Alexander Rosenberg Johansen

Renee D. White, Tristan Peng, Pann Sripitak et al.

A clinical trial is a study that evaluates new biomedical interventions. To design new trials, researchers draw inspiration from those current and completed. In 2022, there were on average more than 100 clinical trials submitted to ClinicalTrials.gov every day, with each trial having a mean of approximately 1500 words [1]. This makes it nearly impossible to keep up to date. To mitigate this issue, we have created a batch clinical trial summarizer called CliniDigest using GPT-3.5. CliniDigest is, to our knowledge, the first tool able to provide real-time, truthful, and comprehensive summaries of clinical trials. CliniDigest can reduce up to 85 clinical trial descriptions (approximately 10,500 words) into a concise 200-word summary with references and limited hallucinations. We have tested CliniDigest on its ability to summarize 457 trials divided across 27 medical subdomains. For each field, CliniDigest generates summaries of $μ=153,\ σ=69 $ words, each of which utilizes $μ=54\%,\ σ=30\% $ of the sources. A more comprehensive evaluation is planned and outlined in this paper.

Andreas Madsen, Alexander Rosenberg Johansen

Neural networks can approximate complex functions, but they struggle to perform exact arithmetic operations over real numbers. The lack of inductive bias for arithmetic operations leaves neural networks without the underlying logic necessary to extrapolate on tasks such as addition, subtraction, and multiplication. We present two new neural network components: the Neural Addition Unit (NAU), which can learn exact addition and subtraction; and the Neural Multiplication Unit (NMU) that can multiply subsets of a vector. The NMU is, to our knowledge, the first arithmetic neural network component that can learn to multiply elements from a vector, when the hidden size is large. The two new components draw inspiration from a theoretical analysis of recently proposed arithmetic components. We find that careful initialization, restricting parameter space, and regularizing for sparsity is important when optimizing the NAU and NMU. Our proposed units NAU and NMU, compared with previous neural units, converge more consistently, have fewer parameters, learn faster, can converge for larger hidden sizes, obtain sparse and meaningful weights, and can extrapolate to negative and small values.

Jeppe Johan Waarkjær Olsen, Peter Ebert Christensen, Martin Hangaard Hansen et al.

Discrete structure rules for validating molecular structures are usually limited to fulfillment of the octet rule or similar simple deterministic heuristics. We propose a model, inspired by language modeling from natural language processing, with the ability to learn from a collection of undirected molecular graphs, enabling fitting of any underlying structure rule present in the collection. We introduce an adaption to the popular Transformer model, which can learn relationships between atoms and bonds. To our knowledge, the Transformer adaption is the first model that is trained to solve the unsupervised task of recovering partially observed molecules. In this work, we assess how different degrees of information impact performance w.r.t. to fitting the QM9 dataset, which conforms to the octet rule, and to fitting the ZINC dataset, which contains hypervalent molecules and ions requiring the model to learn a more complex structure rule. More specifically, we test a full discrete graph with bond order information, a full discrete graph with only connectivity, a bag-of-neighbors, a bag-of-atoms, and a count-based unigram statistics. These results provide encouraging evidence that neural networks, even when only connectivity is available, can learn arbitrary molecular structure rules specific to a dataset, as the Transformer adaption surpasses a strong octet rule baseline on the ZINC dataset.

Andreas Madsen, Alexander Rosenberg Johansen

The Neural Arithmetic Logic Unit (NALU) is a neural network layer that can learn exact arithmetic operations between the elements of a hidden state. The goal of NALU is to learn perfect extrapolation, which requires learning the exact underlying logic of an unknown arithmetic problem. Evaluating the performance of the NALU is non-trivial as one arithmetic problem might have many solutions. As a consequence, single-instance MSE has been used to evaluate and compare performance between models. However, it can be hard to interpret what magnitude of MSE represents a correct solution and models sensitivity to initialization. We propose using a success-criterion to measure if and when a model converges. Using a success-criterion we can summarize success-rate over many initialization seeds and calculate confidence intervals. We contribute a generalized version of the previous arithmetic benchmark to measure models sensitivity under different conditions. This is, to our knowledge, the first extensive evaluation with respect to convergence of the NALU and its sub-units. Using a success-criterion to summarize 4800 experiments we find that consistently learning arithmetic extrapolation is challenging, in particular for multiplication.

Alexander Rosenberg Johansen, Richard Socher

Many recent advances in deep learning for natural language processing have come at increasing computational cost, but the power of these state-of-the-art models is not needed for every example in a dataset. We demonstrate two approaches to reducing unnecessary computation in cases where a fast but weak baseline classier and a stronger, slower model are both available. Applying an AUC-based metric to the task of sentiment classification, we find significant efficiency gains with both a probability-threshold method for reducing computational cost and one that uses a secondary decision network.

Alexander Rosenberg Johansen, Jonas Meinertz Hansen, Elias Khazen Obeid et al.

Most existing Neural Machine Translation models use groups of characters or whole words as their unit of input and output. We propose a model with a hierarchical char2word encoder, that takes individual characters both as input and output. We first argue that this hierarchical representation of the character encoder reduces computational complexity, and show that it improves translation performance. Secondly, by qualitatively studying attention plots from the decoder we find that the model learns to compress common words into a single embedding whereas rare words, such as names and places, are represented character by character.