We discuss automatic creation of medical reports from ASR-generated patient-doctor conversational transcripts using an end-to-end neural summarization approach. We explore both recurrent neural network (RNN) and Transformer-based sequence-to-sequence architectures for summarizing medical conversations. We have incorporated enhancements to these architectures, such as the pointer-generator network that facilitates copying parts of the conversations to the reports, and a hierarchical RNN encoder that makes RNN training three times faster with long inputs. A comparison of the relative improvements from the different model architectures over an oracle extractive baseline is provided on a dataset of 800k orthopedic encounters. Consistent with observations in literature for machine translation and related tasks, we find the Transformer models outperform RNN in accuracy, while taking less than half the time to train. Significantly large wins over a strong oracle baseline indicate that sequence-to-sequence modeling is a promising approach for automatic generation of medical reports, in the presence of data at scale.

In recent years the use of electronic medical records has accelerated resulting in large volumes of medical data when a patient visits a healthcare facility. As a first step towards reimbursement healthcare institutions need to associate ICD-10 billing codes to these documents. This is done by trained clinical coders who may use a computer assisted solution for shortlisting of codes. In this work, we present our work to build a machine learning based scalable system for predicting ICD-10 codes from electronic medical records. We address data imbalance issues by implementing two system architectures using convolutional neural networks and logistic regression models. We illustrate the pros and cons of those system designs and show that the best performance can be achieved by leveraging the advantages of both using a system combination approach.

This paper describes an empirical study of coreference in spoken vs. written text. We focus on the comparison of two particular text types, interviews and popular science texts, as instances of spoken and written texts since they display quite different discourse structures. We believe in fact, that the correlation of difficulties in coreference resolution and varying discourse structures requires a deeper analysis that accounts for the diversity of coreference strategies or their sub-phenomena as indicators of text type or genre. In this work, we therefore aim at defining specific parameters that classify differences in genres of spoken and written texts such as the preferred segmentation strategy, the maximal allowed distance in or the length and size of coreference chains as well as the correlation of structural and syntactic features of coreferring expressions. We argue that a characterization of such genre dependent parameters might improve the performance of current state-of-art coreference resolution technology.

Recently, most of the research in NLP has concentrated on the creation of applications coping with textual entailment. However, there still exist very few resources for the evaluation of such applications. We argue that the reason for this resides not only in the novelty of the research field but also and mainly in the difficulty of defining the linguistic phenomena which are responsible for inference. As the TSNLP project has shown test suites provide optimal diagnostic and evaluation tools for NLP applications, as contrary to text corpora they provide a deep insight in the linguistic phenomena allowing control over the data. Thus in this paper, we present a test suite specifically developed for studying inference problems shown by English adjectives. The construction of the test suite is based on the deep linguistic analysis and following classification of entailment patterns of adjectives and follows the TSNLP guidelines on linguistic databases providing a clear coverage, systematic annotation of inference tasks, large reusability and simple maintenance. With the design of this test suite we aim at creating a resource supporting the evaluation of computational systems handling natural language inference and in particular at providing a benchmark against which to evaluate and compare existing semantic analysers.