BERT-based architectures currently give stateof-the-art performance on many NLP tasks, but little is known about the exact mechanisms that contribute to its success. In the current work, we focus on the interpretation of selfattention, which is one of the fundamental underlying components of BERT. Using a subset of GLUE tasks and a set of handcrafted features-of-interest, we propose the methodology and carry out a qualitative and quantitative analysis of the information encoded by the individual BERT's heads. Our findings suggest that there is a limited set of attention patterns that are repeated across different heads, indicating the overall model overparametrization. While different heads consistently use the same attention patterns, they have varying impact on performance across different tasks. We show that manually disabling attention in certain heads leads to a performance improvement over the regular fine-tuned BERT models.

State of the art models using deep neural networks have become very good in learning an accurate mapping from inputs to outputs. However, they still lack generalization capabilities in conditions that differ from the ones encountered during training. This is even more challenging in specialized, and knowledge intensive domains, where training data is limited. To address this gap, we introduce MedNLI 1 -a dataset annotated by doctors, performing a natural language inference task (NLI), grounded in the medical history of patients. We present strategies to: 1) leverage transfer learning using datasets from the open domain, (e.g. SNLI) and 2) incorporate domain knowledge from external data and lexical sources (e.g. medical terminologies). Our results demonstrate performance gains using both strategies. * Work done during an internship at IBM Research

This paper describes a new shared task for humor understanding that attempts to eschew the ubiquitous binary approach to humor detection and focus on comparative humor ranking instead. The task is based on a new dataset of funny tweets posted in response to shared hashtags, collected from the 'Hashtag Wars' segment of the TV show @midnight. The results are evaluated in two subtasks that require the participants to generate either the correct pairwise comparisons of tweets (subtask A), or the correct ranking of the tweets (subtask B) in terms of how funny they are. 7 teams participated in subtask A, and 5 teams participated in subtask B. The best accuracy in subtask A was 0.675. The best (lowest) rank edit distance for subtask B was 0.872.

This paper demonstrates the effectiveness of a Long Short-Term Memory language model in our initial efforts to generate unconstrained rap lyrics. The goal of this model is to generate lyrics that are similar in style to that of a given rapper, but not identical to existing lyrics: this is the task of ghostwriting. Unlike previous work, which defines explicit templates for lyric generation, our model defines its own rhyme scheme, line length, and verse length. Our experiments show that a Long Short-Term Memory language model produces better "ghostwritten" lyrics than a baseline model.

In order to determine argument structure in text, one must understand how individual components of the overall argument are linked. This work presents the first neural network-based approach to link extraction in argument mining. Specifically, we propose a novel architecture that applies Pointer Network sequence-tosequence attention modeling to structural prediction in discourse parsing tasks. We then develop a joint model that extends this architecture to simultaneously address the link extraction task and the classification of argument components. The proposed joint model achieves state-of-the-art results on two separate evaluation corpora, showing far superior performance than the previously proposed corpus-specific and heavily feature-engineered models. Furthermore, our results demonstrate that jointly optimizing for both tasks is crucial for high performance.