David Konopnicki

Georgios Christos Chouliaras, Kornel Kiełczewski, Amit Beka et al.

In the last few years, the Machine Learning (ML) and Artificial Intelligence community has developed an increasing interest in Software Engineering (SE) for ML Systems leading to a proliferation of best practices, rules, and guidelines aiming at improving the quality of the software of ML Systems. However, understanding their impact on the overall quality has received less attention. Practices are usually presented in a prescriptive manner, without an explicit connection to their overall contribution to software quality. Based on the observation that different practices influence different aspects of software-quality and that one single quality aspect might be addressed by several practices we propose a framework to analyse sets of best practices with focus on quality impact and prioritization of their implementation. We first introduce a hierarchical Software Quality Model (SQM) specifically tailored for ML Systems. Relying on expert knowledge, the connection between individual practices and software quality aspects is explicitly elicited for a large set of well-established practices. Applying set-function optimization techniques we can answer questions such as what is the set of practices that maximizes SQM coverage, what are the most important ones, which practices should be implemented in order to improve specific quality aspects, among others. We illustrate the usage of our framework by analyzing well-known sets of practices.

Yosi Mass, Doron Cohen, Asaf Yehudai et al.

We deal with the scenario of conversational search, where user queries are under-specified or ambiguous. This calls for a mixed-initiative setup. User-asks (queries) and system-answers, as well as system-asks (clarification questions) and user response, in order to clarify her information needs. We focus on the task of selecting the next clarification question, given the conversation context. Our method leverages passage retrieval from a background content to fine-tune two deep-learning models for ranking candidate clarification questions. We evaluated our method on two different use-cases. The first is an open domain conversational search in a large web collection. The second is a task-oriented customer-support setup. We show that our method performs well on both use-cases.

Guy Feigenblat, Chulaka Gunasekara, Benjamin Sznajder et al.

In a typical customer service chat scenario, customers contact a support center to ask for help or raise complaints, and human agents try to solve the issues. In most cases, at the end of the conversation, agents are asked to write a short summary emphasizing the problem and the proposed solution, usually for the benefit of other agents that may have to deal with the same customer or issue. The goal of the present article is advancing the automation of this task. We introduce the first large scale, high quality, customer care dialog summarization dataset with close to 6500 human annotated summaries. The data is based on real-world customer support dialogs and includes both extractive and abstractive summaries. We also introduce a new unsupervised, extractive summarization method specific to dialogs.

Odellia Boni, Guy Feigenblat, Guy Lev et al.

We present HowSumm, a novel large-scale dataset for the task of query-focused multi-document summarization (qMDS), which targets the use-case of generating actionable instructions from a set of sources. This use-case is different from the use-cases covered in existing multi-document summarization (MDS) datasets and is applicable to educational and industrial scenarios. We employed automatic methods, and leveraged statistics from existing human-crafted qMDS datasets, to create HowSumm from wikiHow website articles and the sources they cite. We describe the creation of the dataset and discuss the unique features that distinguish it from other summarization corpora. Automatic and human evaluations of both extractive and abstractive summarization models on the dataset reveal that there is room for improvement.

Chulaka Gunasekara, Guy Feigenblat, Benjamin Sznajder et al.

Many conversation datasets have been constructed in the recent years using crowdsourcing. However, the data collection process can be time consuming and presents many challenges to ensure data quality. Since language generation has improved immensely in recent years with the advancement of pre-trained language models, we investigate how such models can be utilized to generate entire conversations, given only a summary of a conversation as the input. We explore three approaches to generate summary grounded conversations, and evaluate the generated conversations using automatic measures and human judgements. We also show that the accuracy of conversation summarization can be improved by augmenting a conversation summarization dataset with generated conversations.

Jatin Ganhotra, Haggai Roitman, Doron Cohen et al.

A frequent pattern in customer care conversations is the agents responding with appropriate webpage URLs that address users' needs. We study the task of predicting the documents that customer care agents can use to facilitate users' needs. We also introduce a new public dataset which supports the aforementioned problem. Using this dataset and two others, we investigate state-of-the art deep learning (DL) and information retrieval (IR) models for the task. Additionally, we analyze the practicality of such systems in terms of inference time complexity. Our show that an hybrid IR+DL approach provides the best of both worlds.

Guy Lev, Michal Shmueli-Scheuer, Achiya Jerbi et al.

Frequently Asked Questions (FAQ) webpages are created by organizations for their users. FAQs are used in several scenarios, e.g., to answer user questions. On the other hand, the content of FAQs is affected by user questions by definition. In order to promote research in this field, several FAQ datasets exist. However, we claim that being collected from community websites, they do not correctly represent challenges associated with FAQs in an organizational context. Thus, we release orgFAQ, a new dataset composed of $6988$ user questions and $1579$ corresponding FAQs that were extracted from organizations' FAQ webpages in the Jobs domain. In this paper, we provide an analysis of the properties of such FAQs, and demonstrate the usefulness of our new dataset by utilizing it in a relevant task from the Jobs domain. We also show the value of the orgFAQ dataset in a task of a different domain - the COVID-19 pandemic.

Odellia Boni, Guy Feigenblat, Doron Cohen et al.

Researchers and students face an explosion of newly published papers which may be relevant to their work. This led to a trend of sharing human summaries of scientific papers. We analyze the summaries shared in one of these platforms Shortscience.org. The goal is to characterize human summaries of scientific papers, and use some of the insights obtained to improve and adapt existing automatic summarization systems to the domain of scientific papers.

Shai Erera, Michal Shmueli-Scheuer, Guy Feigenblat et al.

We present a novel system providing summaries for Computer Science publications. Through a qualitative user study, we identified the most valuable scenarios for discovery, exploration and understanding of scientific documents. Based on these findings, we built a system that retrieves and summarizes scientific documents for a given information need, either in form of a free-text query or by choosing categorized values such as scientific tasks, datasets and more. Our system ingested 270,000 papers, and its summarization module aims to generate concise yet detailed summaries. We validated our approach with human experts.

Benjamin Sznajder, Ariel Gera, Yonatan Bilu et al.

With the growing interest in social applications of Natural Language Processing and Computational Argumentation, a natural question is how controversial a given concept is. Prior works relied on Wikipedia's metadata and on content analysis of the articles pertaining to a concept in question. Here we show that the immediate textual context of a concept is strongly indicative of this property, and, using simple and language-independent machine-learning tools, we leverage this observation to achieve state-of-the-art results in controversiality prediction. In addition, we analyze and make available a new dataset of concepts labeled for controversiality. It is significantly larger than existing datasets, and grades concepts on a 0-10 scale, rather than treating controversiality as a binary label.

Yosi Mass, Haggai Roitman, Shai Erera et al.

We study the use of BERT for non-factoid question-answering, focusing on the passage re-ranking task under varying passage lengths. To this end, we explore the fine-tuning of BERT in different learning-to-rank setups, comprising both point-wise and pair-wise methods, resulting in substantial improvements over the state-of-the-art. We then analyze the effectiveness of BERT for different passage lengths and suggest how to cope with large passages.

Guy Lev, Michal Shmueli-Scheuer, Jonathan Herzig et al.

Currently, no large-scale training data is available for the task of scientific paper summarization. In this paper, we propose a novel method that automatically generates summaries for scientific papers, by utilizing videos of talks at scientific conferences. We hypothesize that such talks constitute a coherent and concise description of the papers' content, and can form the basis for good summaries. We collected 1716 papers and their corresponding videos, and created a dataset of paper summaries. A model trained on this dataset achieves similar performance as models trained on a dataset of summaries created manually. In addition, we validated the quality of our summaries by human experts.

Edward Moroshko, Guy Feigenblat, Haggai Roitman et al.

We suggest a new idea of Editorial Network - a mixed extractive-abstractive summarization approach, which is applied as a post-processing step over a given sequence of extracted sentences. Our network tries to imitate the decision process of a human editor during summarization. Within such a process, each extracted sentence may be either kept untouched, rephrased or completely rejected. We further suggest an effective way for training the "editor" based on a novel soft-labeling approach. Using the CNN/DailyMail dataset we demonstrate the effectiveness of our approach compared to state-of-the-art extractive-only or abstractive-only baseline methods.

Haggai Roitman, Guy Feigenblat, David Konopnicki et al.

We propose Dual-CES -- a novel unsupervised, query-focused, multi-document extractive summarizer. Dual-CES is designed to better handle the tradeoff between saliency and focus in summarization. To this end, Dual-CES employs a two-step dual-cascade optimization approach with saliency-based pseudo-feedback distillation. Overall, Dual-CES significantly outperforms all other state-of-the-art unsupervised alternatives. Dual-CES is even shown to be able to outperform strong supervised summarizers.

Ella Rabinovich, Benjamin Sznajder, Artem Spector et al.

We introduce a weakly supervised approach for inferring the property of abstractness of words and expressions in the complete absence of labeled data. Exploiting only minimal linguistic clues and the contextual usage of a concept as manifested in textual data, we train sufficiently powerful classifiers, obtaining high correlation with human labels. The results imply the applicability of this approach to additional properties of concepts, additional languages, and resource-scarce scenarios.

Tommy Sandbank, Michal Shmueli-Scheuer, Jonathan Herzig et al.

Virtual agents are becoming a prominent channel of interaction in customer service. Not all customer interactions are smooth, however, and some can become almost comically bad. In such instances, a human agent might need to step in and salvage the conversation. Detecting bad conversations is important since disappointing customer service may threaten customer loyalty and impact revenue. In this paper, we outline an approach to detecting such egregious conversations, using behavioral cues from the user, patterns in agent responses, and user-agent interaction. Using logs of two commercial systems, we show that using these features improves the detection F1-score by around 20% over using textual features alone. In addition, we show that those features are common across two quite different domains and, arguably, universal.