Related papers: Reading StackOverflow Encourages Cheating: Adding …

In this paper, we propose a method for incorporating world knowledge (linked entities and fine-grained entity types) into a neural question generation model. This world knowledge helps to encode additional information related to the…

We introduce Data Diversification: a simple but effective strategy to boost neural machine translation (NMT) performance. It diversifies the training data by using the predictions of multiple forward and backward models and then merging…

The vast diversity of styles, domains, and quality levels present in language model pre-training corpora is essential in developing general model capabilities, but efficiently learning and deploying the correct behaviors exemplified in each…

Conversational machine reading systems help users answer high-level questions (e.g. determine if they qualify for particular government benefits) when they do not know the exact rules by which the determination is made(e.g. whether they…

Code has become a standard component of modern foundation language model (LM) training, yet its role beyond programming remains unclear. We revisit the claim that code improves reasoning through controlled pretraining experiments on a…

A common thread of open-domain question answering (QA) models employs a retriever-reader pipeline that first retrieves a handful of relevant passages from Wikipedia and then peruses the passages to produce an answer. However, even…

Question Answering (QA) tasks requiring information from multiple documents often rely on a retrieval model to identify relevant information for reasoning. The retrieval model is typically trained to maximize the likelihood of the labeled…

There is a key demand to automatically generate code for small tasks for developers. Websites such as StackOverflow provide a simplistic way by offering solutions in small snippets which provide a complete answer to whatever task question…

Despite substantial progress in multilingual extractive Question Answering (QA), models with high and uniformly distributed performance across languages remain challenging, especially for languages with limited resources. We study…

We introduce and study the task of clickbait spoiling: generating a short text that satisfies the curiosity induced by a clickbait post. Clickbait links to a web page and advertises its contents by arousing curiosity instead of providing an…

The ability to acquire latent semantics is one of the key properties that determines the performance of language models. One convenient approach to invoke this ability is to prepend metadata (e.g. URLs, domains, and styles) at the beginning…

Although automated harmful content detection systems are frequently used to monitor online platforms, moderators and end users frequently cannot understand the logic underlying their predictions. While recent studies have focused on…

We present a system for answering questions based on the full text of books (BookQA), which first selects book passages given a question at hand, and then uses a memory network to reason and predict an answer. To improve generalization, we…

Prior work on automated question generation has almost exclusively focused on generating simple questions whose answers can be extracted from a single document. However, there is an increasing interest in developing systems that are capable…

In this paper, we investigate the driving factors behind concatenation, a simple but effective data augmentation method for low-resource neural machine translation. Our experiments suggest that discourse context is unlikely the cause for…

Machine learning relies heavily on data, yet the continuous growth of real-world data poses challenges for efficient dataset construction and training. A fundamental yet unsolved question is: given our current model and data, does a new…

Stack Overflow is one of the most popular technical Q&A sites used by software developers. Seeking help from Stack Overflow has become an essential part of software developers' daily work for solving programming-related questions. Although…

Finding codes given natural language query isb eneficial to the productivity of software developers. Future progress towards better semantic matching between query and code requires richer supervised training resources. To remedy this, we…

Argument mining is a core technology for automating argument search in large document collections. Despite its usefulness for this task, most current approaches to argument mining are designed for use only with specific text types and fall…

Automatic argument generation is an appealing but challenging task. In this paper, we study the specific problem of counter-argument generation, and present a novel framework, CANDELA. It consists of a powerful retrieval system and a novel…