Related papers: Task-Oriented Paraphrase Analytics

Automatically assigning tasks to people is challenging because human performance can vary across tasks for many reasons. This challenge is further compounded in real-life settings in which no oracle exists to assess the quality of human…

Word embeddings are substantially successful in capturing semantic relations among words. However, these lexical semantics are difficult to be interpreted. Definition modeling provides a more intuitive way to evaluate embeddings by…

We study the potential synergy between two different NLP tasks, both confronting predicate lexical variability: identifying predicate paraphrases, and event coreference resolution. First, we used annotations from an event coreference…

While the NLP community has produced numerous summarization benchmarks, none provide the rich annotations required to simultaneously address many important problems related to control and reliability. We introduce a Wikipedia-derived…

The precise formulation of derivation for tree-adjoining grammars has important ramifications for a wide variety of uses of the formalism, from syntactic analysis to semantic interpretation and statistical language modeling. We argue that…

Paraphrase detection is important for a number of applications, including plagiarism detection, authorship attribution, question answering, text summarization, text mining in general, etc. In this paper, we give a performance overview of…

Additive models form a widely popular class of regression models which represent the relation between covariates and response variables as the sum of low-dimensional transfer functions. Besides flexibility and accuracy, a key benefit of…

While LLMs have shown great success in understanding and generating text in traditional conversational settings, their potential for performing ill-defined complex tasks is largely under-studied. Indeed, we are yet to conduct comprehensive…

A great variety of text tasks such as topic or spam identification, user profiling, and sentiment analysis can be posed as a supervised learning problem and tackle using a text classifier. A text classifier consists of several subprocesses,…

Many computer vision tasks address the problem of scene understanding and are naturally interrelated e.g. object classification, detection, scene segmentation, depth estimation, etc. We show that we can leverage the inherent relationships…

We examine the role of character patterns in three tasks: morphological analysis, lemmatization and copy. We use a modified version of the standard sequence-to-sequence model, where the encoder is a pattern matching network. Each pattern…

For the many journalists who use data and computation to report the news, data wrangling is an integral part of their work.Despite an abundance of literature on data wrangling in the context of enterprise data analysis, little is known…

Multi-task learning, as it is understood nowadays, consists of using one single model to carry out several similar tasks. From classifying hand-written characters of different alphabets to figuring out how to play several Atari games using…

Data efficiency, despite being an attractive characteristic, is often challenging to measure and optimize for in task-oriented semantic parsing; unlike exact match, it can require both model- and domain-specific setups, which have,…

Sentence ordering is a general and critical task for natural language generation applications. Previous works have focused on improving its performance in an external, downstream task, such as multi-document summarization. Given its…

Multi-task learning has recently become a very active field in deep learning research. In contrast to learning a single task in isolation, multiple tasks are learned at the same time, thereby utilizing the training signal of related tasks…

Predicting narrative similarity can be understood as an inherently interpretive task: different, equally valid readings of the same text can produce divergent interpretations and thus different similarity judgments, posing a fundamental…

Optimizing the phrasing of argumentative text is crucial in higher education and professional development. However, assessing whether and how the different claims in a text should be revised is a hard task, especially for novice writers. In…

Contextualized word embedding models, such as ELMo, generate meaningful representations of words and their context. These models have been shown to have a great impact on downstream applications. However, in many cases, the contextualized…

Textual representations based on pre-trained language models are key, especially in few-shot learning scenarios. What makes a representation good for text classification? Is it due to the geometric properties of the space or because it is…