Ashutosh Modi

Bio: Ashutosh Modi is an academic researcher from Indian Institute of Technology Kanpur. The author has contributed to research in topics: SemEval & Task (project management). The author has an hindex of 14, co-authored 72 publications receiving 721 citations. Previous affiliations of Ashutosh Modi include Siemens & Saarland University.

SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge

Abstract: This report summarizes the results of the SemEval 2018 task on machine comprehension using commonsense knowledge. For this machine comprehension task, we created a new corpus, MCScript. It contains a high number of questions that require commonsense knowledge for finding the correct answer. 11 teams from 4 different countries participated in this shared task, most of them used neural approaches. The best performing system achieves an accuracy of 83.95%, outperforming the baselines by a large margin, but still far from the human upper bound, which was found to be at 98%.

Affect-driven dialog generation

Abstract: According to one implementation, an affect-driven dialog generation system includes a computing platform having a hardware processor and a system memory storing a software code including a sequence-to-sequence (seq2seq) architecture trained using a loss function having an affective regularizer term based on a difference in emotional content between a target dialog response and a dialog sequence determined by the seq2seq architecture during training. The hardware processor executes the software code to receive an input dialog sequence, and to use the seq2seq architecture to generate emotionally diverse dialog responses based on the input dialog sequence and a predetermined target emotion. The hardware processor further executes the software code to determine, using the seq2seq architecture, a final dialog sequence responsive to the input dialog sequence based on an emotional relevance of each of the emotionally diverse dialog responses, and to provide the final dialog sequence as an output.

Inducing Neural Models of Script Knowledge

Abstract: Induction of common sense knowledge about prototypical sequence of events has recently received much attention (e.g., Chambers and Jurafsky (2008); Regneri et al. (2010)). Instead of inducing this knowledge in the form of graphs, as in much of the previous work, in our method, distributed representations of event realizations are computed based on distributed representations of predicates and their arguments, and then these representations are used to predict prototypical event orderings. The parameters of the compositional process for computing the event representations and the ranking component of the model are jointly estimated. We show that this approach results in a substantial boost in performance on the event ordering task with respect to the previous approaches, both on natural and crowdsourced texts.

Event Embeddings for Semantic Script Modeling

Abstract: Semantic scripts is a conceptual representation which defines how events are organized into higher level activities. Practically all the previous approaches to inducing script knowledge from text relied on count-based techniques (e.g., generative models) and have not attempted to compositionally model events. In this work, we introduce a neural network model which relies on distributed compositional representations of events. The model captures statistical dependencies between events in a scenario, overcomes some of the shortcomings of previous approaches (e.g., by more effectively dealing with data sparsity) and outperforms count-based counterparts on the narrative cloze task.

MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge

Abstract: We introduce a large dataset of narrative texts and questions about these texts, intended to be used in a machine comprehension task that requires reasoning using commonsense knowledge. Our dataset complements similar datasets in that we focus on stories about everyday activities, such as going to the movies or working in the garden, and that the questions require commonsense knowledge, or more specifically, script knowledge, to be answered. We show that our mode of data collection via crowdsourcing results in a substantial amount of such inference questions. The dataset forms the basis of a shared task on commonsense and script knowledge organized at SemEval 2018 and provides challenging test cases for the broader natural language understanding community.

BERTScore: Evaluating Text Generation with BERT

Abstract: We propose BERTScore, an automatic evaluation metric for text generation. Analogously to common metrics, BERTScore computes a similarity score for each token in the candidate sentence with each token in the reference sentence. However, instead of exact matches, we compute token similarity using contextual embeddings. We evaluate using the outputs of 363 machine translation and image captioning systems. BERTScore correlates better with human judgments and provides stronger model selection performance than existing metrics. Finally, we use an adversarial paraphrase detection task to show that BERTScore is more robust to challenging examples when compared to existing metrics.

BERTScore: Evaluating Text Generation with BERT

Abstract: We propose BERTScore, an automatic evaluation metric for text generation. Analogously to common metrics, BERTScore computes a similarity score for each token in the candidate sentence with each token in the reference sentence. However, instead of exact matches, we compute token similarity using contextual embeddings. We evaluate using the outputs of 363 machine translation and image captioning systems. BERTScore correlates better with human judgments and provides stronger model selection performance than existing metrics. Finally, we use an adversarial paraphrase detection task and show that BERTScore is more robust to challenging examples compared to existing metrics.

CoQA: A Conversational Question Answering Challenge

Abstract: Humans gather information through conversations involving a series of interconnected questions and answers. For machines to assist in information gathering, it is therefore essential to enable them to answer conversational questions. We introduce CoQA, a novel dataset for building Conversational Question Answering systems. Our dataset contains 127k questions with answers, obtained from 8k conversations about text passages from seven diverse domains. The questions are conversational, and the answers are free-form text with their corresponding evidence highlighted in the passage. We analyze CoQA in depth and show that conversational questions have challenging phenomena not present in existing reading comprehension datasets, e.g., coreference and pragmatic reasoning. We evaluate strong dialogue and reading comprehension models on CoQA. The best system obtains an F1 score of 65.4%, which is 23.4 points behind human performance (88.8%), indicating there is ample room for improvement. We present CoQA as a challenge to the community at https://stanfordnlp.github.io/coqa

DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs

Abstract: Reading comprehension has recently seen rapid progress, with systems matching humans on the most popular datasets for the task. However, a large body of work has highlighted the brittleness of these systems, showing that there is much work left to be done. We introduce a new reading comprehension benchmark, DROP, which requires Discrete Reasoning Over the content of Paragraphs. In this crowdsourced, adversarially-created, 55k-question benchmark, a system must resolve references in a question, perhaps to multiple input positions, and perform discrete operations over them (such as addition, counting, or sorting). These operations require a much more comprehensive understanding of the content of paragraphs, as they remove the paraphrase-and-entity-typing shortcuts available in prior datasets. We apply state-of-the-art methods from both the reading comprehension and semantic parsing literatures on this dataset and show that the best systems only achieve 38.4% F1 on our generalized accuracy metric, while expert human performance is 96%. We additionally present a new model that combines reading comprehension methods with simple numerical reasoning to achieve 51% F1.