Discourse & Dialogue
Parameter-Efficient Abstractive Question Answering over Tables or Text
Pal, Vaishali, Kanoulas, Evangelos, de Rijke, Maarten
A long-term ambition of information seeking QA systems is to reason over multi-modal contexts and generate natural answers to user queries. Today, memory intensive pre-trained language models are adapted to downstream tasks such as QA by fine-tuning the model on QA data in a specific modality like unstructured text or structured tables. To avoid training such memory-hungry models while utilizing a uniform architecture for each modality, parameter-efficient adapters add and train small task-specific bottle-neck layers between transformer layers. In this work, we study parameter-efficient abstractive QA in encoder-decoder models over structured tabular data and unstructured textual data using only 1.5% additional parameters for each modality. We also ablate over adapter layers in both encoder and decoder modules to study the efficiency-performance trade-off and demonstrate that reducing additional trainable parameters down to 0.7%-1.0% leads to comparable results. Our models out-perform current state-of-the-art models on tabular QA datasets such as Tablesum and FeTaQA, and achieve comparable performance on a textual QA dataset such as NarrativeQA using significantly less trainable parameters than fine-tuning.
A Joint Learning Approach for Semi-supervised Neural Topic Modeling
Chiu, Jeffrey, Mittal, Rajat, Tumma, Neehal, Sharma, Abhishek, Doshi-Velez, Finale
Topic models are some of the most popular ways to represent textual data in an interpret-able manner. Recently, advances in deep generative models, specifically auto-encoding variational Bayes (AEVB), have led to the introduction of unsupervised neural topic models, which leverage deep generative models as opposed to traditional statistics-based topic models. We extend upon these neural topic models by introducing the Label-Indexed Neural Topic Model (LI-NTM), which is, to the extent of our knowledge, the first effective upstream semi-supervised neural topic model. We find that LI-NTM outperforms existing neural topic models in document reconstruction benchmarks, with the most notable results in low labeled data regimes and for data-sets with informative labels; furthermore, our jointly learned classifier outperforms baseline classifiers in ablation studies.
Big Data in Customer Sentiment Analysis
Big data enables businesses to thrive and grow by finding hidden patterns in data. Brands are now getting smarter by taking actions based on customer sentiments. Not only brands but also political parties and governments are looking at social sentiments as a valuable resource for growth. With big data, real-time customer sentiment analysis has become possible. Social media has completely changed how people express themselves.
La veille de la cybersécurité
Communication software platform maker Arena – a provider of a Slack-like chat or bot conversation column to the right side of your screen when you're on an ecommerce site – is endeavoring to bring more human understanding to online marketing and sales. That, in turn, works to establish better rapport with potential customers for ecommerce businesses. The San Francisco-based startup's group chat and messaging application framework for B2C enterprises, having earned the attention of investors, yesterday announced a $13.6 million Series A round led by CRV with Craft Ventures, Artisanal Ventures and Vela Partners also participating. A key marketing trend in 2022 is for consumer companies to find ways to move beyond social media and third-party cookies as a way of gaining better direct insights into their users and customers. Five-year-old Arena recognized this early and built a SaaS platform to replace the need for third-party referrals and social networks, CEO and founder Paolo Martins told VentureBeat.
Conversational data platform taps AI for sentiment analysis
We are excited to bring Transform 2022 back in-person July 19 and virtually July 20 - August 3. Join AI and data leaders for insightful talks and exciting networking opportunities. Communication software platform maker Arena – a provider of a Slack-like chat or bot conversation column to the right side of your screen when you're on an ecommerce site – is endeavoring to bring more human understanding to online marketing and sales. That, in turn, works to establish better rapport with potential customers for ecommerce businesses. The San Francisco-based startup's group chat and messaging application framework for B2C enterprises, having earned the attention of investors, yesterday announced a $13.6 million Series A round led by CRV with Craft Ventures, Artisanal Ventures and Vela Partners also participating. A key marketing trend in 2022 is for consumer companies to find ways to move beyond social media and third-party cookies as a way of gaining better direct insights into their users and customers.
Sentiment Analysis using VADER [mathematics behind it included]
Let's start analyzing the sentiment using VADER: Here, SentimentIntensityAnalyzer() is an object and polarity scores is a method which will give us scores of the following categories: Positive, Negative, Neutral, Compound . Above text is 67.7% Positive, 0% Negative, 32.3% Neutral, while the compound score is 44.04% The compound score is the sum of positive, negative & neutral scores which is then normalized between -1(most extreme negative) and 1 (most extreme positive). How Positive, Negative, Neutral and Compound Scores are Calculated?
Artificial Intelligence: Using Advanced Analytics to Detect Conduct and Patterns of Behavior
Artificial intelligence (AI) adoption has been largely accepted in the legal community, as many have realized the value of technology that can detect relevant content and produce better outcomes. Incorporating AI into document review workflows or using insights to inform case strategy is transformative and drives better results. From government requests to civil litigation and internal investigations, high profile and fast-moving matters require efficient processes. Deploying technology strategically will help teams to identity key documents and themes early in the case and manage the assessment and review of data efficiently. The continued evolution of AI tools, such as the ability to detect conduct and behavior through sentiment analysis and pattern processing, will further assist with investigatory compliance but can also be used proactively.
Market Segmentation in the Emoji Era
Ishaan and Elizabeth, both graduate students in business, are attending a marketing strategy lecture at a business school in the Northeast. While learning about the principles of market segmentation, Ishaan texts "outdated" followed by three thinking--face emojis to Elizabeth. He wonders how demographic-, geographic-, or psychographic-based segmentation--the topic of the lecture--can help his family's franchise restaurant deal with the hundreds of sometimes-not-so-positive online reviews and social media posts. Meanwhile, Elizabeth hopes that the fast-food restaurant where she ordered her lunch understands that she now belongs to the segment of'extremely displeased' customers. Earlier, she used the restaurant's new app to order a burrito without cheese and sour cream, only to discover that the meal included both offending ingredients. Her lunch went straight into the trash can and she angrily tweeted her disappointment to the restaurant. Elizabeth replies to Ishaan's text, "that is so passé," followed by a face_with_ rolling_eyes. This simple vignette illustrates an important point. Organizations of every size are challenged with capitalizing on enormous amounts of unstructured organizational data--for instance, from social media posts--particularly for applications such as market segmentation. The purpose of this article is to give the reader an idea of the challenges and opportunities faced by businesses using market segmentation, including the impacts of big data.
What is a Sentiment Analysis Tool and How Do You Use it?
The words we use and the tone we inflect paint a picture of the ideas we're expressing. Whether in an online meeting, conducting a remote sales presentation, or hosting a live webinar, the emotions that come through can offer key insights. Video conferencing with Sentiment Analysis provides businesses with the unparalleled opportunity to gain a deeper understanding of what's being said amongst prospects, clients, and employees during online meetings and syncs. Intelligent emotion-reading algorithms pull out the meaning behind the text as a way to explore participant satisfaction and so much more. Here's how using video conferencing and Sentiment Analysis can work together to identify and quantify key emotional indicators and help you get a more detailed understanding of what your audience needs.
A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots
Zhang, Sai, Hu, Yuwei, Wu, Yuchuan, Wu, Jiaman, Li, Yongbin, Sun, Jian, Yuan, Caixia, Wang, Xiaojie
A slot value might be provided segment by segment over multiple-turn interactions in a dialog, especially for some important information such as phone numbers and names. It is a common phenomenon in daily life, but little attention has been paid to it in previous work. To fill the gap, this paper defines a new task named Sub-Slot based Task-Oriented Dialog (SSTOD) and builds a Chinese dialog dataset SSD for boosting research on SSTOD. The dataset includes a total of 40K dialogs and 500K utterances from four different domains: Chinese names, phone numbers, ID numbers and license plate numbers. The data is well annotated with sub-slot values, slot values, dialog states and actions. We find some new linguistic phenomena and interactive manners in SSTOD which raise critical challenges of building dialog agents for the task. We test three state-of-the-art dialog models on SSTOD and find they cannot handle the task well on any of the four domains. We also investigate an improved model by involving slot knowledge in a plug-in manner. More work should be done to meet the new challenges raised from SSTOD which widely exists in real-life applications. The dataset and code are publicly available via https://github.com/shunjiu/SSTOD.