Software requirements specification is undoubtedly critical for the whole software life-cycle. Nowadays, writing software requirements specifications primarily depends on human work. Although massive studies have been proposed to fasten the process via proposing advanced elicitation and analysis techniques, it is still a time-consuming and error-prone task that needs to take domain knowledge and business information into consideration. In this paper, we propose an approach, named ReqGen, which can provide recommendations by automatically generating natural language requirements specifications based on certain given keywords. Specifically, ReqGen consists of three critical steps. First, keywords-oriented knowledge is selected from domain ontology and is injected to the basic Unified pre-trained Language Model (UniLM) for domain fine-tuning. Second, a copy mechanism is integrated to ensure the occurrence of keywords in the generated statements. Finally, a requirement syntax constrained decoding is designed to close the semantic and syntax distance between the candidate and reference specifications. Experiments on two public datasets from different groups and domains show that ReqGen outperforms six popular natural language generation approaches with respect to the hard constraint of keywords(phrases) inclusion, BLEU, ROUGE and syntax compliance. We believe that ReqGen can promote the efficiency and intelligence of specifying software requirements.
相關內容
Automated vehicles (AVs) are tested in diverse scenarios, typically specified by parameters such as velocities, distances, or curve radii. To describe scenarios uniformly independent of such parameters, this paper proposes a vectorized scenario description defined by the road geometry and vehicles' trajectories. Data of this form are generated for three scenarios, merged, and used to train the motion prediction model VectorNet, allowing to predict an AV's trajectory for unseen scenarios. Predicting scenario evaluation metrics, VectorNet partially achieves lower errors than regression models that separately process the three scenarios' data. However, for comprehensive generalization, sufficient variance in the training data must be ensured. Thus, contrary to existing methods, our proposed method can merge diverse scenarios' data and exploit spatial and temporal nuances in the vectorized scenario description. As a result, data from specified test scenarios and real-world scenarios can be compared and combined for (predictive) analyses and scenario selection.
With the increasing demand of intelligent systems capable of operating in different user contexts (e.g. users on the move) the correct interpretation of the user-need by such systems has become crucial to give a consistent answer to the user query. The most effective techniques which are used to address such task are in the fields of natural language processing and semantic expansion of terms. Such systems are aimed at estimating the actual meaning of input queries, addressing the concepts of the words which are expressed within the user questions. The aim of this paper is to demonstrate which semantic relation impacts the most in semantic expansion-based retrieval systems and to identify the best tradeoff between accuracy and noise introduction when combining such relations. The evaluations are made building a simple natural language processing system capable of querying any taxonomy-driven domain, making use of the combination of different semantic expansions as knowledge resources. The proposed evaluation employs a wide and varied taxonomy as a use-case, exploiting its labels as basis for the expansions. To build the knowledge resources several corpora have been produced and integrated as gazetteers into the NLP infrastructure with the purpose of estimating the pseudo-queries corresponding to the taxonomy labels, considered as the possible intents.
Explainable AI was born as a pathway to allow humans to explore and understand the inner working of complex systems. However, establishing what is an explanation and objectively evaluating explainability are not trivial tasks. This paper presents a new model-agnostic metric to measure the Degree of Explainability of information in an objective way. We exploit a specific theoretical model from Ordinary Language Philosophy called the Achinstein's Theory of Explanations, implemented with an algorithm relying on deep language models for knowledge graph extraction and information retrieval. To understand whether this metric can measure explainability, we devised a few experiments and user studies involving more than 190 participants, evaluating two realistic systems for healthcare and finance using famous AI technology, including Artificial Neural Networks and TreeSHAP. The results we obtained are statistically significant (with P values lower than .01), suggesting that our proposed metric for measuring the Degree of Explainability is robust in several scenarios, and it aligns with concrete expectations.
While human evaluation remains best practice for accurately judging the faithfulness of automatically-generated summaries, few solutions exist to address the increased difficulty and workload when evaluating long-form summaries. Through a survey of 162 papers on long-form summarization, we first shed light on current human evaluation practices surrounding long-form summaries. We find that 73% of these papers do not perform any human evaluation on model-generated summaries, while other works face new difficulties that manifest when dealing with long documents (e.g., low inter-annotator agreement). Motivated by our survey, we present LongEval, a set of guidelines for human evaluation of faithfulness in long-form summaries that addresses the following challenges: (1) How can we achieve high inter-annotator agreement on faithfulness scores? (2) How can we minimize annotator workload while maintaining accurate faithfulness scores? and (3) Do humans benefit from automated alignment between summary and source snippets? We deploy LongEval in annotation studies on two long-form summarization datasets in different domains (SQuALITY and PubMed), and we find that switching to a finer granularity of judgment (e.g., clause-level) reduces inter-annotator variance in faithfulness scores (e.g., std-dev from 18.5 to 6.8). We also show that scores from a partial annotation of fine-grained units highly correlates with scores from a full annotation workload (0.89 Kendall's tau using 50% judgments). We release our human judgments, annotation templates, and our software as a Python library for future research.
Human doctors with well-structured medical knowledge can diagnose a disease merely via a few conversations with patients about symptoms. In contrast, existing knowledge-grounded dialogue systems often require a large number of dialogue instances to learn as they fail to capture the correlations between different diseases and neglect the diagnostic experience shared among them. To address this issue, we propose a more natural and practical paradigm, i.e., low-resource medical dialogue generation, which can transfer the diagnostic experience from source diseases to target ones with a handful of data for adaptation. It is capitalized on a commonsense knowledge graph to characterize the prior disease-symptom relations. Besides, we develop a Graph-Evolving Meta-Learning (GEML) framework that learns to evolve the commonsense graph for reasoning disease-symptom correlations in a new disease, which effectively alleviates the needs of a large number of dialogues. More importantly, by dynamically evolving disease-symptom graphs, GEML also well addresses the real-world challenges that the disease-symptom correlations of each disease may vary or evolve along with more diagnostic cases. Extensive experiment results on the CMDD dataset and our newly-collected Chunyu dataset testify the superiority of our approach over state-of-the-art approaches. Besides, our GEML can generate an enriched dialogue-sensitive knowledge graph in an online manner, which could benefit other tasks grounded on knowledge graph.
The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search, instances of the task can also be found in many natural language processing applications. This survey provides an overview of text ranking with neural network architectures known as transformers, of which BERT is the best-known example. The combination of transformers and self-supervised pretraining has, without exaggeration, revolutionized the fields of natural language processing (NLP), information retrieval (IR), and beyond. In this survey, we provide a synthesis of existing work as a single point of entry for practitioners who wish to gain a better understanding of how to apply transformers to text ranking problems and researchers who wish to pursue work in this area. We cover a wide range of modern techniques, grouped into two high-level categories: transformer models that perform reranking in multi-stage ranking architectures and learned dense representations that attempt to perform ranking directly. There are two themes that pervade our survey: techniques for handling long documents, beyond the typical sentence-by-sentence processing approaches used in NLP, and techniques for addressing the tradeoff between effectiveness (result quality) and efficiency (query latency). Although transformer architectures and pretraining techniques are recent innovations, many aspects of how they are applied to text ranking are relatively well understood and represent mature techniques. However, there remain many open research questions, and thus in addition to laying out the foundations of pretrained transformers for text ranking, this survey also attempts to prognosticate where the field is heading.
The notion of "in-domain data" in NLP is often over-simplistic and vague, as textual data varies in many nuanced linguistic aspects such as topic, style or level of formality. In addition, domain labels are many times unavailable, making it challenging to build domain-specific systems. We show that massive pre-trained language models implicitly learn sentence representations that cluster by domains without supervision -- suggesting a simple data-driven definition of domains in textual data. We harness this property and propose domain data selection methods based on such models, which require only a small set of in-domain monolingual data. We evaluate our data selection methods for neural machine translation across five diverse domains, where they outperform an established approach as measured by both BLEU and by precision and recall of sentence selection with respect to an oracle.
Interest in the field of Explainable Artificial Intelligence has been growing for decades and has accelerated recently. As Artificial Intelligence models have become more complex, and often more opaque, with the incorporation of complex machine learning techniques, explainability has become more critical. Recently, researchers have been investigating and tackling explainability with a user-centric focus, looking for explanations to consider trustworthiness, comprehensibility, explicit provenance, and context-awareness. In this chapter, we leverage our survey of explanation literature in Artificial Intelligence and closely related fields and use these past efforts to generate a set of explanation types that we feel reflect the expanded needs of explanation for today's artificial intelligence applications. We define each type and provide an example question that would motivate the need for this style of explanation. We believe this set of explanation types will help future system designers in their generation and prioritization of requirements and further help generate explanations that are better aligned to users' and situational needs.
As a crucial component in task-oriented dialog systems, the Natural Language Generation (NLG) module converts a dialog act represented in a semantic form into a response in natural language. The success of traditional template-based or statistical models typically relies on heavily annotated data, which is infeasible for new domains. Therefore, it is pivotal for an NLG system to generalize well with limited labelled data in real applications. To this end, we present FewShotWoz, the first NLG benchmark to simulate the few-shot learning setting in task-oriented dialog systems. Further, we develop the SC-GPT model. It is pre-trained on a large set of annotated NLG corpus to acquire the controllable generation ability, and fine-tuned with only a few domain-specific labels to adapt to new domains. Experiments on FewShotWoz and the large Multi-Domain-WOZ datasets show that the proposed SC-GPT significantly outperforms existing methods, measured by various automatic metrics and human evaluations.
Recent years have witnessed the enormous success of low-dimensional vector space representations of knowledge graphs to predict missing facts or find erroneous ones. Currently, however, it is not yet well-understood how ontological knowledge, e.g. given as a set of (existential) rules, can be embedded in a principled way. To address this shortcoming, in this paper we introduce a framework based on convex regions, which can faithfully incorporate ontological knowledge into the vector space embedding. Our technical contribution is two-fold. First, we show that some of the most popular existing embedding approaches are not capable of modelling even very simple types of rules. Second, we show that our framework can represent ontologies that are expressed using so-called quasi-chained existential rules in an exact way, such that any set of facts which is induced using that vector space embedding is logically consistent and deductively closed with respect to the input ontology.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191