https://arxiv.org/abs/1505.01121v3 Ask Your Neurons: A Neural-based Approach to Answering Questions about Images

By combining latest advances in image representation and natural language processing, we propose Neural-Image-QA, an end-to-end formulation to this problem for which all parts are trained jointly.

https://arxiv.org/abs/1609.08097 Creating Causal Embeddings for Question Answering with Minimal Supervision

A common model for question answering (QA) is that a good answer is one that is closely related to the question, where relatedness is often determined using general-purpose lexical models such as word embeddings. We argue that a better approach is to look for answers that are related to the question in a relevant way, according to the information need of the question, which may be determined through task-specific embeddings. With causality as a use case, we implement this insight in three steps. First, we generate causal embeddings cost-effectively by bootstrapping cause-effect pairs extracted from free text using a small set of seed patterns. Second, we train dedicated embeddings over this data, by using task-specific contexts, i.e., the context of a cause is its effect. Finally, we extend a state-of-the-art reranking approach for QA to incorporate these causal embeddings. We evaluate the causal embedding models both directly with a casual implication task, and indirectly, in a downstream causal QA task using data from Yahoo! Answers. We show that explicitly modeling causality improves performance in both tasks. In the QA task our best model achieves 37.3% P@1, significantly outperforming a strong baseline by 7.7% (relative).

https://arxiv.org/abs/1505.00468v7 VQA: Visual Question Answering

https://arxiv.org/abs/1611.01604 Dynamic Coattention Networks For Question Answering

Several deep learning models have been proposed for question answering. However, due to their single-pass nature, they have no way to recover from local maxima corresponding to incorrect answers. To address this problem, we introduce the Dynamic Coattention Network (DCN) for question answering. The DCN first fuses co-dependent representations of the question and the document in order to focus on relevant parts of both. Then a dynamic pointing decoder iterates over potential answer spans. This iterative procedure enables the model to recover from initial local maxima corresponding to incorrect answers. On the Stanford question answering dataset, a single DCN model improves the previous state of the art from 71.0% F1 to 75.9%, while a DCN ensemble obtains 80.4% F1.

https://arxiv.org/abs/1609.07843 Pointer Sentinel Mixture Models

Recent neural network sequence models with softmax classifiers have achieved their best language modeling performance only with very large hidden states and large vocabularies. Even then they struggle to predict rare or unseen words even if the context makes the prediction unambiguous. We introduce the pointer sentinel mixture architecture for neural sequence models which has the ability to either reproduce a word from the recent context or produce a word from a standard softmax classifier. Our pointer sentinel-LSTM model achieves state of the art language modeling performance on the Penn Treebank (70.9 perplexity) while using far fewer parameters than a standard softmax LSTM. In order to evaluate how well language models can exploit longer contexts and deal with more realistic vocabularies and larger corpora we also introduce the freely available WikiText corpus.

https://arxiv.org/abs/1608.07905 Machine Comprehension Using Match-LSTM and Answer Pointer

Machine comprehension of text is an important problem in natural language processing. A recently released dataset, the Stanford Question Answering Dataset (SQuAD), offers a large number of real questions and their answers created by humans through crowdsourcing. SQuAD provides a challenging testbed for evaluating machine comprehension algorithms, partly because compared with previous datasets, in SQuAD the answers do not come from a small set of candidate answers and they have variable lengths. We propose an end-to-end neural architecture for the task. The architecture is based on match-LSTM, a model we proposed previously for textual entailment, and Pointer Net, a sequence-to-sequence model proposed by Vinyals et al.(2015) to constrain the output tokens to be from the input sequences. We propose two ways of using Pointer Net for our task. Our experiments show that both of our two models substantially outperform the best results obtained by Rajpurkar et al.(2016) using logistic regression and manually crafted features.

https://arxiv.org/pdf/1612.04936v1.pdf LEARNING THROUGH DIALOGUE INTERACTIONS

https://arxiv.org/abs/1606.02270 Natural Language Comprehension with the EpiReader

We present the EpiReader, a novel model for machine comprehension of text. Machine comprehension of unstructured, real-world text is a major research goal for natural language processing. Current tests of machine comprehension pose questions whose answers can be inferred from some supporting text, and evaluate a model's response to the questions. The EpiReader is an end-to-end neural model comprising two components: the first component proposes a small set of candidate answers after comparing a question to its supporting text, and the second component formulates hypotheses using the proposed candidates and the question, then reranks the hypotheses based on their estimated concordance with the supporting text. We present experiments demonstrating that the EpiReader sets a new state-of-the-art on the CNN and Children's Book Test machine comprehension benchmarks, outperforming previous neural models by a significant margin.

https://arxiv.org/pdf/1611.01603.pdf Bidirectional Attention Flow for Machine Comprehension

https://arxiv.org/pdf/1611.08945v3.pdf LEARNING A NATURAL LANGUAGE INTERFACE WITH NEURAL PROGRAMMER

Learning a natural language interface for database tables is a challenging task that involves deep language understanding and multi-step reasoning. The task is often approached by mapping natural language queries to logical forms or programs that provide the desired response when executed on the database. To our knowledge, this paper presents the first weakly supervised, end-to-end neural network model to induce such programs on a real-world dataset. We enhance the objective function of Neural Programmer, a neural network with built-in discrete operations, and apply it on WikiTableQuestions, a natural language question-answering dataset. The model is trained end-to-end with weak supervision of question-answer pairs, and does not require domain-specific grammars, rules, or annotations that are key elements in previous approaches to program induction. The main experimental result in this paper is that a single Neural Programmer model achieves 34.2% accuracy using only 10,000 examples with weak supervision. An ensemble of 15 models, with a trivial combination technique, achieves 37.7% accuracy, which is competitive to the current state-of-the-art accuracy of 37.1% obtained by a traditional natural language semantic parser.

In this paper, we enhance Neural Programmer to work with weaker supervision signals to make it more broadly applicable. Soft selection during training enables the model to actively explore the space of programs by backpropagation with superior sample complexity. In our experiments, we show that the model achieves performance comparable to a state-of-the-art traditional semantic parser even though the training set contains only 10,000 examples. To our knowledge, this is the first instance of a weakly supervised, end-to-end neural network model that induces programs on a real-world dataset.

https://arxiv.org/pdf/1703.04816v1.pdf FastQA: A Simple and Efficient Neural Architecture for Question Answering

an efficient end-to-end neural model for question answering that is very competitive with existing models. We further demonstrate, that an extended version (FastQAExt) achieves state-of-the-art results on recent benchmark datasets, namely SQuAD, NewsQA and MsMARCO, outperforming most existing models. However, we show that increasing the complexity of FastQA to FastQAExt does not yield any systematic improvements.

https://arxiv.org/abs/1703.05320v1 Legal Question Answering using Ranking SVM and Deep Convolutional Neural Network

This paper presents a study of employing Ranking SVM and Convolutional Neural Network for two missions: legal information retrieval and question answering in the Competition on Legal Information Extraction/Entailment. For the first task, our proposed model used a triple of features (LSI, Manhattan, Jaccard), and is based on paragraph level instead of article level as in previous studies. In fact, each single-paragraph article corresponds to a particular paragraph in a huge multiple-paragraph article. For the legal question answering task, additional statistical features from information retrieval task integrated into Convolutional Neural Network contribute to higher accuracy.

https://arxiv.org/abs/1703.08885v1 Question Answering from Unstructured Text by Retrieval and Comprehension

In this work we present a two-step approach to question answering from unstructured text, consisting of a retrieval step and a comprehension step. For comprehension, we present an RNN based attention model with a novel mixture mechanism for selecting answers from either retrieved articles or a fixed vocabulary.

While there has been a lot of research on comprehension, little focus has been given to designing neural network based retrieval models. We present a simple such model, and emphasize the importance of this direction of research.

https://arxiv.org/pdf/1703.09831.pdf A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment

https://arxiv.org/pdf/1704.03493.pdf Creativity: Generating Diverse Questions using Variational Autoencoders

Generating diverse questions for given images is an important task for computational education, entertainment and AI assistants. Different from many conventional prediction techniques is the need for algorithms to generate a diverse set of plausible questions, which we refer to as “creativity”. In this paper we propose a creative algorithm for visual question generation which combines the advantages of variational autoencoders with long short-term memory networks. We demonstrate that our framework is able to generate a large set of varying questions given a single input image.

https://arxiv.org/abs/1704.00051v2 Reading Wikipedia to Answer Open-Domain Questions

neural network model trained to detect answers in Wikipedia paragraphs. Our experiments on multiple existing QA datasets indicate that (1) both modules are highly competitive with respect to existing counterparts and (2) multitask learning using distant supervision on their combination is an effective complete system on this challenging task.

https://arxiv.org/pdf/1606.03254v2.pdf Natural Language Generation enhances human decision-making with uncertain information

We show that the use of Natural Language Generation (NLG) improves decision-making under uncertainty, compared to state-of-theart graphical-based representation methods. In a task-based study with 442 adults, we found that presentations using NLG lead to 24% better decision-making on average than the graphical presentations, and to 44% better decision-making when NLG is combined with graphics. We also show that women achieve significantly better results when presented with NLG output (an 87% increase on average compared to graphical presentations).

https://arxiv.org/abs/1704.05179v1 SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine

We publicly release a new large-scale dataset, called SearchQA, for machine comprehension, or question-answering. Unlike recently released datasets, such as DeepMind CNN/DailyMail and SQuAD, the proposed SearchQA was constructed to reflect a full pipeline of general question-answering. That is, we start not from an existing article and generate a question-answer pair, but start from an existing question-answer pair, crawled from J! Archive, and augment it with text snippets retrieved by Google. Following this approach, we built SearchQA, which consists of more than 140k question-answer pairs with each pair having 49.6 snippets on average. Each question-answer-context tuple of the SearchQA comes with additional meta-data such as the snippet's URL, which we believe will be valuable resources for future research. We conduct human evaluation as well as test two baseline methods, one simple word selection and the other deep learning based, on the SearchQA. We show that there is a meaningful gap between the human and machine performances. This suggests that the proposed dataset could well serve as a benchmark for question-answering.

https://einstein.ai/static/images/layouts/research/seq2sql/seq2sql.pdf Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning

A significant amount of the world’s knowledge is stored in relational databases. However, the ability for users to retrieve facts from a database is limited due to a lack of understanding of query languages such as SQL. We propose Seq2SQL, a deep neural network for translating natural language questions to corresponding SQL queries. Our model leverages the structure of SQL queries to significantly reduce the output space of generated queries. Moreover, we use rewards from in-theloop query execution over the database to learn a policy to generate unordered parts of the query, which we show are less suitable for optimization via cross entropy loss. In addition, we will publish WikiSQL, a dataset of 87726 hand-annotated examples of questions and SQL queries distributed across 26375 tables from Wikipedia. This dataset is required to train our model and is an order of magnitude larger than comparable datasets. By applying policy-based reinforcement learning with a query execution environment to WikiSQL, our model Seq2SQL outperforms attentional sequence to sequence models, improving execution accuracy from 35.9% to 60.3% and logical form accuracy from 23.4% to 49.2%.

https://arxiv.org/abs/1711.08105v1 Visual Question Answering as a Meta Learning Task

We propose instead to approach VQA as a meta learning task, thus separating the question answering method from the information required. At test time, the method is provided with a support set of example questions/answers, over which it reasons to resolve the given question. The support set is not fixed and can be extended without retraining, thereby expanding the capabilities of the model. To exploit this dynamically provided information, we adapt a state-of-the-art VQA model with two techniques from the recent meta learning literature, namely prototypical networks and meta networks.

https://www.academia.edu/30775838/An_inference-based_framework_for_multistrategy_learning An inference-based framework for multistrategy learning

https://arxiv.org/abs/1806.08896 Towards Practical Visual Search Engine within Elasticsearch

https://arxiv.org/abs/1808.07036 QuAC : Question Answering in Context

https://arxiv.org/abs/1808.10568 Multi-Hop Knowledge Graph Reasoning with Reward Shaping

We propose two modeling advances to address both issues: (1) we reduce the impact of false negative supervision by adopting a pretrained one-hop embedding model to estimate the reward of unobserved facts; (2) we counter the sensitivity to spurious paths of on-policy RL by forcing the agent to explore a diverse set of paths using randomly generated edge masks. Our approach significantly improves over existing path-based KGQA models on several benchmark datasets and is comparable or better than embedding-based models.

https://arxiv.org/abs/1809.01494 Interpretation of Natural Language Rules in Conversational Machine Reading

https://hotpotqa.github.io/

https://arxiv.org/pdf/1809.00782.pdf Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text

https://arxiv.org/pdf/1810.02338.pdf Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding

https://ai.googleblog.com/2018/10/open-sourcing-active-question.html

https://arxiv.org/abs/1811.00232 Textbook Question Answering with Knowledge Graph Understanding and Unsupervised Open-set Text Comprehension

https://arxiv.org/abs/1811.00538 Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering