5.2k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- SupélecFR485 papers
- University of Applied Sciences and Arts of Southern SwitzerlandCH485 papers
- New York UniversityUS52 papers
- Google (United States)US16 papers
- Princeton UniversityUS15 papers
- Courant Institute of Mathematical SciencesUS13 papers
- Meta (Israel)IL11 papers
- Massachusetts Institute of TechnologyUS10 papers
- Stanford UniversityUS8 papers
- University of California, BerkeleyUS8 papers
- Cornell UniversityUS7 papers
- Carnegie Mellon UniversityUS6 papers
18 papers · 2 filters
When Do You Need Billions of Words of Pretraining Data?
Yian Zhang, Alex Warstadt, Haau-Sing Li +1
NLP is currently dominated by general-purpose pretrained language models like RoBERTa, which achieve strong performance on NLU tasks through pretraining on billions of words. But w…
NADI 2020: The First Nuanced Arabic Dialect Identification Shared Task
Muhammad Abdul-Mageed, Chiyu Zhang, Houda Bouamor +1
We present the results and findings of the First Nuanced Arabic Dialect Identification Shared Task (NADI). This Shared Task includes two subtasks: country-level dialect identificat…
Meta-Learning for Natural Language Understanding under Continual Learning Framework
Jiacheng Wang, Yong Fan, Duo Jiang +1
Neural network has been recognized with its accomplishments on tackling various natural language understanding (NLU) tasks. Methods have been developed to train a robust model to h…
Rethinking embedding coupling in pre-trained language models
Hyung Won Chung, Thibault Févry, Henry Tsai +2
We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provi…
An Evaluation Protocol for Generative Conversational Systems
Seolhwa Lee, Heuiseok Lim, João Sedoc
There is a multitude of novel generative models for open-domain conversational systems; however, there is no systematic evaluation of different systems. Systematic comparisons requ…
Six Attributes of Unhealthy Conversation
Ilan Price, Jordan Gifford-Moore, Jory Fleming +6
We present a new dataset of approximately 44000 comments labeled by crowdworkers. Each comment is labelled as either 'healthy' or 'unhealthy', in addition to binary labels for the…
Latent Tree Learning with Ordered Neurons: What Parses Does It Produce?
Yian Zhang
Recent latent tree learning models can learn constituency parsing without any exposure to human-annotated tree structures. One such model is ON-LSTM (Shen et al., 2019), which is t…
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data
William Huang, Haokun Liu, Samuel R. Bowman
A growing body of work shows that models exploit annotation artifacts to achieve state-of-the-art performance on standard crowdsourced benchmarks---datasets collected from crowdwor…
Precise Task Formalization Matters in Winograd Schema Evaluations
Haokun Liu, William Huang, Dhara A. Mungra +1
Performance on the Winograd Schema Challenge (WSC), a respected English commonsense reasoning benchmark, recently rocketed from chance accuracy to 89% on the SuperGLUE leaderboard,…
Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule
Shuhei Kurita, Kyunghyun Cho
Vision-and-language navigation (VLN) is a task in which an agent is embodied in a realistic 3D environment and follows an instruction to reach the goal node. While most of the prev…
Text Generation by Learning from Demonstrations
Richard Yuanzhe Pang, He He
Current approaches to text generation largely rely on autoregressive models and maximum likelihood estimation. This paradigm leads to (i) diverse but low-quality samples due to mis…
An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models
Lifu Tu, Garima Lalwani, Spandana Gella +1
Recent work has shown that pre-trained language models such as BERT improve robustness to spurious correlations in the dataset. Intrigued by these results, we find that the key to…
The test set for the TransCoder system
Ernest Davis
The TransCoder system translates source code between Java, C++, and Python 3. The test set that was used to evaluate its quality is missing important features of Java, including th…
Can neural networks acquire a structural bias from raw linguistic data?
Alex Warstadt, Samuel R. Bowman
We evaluate whether BERT, a widely used neural network for sentence processing, acquires an inductive bias towards forming structural generalizations through pretraining on raw dat…
ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
Lifu Tu, Richard Yuanzhe Pang, Sam Wiseman +1
We propose to train a non-autoregressive machine translation model to minimize the energy defined by a pretrained autoregressive model. In particular, we view our non-autoregressiv…
Weakly Supervised POS Taggers Perform Poorly on Truly Low-Resource Languages
Katharina Kann, Ophélie Lacroix, Anders Søgaard
Part-of-speech (POS) taggers for low-resource languages which are exclusively based on various forms of weak supervision - e.g., cross-lingual transfer, type-level supervision, or…
Learning to Learn Morphological Inflection for Resource-Poor Languages
Katharina Kann, Samuel R. Bowman, Kyunghyun Cho
We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem. Treating each lan…
Asking and Answering Questions to Evaluate the Factual Consistency of Summaries
Alex Wang, Kyunghyun Cho, Mike Lewis
Practical applications of abstractive summarization models are limited by frequent factual inconsistencies with respect to their input. Existing automatic evaluation metrics for su…