Task.
1 code implementation • ACL 2017 • Hao Peng, Sam Thomson, Noah A. Smith
We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms.
1 code implementation • ACL 2017 • Chenhao Tan, Dallas Card, Noah A. Smith
Combining two statistics --- cooccurrence within documents and prevalence correlation over time --- our approach reveals a number of different ways in which ideas can cooperate and compete.
3 code implementations • ACL 2018 • Dallas Card, Chenhao Tan, Noah A. Smith
Most real-world document collections involve various types of metadata, such as author, source, and date, and yet the most commonly-used approaches to modeling text corpora ignore this information.
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.
no code implementations • ICLR 2018 • Jesse Dodge, Kevin Jamieson, Noah A. Smith
Driven by the need for parallelizable hyperparameter optimization methods, this paper studies \emph{open loop} search methods: sequences that are predetermined and can be generated before a single configuration is evaluated.
10 code implementations • 29 Jun 2017 • Swabha Swayamdipta, Sam Thomson, Chris Dyer, Noah A. Smith
We present a new, efficient frame-semantic parser that labels semantic arguments to FrameNet predicates.
no code implementations • 1 Aug 2017 • Hao Tang, Liang Lu, Lingpeng Kong, Kevin Gimpel, Karen Livescu, Chris Dyer, Noah A. Smith, Steve Renals
Segmental models are an alternative to frame-based models for sequence prediction, where hypothesized path weights are based on entire segment scores rather than a single frame at a time.
2 code implementations • EMNLP 2017 • Yangfeng Ji, Chenhao Tan, Sebastian Martschat, Yejin Choi, Noah A. Smith
Understanding a long document requires tracking how entities are introduced and evolve over time.
no code implementations • 23 Feb 2018 • Chenhao Tan, Hao Peng, Noah A. Smith
We first examine the effect of wording and propose a binary classification framework that controls for both the speaker and the debate situation.
no code implementations • NAACL 2018 • Suchin Gururangan, Swabha Swayamdipta, Omer Levy, Roy Schwartz, Samuel R. Bowman, Noah A. Smith
Large-scale datasets for natural language inference are created by presenting crowd workers with a sentence (premise), and asking them to generate three new sentences (hypotheses) that it entails, contradicts, or is logically neutral with respect to.
2 code implementations • NAACL 2018 • Hao Peng, Sam Thomson, Swabha Swayamdipta, Noah A. Smith
We present a new approach to learning semantic parsers from multiple datasets, even when the target semantic formalisms are drastically different, and the underlying corpora do not overlap.
1 code implementation • NAACL 2018 • Yijia Liu, Yi Zhu, Wanxiang Che, Bing Qin, Nathan Schneider, Noah A. Smith
Nonetheless, using the new treebank, we build a pipeline system to parse raw tweets into UD.
Ranked #2 on Dependency Parsing on Tweebank
no code implementations • NAACL 2018 • Hao Fang, Hao Cheng, Maarten Sap, Elizabeth Clark, Ari Holtzman, Yejin Choi, Noah A. Smith, Mari Ostendorf
We present Sounding Board, a social chatbot that won the 2017 Amazon Alexa Prize.
1 code implementation • ACL 2018 • Hao Peng, Sam Thomson, Noah A. Smith
We introduce the structured projection of intermediate gradients optimization technique (SPIGOT), a new method for backpropagating through neural networks that include hard-decision structured predictions (e. g., parsing) in intermediate layers.
2 code implementations • 15 May 2018 • Roy Schwartz, Sam Thomson, Noah A. Smith
Recurrent and convolutional neural networks comprise two distinct families of models that have proven to be useful for encoding natural language utterances.
Explainable artificial intelligence General Classification +3
no code implementations • ACL 2018 • Hannah Rashkin, Maarten Sap, Emily Allaway, Noah A. Smith, Yejin Choi
We investigate a new commonsense inference task: given an event described in a short free-form text ("X drinks coffee in the morning"), a system reasons about the likely intents ("X wants to stay awake") and reactions ("X feels alert") of the event's participants.
Ranked #1 on Common Sense Reasoning on Event2Mind test
1 code implementation • HLT 2015 • Fei Liu, Jeffrey Flanigan, Sam Thomson, Norman Sadeh, Noah A. Smith
We present a novel abstractive summarization framework that draws on the recent development of a treebank for the Abstract Meaning Representation (AMR).
no code implementations • WS 2018 • Nelson F. Liu, Omer Levy, Roy Schwartz, Chenhao Tan, Noah A. Smith
While recurrent neural networks have found success in a variety of natural language processing applications, they are general models of sequential data.
no code implementations • WS 2018 • Nelson F. Liu, Gina-Anne Levow, Noah A. Smith
We introduce a simple method for extracting non-arbitrary form-meaning representations from a collection of semantic vectors.
no code implementations • NAACL 2018 • Dallas Card, Noah A. Smith
Estimating label proportions in a target corpus is a type of measurement that is useful for answering certain types of social-scientific questions.
no code implementations • NAACL 2018 • Elizabeth Clark, Yangfeng Ji, Noah A. Smith
We introduce an approach to neural text generation that explicitly represents entities mentioned in the text.
no code implementations • ACL 2018 • Roy Schwartz, Sam Thomson, Noah A. Smith
Recurrent and convolutional neural networks comprise two distinct families of models that have proven to be useful for encoding natural language utterances.
no code implementations • 28 Aug 2018 • Lucy H. Lin, Scott Miles, Noah A. Smith
We consider the case of a domain expert who wishes to explore the extent to which a particular idea is expressed in a text collection.
1 code implementation • EMNLP 2018 • Hao Peng, Roy Schwartz, Sam Thomson, Noah A. Smith
We characterize this connection formally, defining rational recurrences to be recurrent hidden state update functions that can be written as the Forward calculation of a finite set of WFSAs.
1 code implementation • EMNLP 2018 • Jiateng Xie, Zhilin Yang, Graham Neubig, Noah A. Smith, Jaime Carbonell
To improve robustness to word order differences, we propose to use self-attention, which allows for a degree of flexibility with respect to word order.
1 code implementation • EMNLP 2018 • Swabha Swayamdipta, Sam Thomson, Kenton Lee, Luke Zettlemoyer, Chris Dyer, Noah A. Smith
We introduce the syntactic scaffold, an approach to incorporating syntactic information into semantic tasks.
2 code implementations • 31 Oct 2018 • Maarten Sap, Ronan LeBras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A. Smith, Yejin Choi
We present ATOMIC, an atlas of everyday commonsense reasoning, organized through 877k textual descriptions of inferential knowledge.
1 code implementation • 31 Oct 2018 • Ofir Press, Noah A. Smith
In NMT, how far can we get without attention and without separate encoding and decoding?
2 code implementations • 6 Nov 2018 • Dallas Card, Michael Zhang, Noah A. Smith
Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text.
3 code implementations • 15 Feb 2019 • Noah A. Smith
This introduction aims to tell the story of how we put words into computers.
1 code implementation • NAACL 2019 • Phoebe Mulcaire, Jungo Kasai, Noah A. Smith
We introduce Rosita, a method to produce multilingual contextual word representations by training a single language model on text from multiple languages.
no code implementations • TACL 2019 • Kelvin Luu, Chenhao Tan, Noah A. Smith
We build on a widely used model of skill in two-player games and augment it with linguistic features of a debater{'}s content.
no code implementations • WS 2019 • Matthew E. Peters, Sebastian Ruder, Noah A. Smith
While most previous work has focused on different pretraining objectives and architectures for transfer learning, we ask how to best adapt the pretrained model to a given target task.
no code implementations • NAACL 2019 • Nelson F. Liu, Matt Gardner, Yonatan Belinkov, Matthew E. Peters, Noah A. Smith
Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language.
no code implementations • NAACL 2019 • Nelson F. Liu, Roy Schwartz, Noah A. Smith
Several datasets have recently been constructed to expose brittleness in models trained on existing benchmarks.
1 code implementation • ACL 2019 • Gabriel Stanovsky, Noah A. Smith, Luke Zettlemoyer
We present the first challenge set and evaluation protocol for the analysis of gender bias in machine translation (MT).
1 code implementation • ACL 2019 • Suchin Gururangan, Tam Dang, Dallas Card, Noah A. Smith
We accompany this paper with code to pretrain and use VAMPIRE embeddings in downstream tasks.
1 code implementation • ACL 2019 • Sofia Serrano, Noah A. Smith
Attention mechanisms have recently boosted performance on a range of NLP tasks.
no code implementations • ACL 2019 • Maarten Sap, Dallas Card, Saadia Gabriel, Yejin Choi, Noah A. Smith
We investigate how annotators{'} insensitivity to differences in dialect can lead to racial bias in automatic hate speech detection models, potentially amplifying harm against minority populations.
no code implementations • ACL 2019 • Elizabeth Clark, Asli Celikyilmaz, Noah A. Smith
For evaluating machine-generated texts, automatic methods hold the promise of avoiding collection of human judgments, which can be expensive and time-consuming.
2 code implementations • 22 Jul 2019 • Roy Schwartz, Jesse Dodge, Noah A. Smith, Oren Etzioni
Moreover, the financial cost of the computations can make it difficult for academics, students, and researchers, in particular those from emerging economies, to engage in deep learning research.
1 code implementation • IJCNLP 2019 • Pradeep Dasigi, Nelson F. Liu, Ana Marasović, Noah A. Smith, Matt Gardner
Machine comprehension of texts longer than a single sentence often requires coreference resolution.
no code implementations • 29 Aug 2019 • Swabha Swayamdipta, Matthew Peters, Brendan Roof, Chris Dyer, Noah A. Smith
Shallow syntax provides an approximation of phrase-syntactic structure of sentences; it can be produced with high accuracy, and is computationally cheap to obtain.
1 code implementation • IJCNLP 2019 • Sachin Kumar, Shuly Wintner, Noah A. Smith, Yulia Tsvetkov
Despite impressive performance on many text classification tasks, deep neural networks tend to learn frequent superficial patterns that are specific to the training data and do not always generalize well.
1 code implementation • IJCNLP 2019 • Hao Peng, Roy Schwartz, Noah A. Smith
We present PaLM, a hybrid parser and neural language model.
1 code implementation • IJCNLP 2019 • Jesse Dodge, Roy Schwartz, Hao Peng, Noah A. Smith
Our method also highlights the interpretable properties of rational RNNs.
4 code implementations • IJCNLP 2019 • Jesse Dodge, Suchin Gururangan, Dallas Card, Roy Schwartz, Noah A. Smith
Research in natural language processing proceeds, in part, by demonstrating that new models achieve superior performance (e. g., accuracy) on held-out test data, compared to previous results.
1 code implementation • IJCNLP 2019 • Matthew E. Peters, Mark Neumann, Robert L. Logan IV, Roy Schwartz, Vidur Joshi, Sameer Singh, Noah A. Smith
Contextual word representations, typically trained on unstructured, unlabeled text, do not contain any explicit grounding to real world entities and are often unable to remember facts about those entities.
Ranked #9 on Relation Classification on TACRED
1 code implementation • 18 Sep 2019 • Deric Pang, Lucy H. Lin, Noah A. Smith
We introduce a novel approach to incorporate syntax into natural language inference (NLI) models.
no code implementations • CONLL 2019 • Phoebe Mulcaire, Jungo Kasai, Noah A. Smith
Despite advances in dependency parsing, languages with small treebanks still present challenges.
no code implementations • ICLR 2020 • Lucy H. Lin, Noah A. Smith
As distributed approaches to natural language semantics have developed and diversified, embedders for linguistic units larger than words have come to play an increasingly important role.
no code implementations • ACL 2020 • Maarten Sap, Saadia Gabriel, Lianhui Qin, Dan Jurafsky, Noah A. Smith, Yejin Choi
We introduce Social Bias Frames, a new conceptual formalism that aims to model the pragmatic frames in which people project social biases and stereotypes onto others.
2 code implementations • ACL 2020 • Ofir Press, Noah A. Smith, Omer Levy
Multilayer transformer networks consist of interleaved self-attention and feedforward sublayers.
Ranked #7 on Language Modelling on enwik8
no code implementations • 2 Jan 2020 • Dallas Card, Noah A. Smith
In this paper we provide a consequentialist critique of common definitions of fairness within machine learning, as well as a machine learning perspective on consequentialism.
1 code implementation • ACL 2021 • Kelvin Luu, Xinyi Wu, Rik Koncel-Kedziorski, Kyle Lo, Isabel Cachola, Noah A. Smith
We address the task of explaining relationships between two scientific documents using natural language text.
no code implementations • 2 Mar 2020 • Qiaolin Xia, Xiujun Li, Chunyuan Li, Yonatan Bisk, Zhifang Sui, Jianfeng Gao, Yejin Choi, Noah A. Smith
Learning to navigate in a visual environment following natural language instructions is a challenging task because natural language instructions are highly variable, ambiguous, and under-specified.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Matt Gardner, Yoav Artzi, Victoria Basmova, Jonathan Berant, Ben Bogin, Sihao Chen, Pradeep Dasigi, Dheeru Dua, Yanai Elazar, Ananth Gottumukkala, Nitish Gupta, Hanna Hajishirzi, Gabriel Ilharco, Daniel Khashabi, Kevin Lin, Jiangming Liu, Nelson F. Liu, Phoebe Mulcaire, Qiang Ning, Sameer Singh, Noah A. Smith, Sanjay Subramanian, Reut Tsarfaty, Eric Wallace, Ally Zhang, Ben Zhou
Unfortunately, when a dataset has systematic gaps (e. g., annotation artifacts), these evaluations are misleading: a model can learn simple decision rules that perform well on the test set but do not capture a dataset's intended capabilities.
1 code implementation • ACL 2020 • Roy Schwartz, Gabriel Stanovsky, Swabha Swayamdipta, Jesse Dodge, Noah A. Smith
Our method presents a favorable speed/accuracy tradeoff in almost all cases, producing models which are up to five times faster than the state of the art, while preserving their accuracy.
no code implementations • ACL 2020 • William Merrill, Gail Weiss, Yoav Goldberg, Roy Schwartz, Noah A. Smith, Eran Yahav
While formally extending these findings to unsaturated RNNs is left to future work, we hypothesize that the practical learnable capacity of unsaturated RNNs obeys a similar hierarchy.
6 code implementations • ACL 2020 • Suchin Gururangan, Ana Marasović, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, Noah A. Smith
Language models pretrained on text from a wide variety of sources form the foundation of today's NLP.
no code implementations • 13 May 2020 • Hao Peng, Roy Schwartz, Dianqi Li, Noah A. Smith
Multi-head attentive neural architectures have achieved state-of-the-art results on a variety of natural language processing tasks.
no code implementations • CL 2020 • Marta R. Costa-juss{\`a}, Cristina Espa{\~n}a-Bonet, Pascale Fung, Noah A. Smith
We introduce the Computational Linguistics special issue on Multilingual and Interlingual Semantic Representations for Natural Language Processing.
2 code implementations • ICLR 2021 • Jungo Kasai, Nikolaos Pappas, Hao Peng, James Cross, Noah A. Smith
We show that the speed disadvantage for autoregressive baselines compared to non-autoregressive methods has been overestimated in three aspects: suboptimal layer allocation, insufficient speed measurement, and lack of knowledge distillation.
no code implementations • WS 2020 • Tal August, Maarten Sap, Elizabeth Clark, Katharina Reinecke, Noah A. Smith
We analyze the effect of author and reader characteristics and story writing setup on the quality of stories in a short storytelling task.
no code implementations • ACL 2020 • Hao Peng, Roy Schwartz, Dianqi Li, Noah A. Smith
Multi-head attentive neural architectures have achieved state-of-the-art results on a variety of natural language processing tasks.
no code implementations • ACL 2020 • Maarten Sap, Eric Horvitz, Yejin Choi, Noah A. Smith, James Pennebaker
We introduce a measure of narrative flow and use this to examine the narratives for imagined and recalled events.
6 code implementations • EMNLP 2020 • Swabha Swayamdipta, Roy Schwartz, Nicholas Lourie, Yizhong Wang, Hannaneh Hajishirzi, Noah A. Smith, Yejin Choi
Experiments across four datasets show that these model-dependent measures reveal three distinct regions in the data map, each with pronounced characteristics.
1 code implementation • EMNLP 2020 • Nikolaos Pappas, Phoebe Mulcaire, Noah A. Smith
To our knowledge, the result is the first word-level language model with a size that does not depend on the training vocabulary.
2 code implementations • Findings of the Association for Computational Linguistics 2020 • Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, Noah A. Smith
We investigate the extent to which pretrained LMs can be prompted to generate toxic language, and the effectiveness of controllable text generation algorithms at preventing such toxic degeneration.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Ethan C. Chau, Lucy H. Lin, Noah A. Smith
Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties.
no code implementations • 1 Oct 2020 • Matt Gardner, Yoav Artzi, Victoria Basmova, Jonathan Berant, Ben Bogin, Sihao Chen, Pradeep Dasigi, Dheeru Dua, Yanai Elazar, Ananth Gottumukkala, Nitish Gupta, Hanna Hajishirzi, Gabriel Ilharco, Daniel Khashabi, Kevin Lin, Jiangming Liu, Nelson F. Liu, Phoebe Mulcaire, Qiang Ning, Sameer Singh, Noah A. Smith, Sanjay Subramanian, Reut Tsarfaty, Eric Wallace, A. Zhang, Ben Zhou
Unfortunately, when a dataset has systematic gaps (e. g., annotation artifacts), these evaluations are misleading: a model can learn simple decision rules that perform well on the test set but do not capture a dataset's intended capabilities.
1 code implementation • EMNLP 2020 • Xuhui Zhou, Nikolaos Pappas, Noah A. Smith
Text alignment finds application in tasks such as citation recommendation and plagiarism detection.
1 code implementation • EMNLP 2020 • Florian Mai, Nikolaos Pappas, Ivan Montero, Noah A. Smith, James Henderson
Text autoencoders are commonly used for conditional generation tasks such as style transfer.
1 code implementation • EMNLP 2020 • Phillip Keung, Yichao Lu, György Szarvas, Noah A. Smith
We present the Multilingual Amazon Reviews Corpus (MARC), a large-scale collection of Amazon reviews for multilingual text classification.
no code implementations • 15 Oct 2020 • Phillip Keung, Julian Salazar, Yichao Lu, Noah A. Smith
We then improve an XLM-based unsupervised neural MT system pre-trained on Wikipedia by supplementing it with pseudo-parallel text mined from the same corpus, boosting unsupervised translation performance by up to 3. 5 BLEU on the WMT'14 French-English and WMT'16 German-English tasks and outperforming the previous state-of-the-art.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Ana Marasović, Chandra Bhagavatula, Jae Sung Park, Ronan Le Bras, Noah A. Smith, Yejin Choi
Natural language rationales could provide intuitive, higher-level explanations that are easily understandable by humans, complementing the more broadly studied lower-level explanations based on gradients or attention weights.
1 code implementation • EMNLP 2021 • Sarah Wiegreffe, Ana Marasović, Noah A. Smith
In interpretable NLP, we require faithful rationales that reflect the model's decision-making process for an explained instance.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Rachel Rudinger, Vered Shwartz, Jena D. Hwang, Chandra Bhagavatula, Maxwell Forbes, Ronan Le Bras, Noah A. Smith, Yejin Choi
Defeasible inference is a mode of reasoning in which an inference (X is a bird, therefore X flies) may be weakened or overturned in light of new evidence (X is a penguin).
1 code implementation • 10 Dec 2020 • Zhaofeng Wu, Hao Peng, Noah A. Smith
For natural language processing systems, two kinds of evidence support the use of text representations from neural language models "pretrained" on large unannotated corpora: performance on application-inspired benchmarks (Peters et al., 2018, inter alia), and the emergence of syntactic abstractions in those representations (Tenney et al., 2019, inter alia).
1 code implementation • ACL 2021 • Ofir Press, Noah A. Smith, Mike Lewis
Increasing the input length has been a driver of progress in language modeling with transformers.
Ranked #26 on Language Modelling on WikiText-103
2 code implementations • 17 Jan 2021 • Daniel Khashabi, Gabriel Stanovsky, Jonathan Bragg, Nicholas Lourie, Jungo Kasai, Yejin Choi, Noah A. Smith, Daniel S. Weld
While often assumed a gold standard, effective human evaluation of text generation remains an important, open area for research.
2 code implementations • EACL 2021 • Xuhui Zhou, Maarten Sap, Swabha Swayamdipta, Noah A. Smith, Yejin Choi
Overall, our findings show that debiasing a model trained on biased toxic language data is not as effective as simply relabeling the data to remove existing biases.
no code implementations • ICLR 2021 • Hao Peng, Nikolaos Pappas, Dani Yogatama, Roy Schwartz, Noah A. Smith, Lingpeng Kong
RFA can be used as a drop-in replacement for conventional softmax attention and offers a straightforward way of learning with recency bias through an optional gating mechanism.
Ranked #27 on Machine Translation on IWSLT2014 German-English
1 code implementation • EMNLP 2021 • Jungo Kasai, Hao Peng, Yizhe Zhang, Dani Yogatama, Gabriel Ilharco, Nikolaos Pappas, Yi Mao, Weizhu Chen, Noah A. Smith
Specifically, we propose a swap-then-finetune procedure: in an off-the-shelf pretrained transformer, we replace the softmax attention with its linear-complexity recurrent alternative and then finetune.
Ranked #2 on Machine Translation on WMT2017 Chinese-English
1 code implementation • Findings (EMNLP) 2021 • Leo Z. Liu, Yizhong Wang, Jungo Kasai, Hannaneh Hajishirzi, Noah A. Smith
Models of language trained on very large corpora have been demonstrated useful for NLP.
no code implementations • EMNLP 2021 • Matt Gardner, William Merrill, Jesse Dodge, Matthew E. Peters, Alexis Ross, Sameer Singh, Noah A. Smith
In this work we argue that for complex language understanding tasks, all simple feature correlations are spurious, and we formalize this notion into a class of problems which we call competency problems.
1 code implementation • 18 Apr 2021 • Rik Koncel-Kedziorski, Noah A. Smith
This method can improve perplexity of pretrained LMs with no updates to the LM's own parameters.
no code implementations • 22 Apr 2021 • William Merrill, Yoav Goldberg, Roy Schwartz, Noah A. Smith
We study whether assertions enable a system to emulate representations preserving semantic relations like equivalence.
1 code implementation • ACL 2021 • Alisa Liu, Maarten Sap, Ximing Lu, Swabha Swayamdipta, Chandra Bhagavatula, Noah A. Smith, Yejin Choi
Despite recent advances in natural language generation, it remains challenging to control attributes of generated text.
1 code implementation • NAACL 2021 • Pradeep Dasigi, Kyle Lo, Iz Beltagy, Arman Cohan, Noah A. Smith, Matt Gardner
Readers of academic research papers often read with the goal of answering specific questions.
Ranked #1 on Evidence Selection on QASPER
no code implementations • NAACL 2021 • Elizabeth Clark, Noah A. Smith
Story generation is an open-ended and subjective task, which poses a challenge for evaluating story generation models.
1 code implementation • EMNLP (MRL) 2021 • Ethan C. Chau, Noah A. Smith
Pretrained multilingual language models have become a common tool in transferring NLP capabilities to low-resource languages, often with adaptations.
1 code implementation • AKBC 2021 • Rahul Nadkarni, David Wadden, Iz Beltagy, Noah A. Smith, Hannaneh Hajishirzi, Tom Hope
Biomedical knowledge graphs (KGs) hold rich information on entities such as diseases, drugs, and genes.
no code implementations • 30 Jun 2021 • William Merrill, Ashish Sabharwal, Noah A. Smith
Transformers have become a standard neural network architecture for many NLP problems, motivating theoretical analysis of their power in terms of formal languages.
no code implementations • 30 Jun 2021 • Elizabeth Clark, Tal August, Sofia Serrano, Nikita Haduong, Suchin Gururangan, Noah A. Smith
Human evaluations are typically considered the gold standard in natural language generation, but as models' fluency improves, how well can evaluators detect and judge machine-generated text?
no code implementations • ACL 2022 • Yao Dou, Maxwell Forbes, Rik Koncel-Kedziorski, Noah A. Smith, Yejin Choi
To support the broad range of real machine errors that can be identified by laypeople, the ten error categories of Scarecrow -- such as redundancy, commonsense errors, and incoherence -- are identified through several rounds of crowd annotation experiments without a predefined ontology.
no code implementations • ACL 2021 • Elizabeth Clark, Tal August, Sofia Serrano, Nikita Haduong, Suchin Gururangan, Noah A. Smith
Human evaluations are typically considered the gold standard in natural language generation, but as models{'} fluency improves, how well can evaluators detect and judge machine-generated text?
2 code implementations • NAACL 2022 • Suchin Gururangan, Mike Lewis, Ari Holtzman, Noah A. Smith, Luke Zettlemoyer
We introduce a new domain expert mixture (DEMix) layer that enables conditioning a language model (LM) on the domain of the input text.
7 code implementations • ICLR 2022 • Ofir Press, Noah A. Smith, Mike Lewis
Since the introduction of the transformer model by Vaswani et al. (2017), a fundamental question has yet to be answered: how does a model achieve extrapolation at inference time for sequences that are longer than it saw during training?
1 code implementation • EMNLP 2021 • Ivan Montero, Nikolaos Pappas, Noah A. Smith
Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems.
no code implementations • 1 Oct 2021 • Jesse Dodge, Suchin Gururangan, Dallas Card, Roy Schwartz, Noah A. Smith
We find that the two biased estimators lead to the fewest incorrect conclusions, which hints at the importance of minimizing variance and MSE.
no code implementations • ACL 2022 • Hao Peng, Jungo Kasai, Nikolaos Pappas, Dani Yogatama, Zhaofeng Wu, Lingpeng Kong, Roy Schwartz, Noah A. Smith
One way to improve the efficiency is to bound the memory size.
1 code implementation • NAACL 2022 • Kelvin Luu, Daniel Khashabi, Suchin Gururangan, Karishma Mandyam, Noah A. Smith
When an NLP model is trained on text data from one time period and tested or deployed on data from another, the resulting temporal misalignment can degrade end-task performance.
no code implementations • NAACL 2022 • Maarten Sap, Swabha Swayamdipta, Laura Vianna, Xuhui Zhou, Yejin Choi, Noah A. Smith
The perceived toxicity of language can vary based on someone's identity and beliefs, but this variation is often ignored when collecting toxic language datasets, resulting in dataset and model biases.
2 code implementations • NAACL 2022 • Jungo Kasai, Keisuke Sakaguchi, Lavinia Dunagan, Jacob Morrison, Ronan Le Bras, Yejin Choi, Noah A. Smith
We establish THumB, a rubric-based human evaluation protocol for image captioning models.
2 code implementations • NAACL 2022 • Jungo Kasai, Keisuke Sakaguchi, Ronan Le Bras, Lavinia Dunagan, Jacob Morrison, Alexander R. Fabbri, Yejin Choi, Noah A. Smith
We therefore propose a generalization of leaderboards, bidimensional leaderboards (Billboards), that simultaneously tracks progress in language generation models and metrics for their evaluation.
1 code implementation • NAACL 2022 • Ximing Lu, Sean Welleck, Peter West, Liwei Jiang, Jungo Kasai, Daniel Khashabi, Ronan Le Bras, Lianhui Qin, Youngjae Yu, Rowan Zellers, Noah A. Smith, Yejin Choi
To enable constrained generation, we build on NeuroLogic decoding (Lu et al., 2021), combining its flexibility in incorporating logical constraints with A*esque estimates of future constraint satisfaction.
Ranked #1 on Text Generation on ROCStories
no code implementations • 7 Jan 2022 • Maarten Sap, Anna Jafarpour, Yejin Choi, Noah A. Smith, James W. Pennebaker, Eric Horvitz
We quantify the differences between autobiographical and imagined stories by introducing sequentiality, a measure of narrative flow of events, drawing probabilistic inferences from a cutting-edge large language model (GPT-3).
1 code implementation • 16 Jan 2022 • Alisa Liu, Swabha Swayamdipta, Noah A. Smith, Yejin Choi
Starting with an existing dataset, MultiNLI for natural language inference (NLI), our approach uses dataset cartography to automatically identify examples that demonstrate challenging reasoning patterns, and instructs GPT-3 to compose new examples with similar patterns.
1 code implementation • 16 Jan 2022 • Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu
Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering over knowledge bases.
Ranked #1 on Task-Oriented Dialogue Systems on KVRET
no code implementations • 25 Jan 2022 • Suchin Gururangan, Dallas Card, Sarah K. Dreier, Emily K. Gade, Leroy Z. Wang, Zeyu Wang, Luke Zettlemoyer, Noah A. Smith
Language models increasingly rely on massive web dumps for diverse text data.
1 code implementation • 16 Mar 2022 • Yushi Hu, Chia-Hsuan Lee, Tianbao Xie, Tao Yu, Noah A. Smith, Mari Ostendorf
In this work, we propose an in-context learning (ICL) framework for zero-shot and few-shot learning DST, where a large pre-trained language model (LM) takes a test instance and a few exemplars as input, and directly decodes the dialogue state without any parameter updates.
1 code implementation • 11 Apr 2022 • Jungo Kasai, Keisuke Sakaguchi, Ronan Le Bras, Dragomir Radev, Yejin Choi, Noah A. Smith
Based on this finding, we introduce a patience factor, a simple modification to this beam decoding implementation, that generalizes the stopping criterion and provides flexibility to the depth of search.
7 code implementations • 16 Apr 2022 • Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, Arut Selvan Dhanasekaran, Atharva Naik, David Stap, Eshaan Pathak, Giannis Karamanolakis, Haizhi Gary Lai, Ishan Purohit, Ishani Mondal, Jacob Anderson, Kirby Kuznia, Krima Doshi, Maitreya Patel, Kuntal Kumar Pal, Mehrad Moradshahi, Mihir Parmar, Mirali Purohit, Neeraj Varshney, Phani Rohitha Kaza, Pulkit Verma, Ravsehaj Singh Puri, Rushang Karia, Shailaja Keyur Sampat, Savan Doshi, Siddhartha Mishra, Sujan Reddy, Sumanta Patro, Tanay Dixit, Xudong Shen, Chitta Baral, Yejin Choi, Noah A. Smith, Hannaneh Hajishirzi, Daniel Khashabi
This large and diverse collection of tasks enables rigorous benchmarking of cross-task generalization under instructions -- training models to follow instructions on a subset of tasks and evaluating them on the remaining unseen ones.