Kevin Clark


pdf bib
Meta-Learning Fast Weight Language Models
Kevin Clark | Kelvin Guu | Ming-Wei Chang | Panupong Pasupat | Geoffrey Hinton | Mohammad Norouzi
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Dynamic evaluation of language models (LMs) adapts model parameters at test time using gradient information from previous tokens and substantially improves LM performance. However, it requires over 3x more compute than standard inference. We present Fast Weight Layers (FWLs), a neural component that provides the benefits of dynamic evaluation much more efficiently by expressing gradient updates as linear attention. A key improvement over dynamic evaluation is that FWLs can also be applied at training time, so the model learns to make good use of gradient updates. FWLs can easily be added on top of existing transformer models, require relatively little extra compute or memory to run, and significantly improve language modeling perplexity.


pdf bib
Pre-Training Transformers as Energy-Based Cloze Models
Kevin Clark | Minh-Thang Luong | Quoc Le | Christopher D. Manning
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

We introduce Electric, an energy-based cloze model for representation learning over text. Like BERT, it is a conditional generative model of tokens given their contexts. However, Electric does not use masking or output a full distribution over tokens that could occur in a context. Instead, it assigns a scalar energy score to each input token indicating how likely it is given its context. We train Electric using an algorithm based on noise-contrastive estimation and elucidate how this learning objective is closely related to the recently proposed ELECTRA pre-training method. Electric performs well when transferred to downstream tasks and is particularly effective at producing likelihood scores for text: it re-ranks speech recognition n-best lists better than language models and much faster than masked language models. Furthermore, it offers a clearer and more principled view of what ELECTRA learns during pre-training.


pdf bib
What Does BERT Look at? An Analysis of BERT’s Attention
Kevin Clark | Urvashi Khandelwal | Omer Levy | Christopher D. Manning
Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

Large pre-trained neural networks such as BERT have had great recent success in NLP, motivating a growing body of research investigating what aspects of language they are able to learn from unlabeled data. Most recent analysis has focused on model outputs (e.g., language model surprisal) or internal vector representations (e.g., probing classifiers). Complementary to these works, we propose methods for analyzing the attention mechanisms of pre-trained models and apply them to BERT. BERT’s attention heads exhibit patterns such as attending to delimiter tokens, specific positional offsets, or broadly attending over the whole sentence, with heads in the same layer often exhibiting similar behaviors. We further show that certain attention heads correspond well to linguistic notions of syntax and coreference. For example, we find heads that attend to the direct objects of verbs, determiners of nouns, objects of prepositions, and coreferent mentions with remarkably high accuracy. Lastly, we propose an attention-based probing classifier and use it to further demonstrate that substantial syntactic information is captured in BERT’s attention.

pdf bib
BAM! Born-Again Multi-Task Networks for Natural Language Understanding
Kevin Clark | Minh-Thang Luong | Urvashi Khandelwal | Christopher D. Manning | Quoc V. Le
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

It can be challenging to train multi-task neural networks that outperform or even match their single-task counterparts. To help address this, we propose using knowledge distillation where single-task models teach a multi-task model. We enhance this training with teacher annealing, a novel method that gradually transitions the model from distillation to supervised learning, helping the multi-task model surpass its single-task teachers. We evaluate our approach by multi-task fine-tuning BERT on the GLUE benchmark. Our method consistently improves over standard single-task and multi-task training.


pdf bib
Semi-Supervised Sequence Modeling with Cross-View Training
Kevin Clark | Minh-Thang Luong | Christopher D. Manning | Quoc Le
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Unsupervised representation learning algorithms such as word2vec and ELMo improve the accuracy of many supervised NLP models, mainly because they can take advantage of large amounts of unlabeled text. However, the supervised models only learn from task-specific labeled data during the main training phase. We therefore propose Cross-View Training (CVT), a semi-supervised learning algorithm that improves the representations of a Bi-LSTM sentence encoder using a mix of labeled and unlabeled data. On labeled examples, standard supervised learning is used. On unlabeled examples, CVT teaches auxiliary prediction modules that see restricted views of the input (e.g., only part of a sentence) to match the predictions of the full model seeing the whole input. Since the auxiliary modules and the full model share intermediate representations, this in turn improves the full model. Moreover, we show that CVT is particularly effective when combined with multi-task learning. We evaluate CVT on five sequence tagging tasks, machine translation, and dependency parsing, achieving state-of-the-art results.


pdf bib
Large-scale Analysis of Counseling Conversations: An Application of Natural Language Processing to Mental Health
Tim Althoff | Kevin Clark | Jure Leskovec
Transactions of the Association for Computational Linguistics, Volume 4

Mental illness is one of the most pressing public health issues of our time. While counseling and psychotherapy can be effective treatments, our knowledge about how to conduct successful counseling conversations has been limited due to lack of large-scale data with labeled outcomes of the conversations. In this paper, we present a large-scale, quantitative study on the discourse of text-message-based counseling conversations. We develop a set of novel computational discourse analysis methods to measure how various linguistic aspects of conversations are correlated with conversation outcomes. Applying techniques such as sequence-based conversation models, language model comparisons, message clustering, and psycholinguistics-inspired word frequency analyses, we discover actionable conversation strategies that are associated with better conversation outcomes.

pdf bib
Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora
William L. Hamilton | Kevin Clark | Jure Leskovec | Dan Jurafsky
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Deep Reinforcement Learning for Mention-Ranking Coreference Models
Kevin Clark | Christopher D. Manning
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Improving Coreference Resolution by Learning Entity-Level Distributed Representations
Kevin Clark | Christopher D. Manning
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)


pdf bib
Entity-Centric Coreference Resolution with Model Stacking
Kevin Clark | Christopher D. Manning
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)