Разнообразие

In this paper, we propose a multi-criteria- based active learning approach and effec- tively apply it to named entity recognition. Active learning targets to minimize the human annotation efforts by …...

We analyze collective discourse, a collective human behavior in content generation, and show that it exhibits diversity, a property of general collective systems. Using extensive analysis, we propose a novel …...

This paper addresses the problem of produc- ing a diverse set of plausible translations. We present a simple procedure that can be used with any statistical machine translation (MT) system. …...

This paper addresses the problem of building concise, diverse and relevant lists of documents, which can be recommended to the participants of a conversation to fulfill their information needs without …...

In this paper we study the task of movie script summarization, which we argue could enhance script browsing, give readers a rough idea of the script’s plotline, and speed up …...

AbstractWe release Galactic Dependencies 1.0—a large set of synthetic languages not found on Earth, but annotated in Universal Dependencies format. This new resource aims to provide training and development data …...

AbstractEnterprise content writers are engaged in writing textual content for various purposes. Often, the text being written may already be present in the enterprise corpus in the form of past …...

AbstractAutomatic image description systems typically produce generic sentences that only make use of a small subset of the vocabulary available to them. In this paper, we consider the production of …...

AbstractWe present a new summary evaluation approach that does not require human model summaries. Our approach exploits the compositional capabilities of corpus-based and lexical resource-based word embeddings to develop the …...

AbstractNeural models have become one of the most important approaches to dialog response generation. However, they still tend to generate the most common and generic responses in the corpus all …...

AbstractAlthough neural conversational models are effective in learning how to produce fluent responses, their primary challenge lies in knowing what to say to make the conversation contentful and non-vacuous. We …...

AbstractIt is desirable for dialog systems to have capability to express specific emotions during a conversation, which has a direct, quantifiable impact on improvement of their usability and user satisfaction. …...

AbstractAlthough recent neural conversation models have shown great potential, they often generate bland and generic responses. While various approaches have been explored to diversify the output of the conversation model, …...

AbstractMulti-turn conversations consist of complex semantic structures, and it is still a challenge to generate coherent and diverse responses given previous utterances. It’s practical that a conversation takes place under …...

AbstractWe consider neural language generation under a novel problem setting: generating the words of a sentence according to the order of their first appearance in its lexicalized PCFG parse tree, …...

AbstractNLP models are shown to suffer from robustness issues, i.e., a model’s prediction can be easily changed under small perturbations to the input. In this work, we present a Controlled …...

AbstractEmotion-controllable response generation is an attractive and valuable task that aims to make open-domain conversations more empathetic and engaging. Existing methods mainly enhance the emotion expression by adding regularization terms …...

AbstractMuch progress has been made in text summarization, fueled by neural architectures using large-scale training corpora. However, in the news domain, neural models easily overfit by leveraging position-related features due …...

AbstractDespite recent advances in neural text generation, encoding the rich diversity in human language remains elusive. We argue that the sub-optimal text generation is mainly attributable to the imbalanced token …...

AbstractTraining the generative models with minimal corpus is one of the critical challenges for building open-domain dialogue systems. Existing methods tend to use the meta-learning framework which pre-trains the parameters …...

AbstractNeural network (NN) based data2text models achieve state-of-the-art (SOTA) performance in most metrics, but they sometimes drop or modify the information in the input, and it is hard to control …...

AbstractExisting pre-trained large language models have shown unparalleled generative capabilities. However, they are not controllable. In this paper, we propose MEGATRON-CNTRL, a novel framework that uses large-scale language models and …...

AbstractPast work on story generation has demonstrated the usefulness of conditioning on a generation plan to generate coherent stories. However, these approaches have used heuristics or off-the-shelf models to first …...

AbstractParaphrasing natural language sentences is a multifaceted process: it might involve replacing individual words or short phrases, local rearrangement of content, or high-level restructuring like topicalization or passivization. Past approaches …...

AbstractSequence-to-sequence based models have recently shown promising results in generating high-quality questions. However, these models are also known to have main drawbacks such as lack of diversity and bad sentence …...

AbstractExposure bias has been regarded as a central problem for auto-regressive language models (LM). It claims that teacher forcing would cause the test-time generation to be incrementally distorted due to …...

AbstractGenerating some appealing questions in open-domain conversations is an effective way to improve human-machine interactions and lead the topic to a broader or deeper direction. To avoid dull or deviated …...

Writing a coherent and engaging story is not easy. Creative writers use their knowledge and worldview to put disjointed elements together to form a coherent storyline, and work and rework …...

In recent years, neural paraphrase generation based on Seq2Seq has achieved superior per- formance, however, the generated paraphrase still has the problem of lack of diversity. In this paper, we …...

AbstractGenerating paragraphs of diverse contents is important in many applications. Existing generation models produce similar contents from homogenized contexts due to the fixed left-to-right sentence order. Our idea is permuting …...

AbstractA typical goal for language understanding is to logically connect the events of a discourse, but often connective events are not described due to their commonsense nature. In order to …...

AbstractNews recommender systems face certain challenges. These challenges arise due to evolving users’ preferences over dynamically created news articles. The diversity is necessary for a news recommender system to expose …...

AbstractGenerative commonsense reasoning (GCR) in natural language is to reason about the commonsense while generating coherent text. Recent years have seen a surge of interest in improving the generation quality …...

AbstractOpen-ended text generation tasks, such as dialogue generation and story completion, require models to generate a coherent continuation given limited preceding context. The open-ended nature of these tasks brings new …...

AbstractIn modern recommender systems, there are usually comments or reviews from users that justify their ratings for different items. Trained on such textual corpus, explainable recommendation models learn to discover …...

AbstractZero-shot paraphrase generation has drawn much attention as the large-scale high-quality paraphrase corpus is limited. Back-translation, also known as the pivot-based method, is typical to this end. Several works leverage …...

AbstractEmpathy is a crucial factor in open-domain conversations, which naturally shows one’s caring and understanding to others. Though several methods have been proposed to generate empathetic responses, existing works often …...

AbstractIn this paper, we propose DimonGen, which aims to generate diverse sentences describing concept relationships in various everyday scenarios. To support this, we first create a benchmark dataset for this …...

AbstractCompositional generalization–understanding unseen combinations of seen primitives–is an essential reasoning capability in human intelligence. The AI community mainly studies this capability by fine-tuning neural networks on lots of training samples, …...

AbstractLarge language models (LLMs) can be used to generate text data for training and evaluating other models. However, creating high-quality datasets with LLMs can be challenging. In this work, we …...

AbstractLogical Table-to-Text (LT2T) generation is tasked with generating logically faithful sentences from tables. There currently exists two challenges in the field: 1) Faithfulness: how to generate sentences that are factually …...