Matrix Factorization Techniques for Recommender Systems

Recent work on open domain question answering (QA) assumes strong supervision of the supporting evidence and/or assumes a blackbox information retrieval (IR) system to retrieve evidence candidates. We argue that both are suboptimal, since gold evidence is not always available, and QA is fundamentally different from IR. We show for the first time that it is possible to jointly learn the retriever and reader from question-answer string pairs and without any IR system. In this setting, evidence retrieval from all of Wikipedia is treated as a latent variable. Since this is impractical to learn from scratch, we pre-train the retriever with an Inverse Cloze Task. We evaluate on open versions of five QA datasets. On datasets where the questioner already knows the answer, a traditional IR system such as BM25 is sufficient. On datasets where a user is genuinely seeking an answer, we show that learned retrieval is crucial, outperforming BM25 by up to 19 points in exact match.

/pdf/latent-retrieval-for-weakly-supervised-open-domain-question-3pkzwd92g3.pdf

Latent Retrieval for Weakly Supervised Open Domain Question Answering

Generative models for open domain question answering have proven to be competitive, without resorting to external knowledge. While promising, this approach requires to use models with billions of parameters, which are expensive to train and query. In this paper, we investigate how much these models can benefit from retrieving text passages, potentially containing evidence. We obtain state-of-the-art results on the Natural Questions and TriviaQA open benchmarks. Interestingly, we observe that the performance of this method significantly improves when increasing the number of retrieved passages. This is evidence that generative models are good at aggregating and combining evidence from multiple passages.

Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

We demonstrate an end-to-end question answering system that integrates BERT with the open-source Anserini information retrieval toolkit. In contrast to most question answering and reading comprehension models today, which operate over small amounts of input text, our system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles in an end-to-end fashion. We report large improvements over previous results on a standard benchmark test collection, showing that fine-tuning pretrained BERT with SQuAD is sufficient to achieve high accuracy in identifying answer spans.

End-to-End Open-Domain Question Answering with BERTserini

Similarity has always been a key aspect in computer science and statistics. Any time two element vectors are compared, many different similarity approaches can be used, depending on the final goal of the comparison (Euclidean distance, Pearson correlation coefficient, Spearman's rank correlation coefficient, and others). But if the comparison has to be applied to more complex data samples, with features having different dimensionality and types which might need compression before processing, these measures would be unsuitable. In these cases, a siamese neural network may be the best choice: it consists of two identical artificial neural networks each capable of learning the hidden representation of an input vector. The two neural networks are both feedforward perceptrons, and employ error back-propagation during training; they work parallelly in tandem and compare their outputs at the end, usually through a cosine distance. The output generated by a siamese neural network execution can be considered the semantic similarity between the projected representation of the two input vectors. In this overview we first describe the siamese neural network architecture, and then we outline its main applications in a number of computational fields since its appearance in 1994. Additionally, we list the programming languages, software packages, tutorials, and guides that can be practically used by readers to implement this powerful machine learning model.

Siamese Neural Networks: An Overview.

Recently, open-domain question answering (QA) has been combined with machine comprehension models to find answers in a large knowledge source As open-domain QA requires retrieving relevant documents from text corpora to answer questions, its performance largely depends on the performance of document retrievers However, since traditional information retrieval systems are not effective in obtaining documents with a high probability of containing answers, they lower the performance of QA systems Simply extracting more documents increases the number of irrelevant documents, which also degrades the performance of QA systems In this paper, we introduce Paragraph Ranker which ranks paragraphs of retrieved documents for a higher answer recall with less noise We show that ranking paragraphs and aggregating answers using Paragraph Ranker improves performance of open-domain QA pipeline on the four open-domain QA datasets by 78% on average

/pdf/ranking-paragraphs-for-improving-answer-recall-in-open-n7je95my1e.pdf

Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering

Motivation Traditional drug discovery approaches identify a target for a disease and find a compound that binds to the target. In this approach, structures of compounds are considered as the most important features because it is assumed that similar structures will bind to the same target. Therefore, structural analogs of the drugs that bind to the target are selected as drug candidates. However, even though compounds are not structural analogs, they may achieve the desired response. A new drug discovery method based on drug response, which can complement the structure-based methods, is needed. Results We implemented Siamese neural networks called ReSimNet that take as input two chemical compounds and predicts the CMap score of the two compounds, which we use to measure the transcriptional response similarity of the two compounds. ReSimNet learns the embedding vector of a chemical compound in a transcriptional response space. ReSimNet is trained to minimize the difference between the cosine similarity of the embedding vectors of the two compounds and the CMap score of the two compounds. ReSimNet can find pairs of compounds that are similar in response even though they may have dissimilar structures. In our quantitative evaluation, ReSimNet outperformed the baseline machine learning models. The ReSimNet ensemble model achieves a Pearson correlation of 0.518 and a precision@1% of 0.989. In addition, in the qualitative analysis, we tested ReSimNet on the ZINC15 database and showed that ReSimNet successfully identifies chemical compounds that are relevant to a prototype drug whose mechanism of action is known. Availability and implementation The source code and the pre-trained weights of ReSimNet are available at https://github.com/dmis-lab/ReSimNet. Supplementary information Supplementary data are available at Bioinformatics online.

ReSimNet: drug response similarity prediction using Siamese neural networks.

Many extractive question answering models are trained to predict start and end positions of answers. The choice of predicting answers as positions is mainly due to its simplicity and effectiveness. In this study, we hypothesize that when the distribution of the answer positions is highly skewed in the training set (e.g., answers lie only in the k-th sentence of each passage), QA models predicting answers as positions can learn spurious positional cues and fail to give answers in different positions. We first illustrate this position bias in popular extractive QA models such as BiDAF and BERT and thoroughly examine how position bias propagates through each layer of BERT. To safely deliver position information without position bias, we train models with various de-biasing methods including entropy regularization and bias ensembling. Among them, we found that using the prior distribution of answer positions as a bias model is very effective at reducing position bias, recovering the performance of BERT from 37.48% to 81.64% when trained on a biased SQuAD dataset.

Look at the First Sentence: Position Bias in Question Answering

The recent outbreak of the novel coronavirus is wreaking havoc on the world and researchers are struggling to effectively combat it. One reason why the fight is difficult is due to the lack of information and knowledge. In this work, we outline our effort to contribute to shrinking this knowledge vacuum by creating covidAsk, a question answering (QA) system that combines biomedical text mining and QA techniques to provide answers to questions in real-time. Our system also leverages information retrieval (IR) approaches to provide entity-level answers that are complementary to QA models. Evaluation of covidAsk is carried out by using a manually created dataset called COVID-19 Questions which is based on information from various sources, including the CDC and the WHO. We hope our system will be able to aid researchers in their search for knowledge and information not only for COVID-19, but for future pandemics as well.

/pdf/answering-questions-on-covid-19-in-real-time-8geb48v8mi.pdf

Answering Questions on COVID-19 in Real-Time

/pdf/look-at-the-first-sentence-position-bias-in-question-428ggnw9uo.pdf

Miyoung Ko

Papers

Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering

ReSimNet: drug response similarity prediction using Siamese neural networks.

Look at the First Sentence: Position Bias in Question Answering

Answering Questions on COVID-19 in Real-Time

Look at the First Sentence: Position Bias in Question Answering