Clinical notes are text documents that are created by clinicians for each patient encounter. They are typically accompanied by medical codes, which describe the diagnosis and treatment. Annotating these codes is labor intensive and error prone; furthermore, the connection between the codes and the text is not annotated, obscuring the reasons and details behind specific diagnoses and treatments. We present an attentional convolutional network that predicts medical codes from clinical text. Our method aggregates information across the document using a convolutional neural network, and uses an attention mechanism to select the most relevant segments for each of the thousands of possible codes. The method is accurate, achieving precision@8 of 0.71 and a Micro-F1 of 0.54, which are both better than the prior state of the art. Furthermore, through an interpretability evaluation by a physician, we show that the attention mechanism identifies meaningful explanations for each code assignment.

The public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggesstions for reducing this burden, to Washington Headquarters Services, Directorate for Information Operations and Reports,

We present a study of the relationship between gender, linguistic style, and social networks, using a novel corpus of 14,000 Twitter users. Prior quantitative work on gender often treats this social variable as a female/male binary; we argue for a more nuanced approach. By clustering Twitter users, we find a natural decomposition of the dataset into various styles and topical interests. Many clusters have strong gender orientations, but their use of linguistic resources sometimes directly conflicts with the population-level language statistics. We view these clusters as a more accurate reflection of the multifaceted nature of gendered language styles. Previous corpus-based work has also had little to say about individuals whose linguistic styles defy population-level gender patterns. To identify such individuals, we train a statistical classifier, and measure the classifier confidence for each individual in the dataset. Examining individuals whose language does not match the classifier's model for their gender, we find that they have social networks that include significantly fewer same-gender social connections and that, in general, social network homophily is correlated with the use of same-gender language markers. Pairing computational methods and social theory thus offers a new perspective on how gender emerges as individuals position themselves relative to audiences, topics, and mainstream gender norms.Comment: submission versio

Text-level discourse parsing is notoriously difficult, as distinctions between discourse relations require subtle semantic judgments that are not easily captured using standard features. In this paper, we present a representation learning approach, in which we transform surface features into a latent space that facilitates RST discourse parsing. By combining the machinery of large-margin transition-based structured prediction with representation learning, our method jointly learns to parse discourse while at the same time learning a discourse-driven projection of surface features. The resulting shift-reduce discourse parser obtains substantial improvements over the previous state-of-the-art in predicting relations and nuclearity on the RST Treebank.

This paper describes a novel Bayesian approach to unsupervised topic segmentation. Unsupervised systems for this task are driven by lexical cohesion: the tendency of wellformed segments to induce a compact and consistent lexical distribution. We show that lexical cohesion can be placed in a Bayesian context by modeling the words in each topic segment as draws from a multinomial language model associated with the segment; maximizing the observation likelihood in such a model yields a lexically-cohesive segmentation. This contrasts with previous approaches, which relied on hand-crafted cohesion metrics. The Bayesian framework provides a principled way to incorporate additional features such as cue phrases, a powerful indicator of discourse structure that has not been previously used in unsupervised segmentation systems. Our model yields consistent improvements over an array of state-of-the-art systems on both text and speech datasets. We also show that both an entropy-based analysis and a well-known previous technique can be derived as special cases of the Bayesian framework. 1

Computer-mediated communication is driving fundamental changes in the nature of written language. We investigate these changes by statistical analysis of a dataset comprising 107 million Twitter messages (authored by 2.7 million unique user accounts). Using a latent vector autoregressive model to aggregate across thousands of words, we identify high-level patterns in diffusion of linguistic change over the United States. Our model is robust to unpredictable changes in Twitter's sampling rate, and provides a probabilistic characterization of the relationship of macro-scale linguistic influence to a set of demographic and geographic predictors. The results of this analysis offer support for prior arguments that focus on geographical proximity and population size. However, demographic similarity – especially with regard to race – plays an even more central role, as cities with similar racial demographics are far more likely to share linguistic influence. Rather than moving towards a single unified “netspeak” dialect, language evolution in computer-mediated communication reproduces existing fault lines in spoken American English.

Contextualized word embeddings such as ELMo and BERT provide a foundation for strong performance across a wide range of natural language processing tasks by pretraining on large corpora of unlabeled text. However, the applicability of this approach is unknown when the target domain varies substantially from the pretraining corpus. We are specifically interested in the scenario in which labeled data is available in only a canonical source domain such as newstext, and the target domain is distinct from both the labeled and pretraining texts. To address this scenario, we propose domain-adaptive finetuning, in which the contextualized embeddings are adapted by masked language modeling on text from the target domain. We test this approach on sequence labeling in two challenging domains: Early Modern English and Twitter. Both domains differ substantially from existing pretraining corpora, and domain-adaptive fine-tuning yields substantial improvements over strong BERT baselines, with particularly impressive results on out-ofvocabulary words. We conclude that domainadaptive fine-tuning offers a simple and effective approach for the unsupervised adaptation of sequence labeling to difficult new domains. 1 2 While it might be desirable to completely retrain contextualized word embedding models in the target domain (e.g., , this requires data and computational resources that are often unavailable.

Word embeddings improve generalization over lexical features by placing each word in a lower-dimensional space, using distributional information obtained from unlabeled data. However, the effectiveness of word embeddings for downstream NLP tasks is limited by out-of-vocabulary (OOV) words, for which embeddings do not exist. In this paper, we present MIM-ICK, an approach to generating OOV word embeddings compositionally, by learning a function from spellings to distributional embeddings. Unlike prior work, MIMICK does not require re-training on the original word embedding corpus; instead, learning is performed at the type level. Intrinsic and extrinsic evaluations demonstrate the power of this simple approach. On 23 languages, MIMICK improves performance over a word-based baseline for tagging part-of-speech and morphosyntactic attributes. It is competitive with (and complementary to) a supervised characterbased model in low-resource settings.