6 Best NLP Tools: AI Tools for Content Excellence

Salesforce Unveils A Big Advance In Natural Language Processing

Just a few years ago, asking your phone a question to find information on the internet was, well, pretty much out of the question because computers weren't all that great at understanding phrases outside a narrow few.

Now, thanks to advances in machine learning, we think nothing of Google or Siri answering our queries with pretty good responses. But this progress has been painstaking, requiring intensive training on very specific natural language processing tasks such as translating text into speech, analyzing sentiment or understanding pronoun references.

That's the problem Salesforce.Com Inc. Researchers think they've started to solve. Today, they're releasing a paper that outlines a way to use a single model that can handle 10 separate NLP tasks at once. The paper is essentially a challenge, called the Natural Language decathlon or decaNLP for short, paired with a "multitask question answering network" or MQAN model that jointly learns all 10 tasks at once.

"Our model is like the Swiss Army Knife for NLP," Richard Socher (pictured), chief scientist at Salesforce, said in an interview. In other words, researchers and developers essentially can use one tool instead of having to use one for each of those tasks, which have required hypercustomized models that can't be used for any other task.

Ultimately, the result could be much more capable chatbots, for instance, that can converse more naturally with people.

Socher drew an analogy to ImageNet, the database of labeled images he helped develop that is widely seen as kicking off the revolution in deep learning that led to breakthroughs in image recognition. But there's no one task that similarly defines natural language processing, which encompasses things such as machine translation, natural language inference, goal-oriented dialogue and pronoun resolution. "In NLP, there isn't really a single task where all researchers think if you make progress on it, it will improve NLP overall," Socher said.

The approach of the Salesforce researchers, who also include Bryan McCann, Nitish Shirish Keskar and Caiming Xiong, was to pose each of those tasks as a question answering problem. "Question answering is so broad — you can literally ask any question — it gives you the flavor of a single model for several tasks," Socher explained.

MQAN allows for what is known as "zero-shot" learning, which means the model can handle tasks it hasn't seen before or been trained to do. "You're applying it to a completely new task, which has never been done before," McCann said. "Most models are not robust to rephrasing or slight variations in meaning. Ours is. Even if it's never seen anything like that, it can do it."

To bring it down to earth, he added, chatbots could do a much better job with phrases that aren't precisely what it has already learned, more like how people converse.

Salesforce is open-sourcing the model, so "people can pick up right where we left off," said McCann.

Salesforce provided a perspective from noted AI researcher Yoshua Bengio, professor for the Department of Computer Science and Operations Research at the University of Montreal, who has worked with Socher in the close-knit machine learning community.

"Since I started working on word embeddings for representing natural language almost twenty years ago, my goal was that the same representations should be used for all natural language tasks," he said. "The idea in this paper to represent all of these tasks as question-answering is crucial, but it was not enough. The authors came up with the natural language decathlon to define a benchmark for this objective, and introduced architectural innovations which finally made this dream possible."

Photo: Salesforce.Com Your vote of support is important to us and it helps us keep the content FREE. One click below supports our mission to provide free, deep, and relevant content.   Join our community on YouTube Join the community that includes more than 15,000 #CubeAlumni experts, including Amazon.Com CEO Andy Jassy, Dell Technologies founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many more luminaries and experts.

"TheCUBE is an important partner to the industry. You guys really are a part of our events and we really appreciate you coming and I know people appreciate the content you create as well" – Andy Jassy

THANK YOU

Salesforce Research Creates Swiss Army Knife For Natural Language Processing

Salesforce Research has created a natural language processing architecture that can handle multiple models and tasks. Typically, natural language processing (NLP) has a model for each function such as translation, sentiment analysis and question and answer.

The research, led by Salesforce Chief Scientist Richard Socher, revolves around a challenge dubbed Natural Language Decathalon (decaNLP). The challenge spans 10 tasks--question answering, machine translation, summarization, natural language inference, sentiment analysis, semantic role labeling, relation extraction, goal-oriented dialogue, database query generation, and pronoun resolution--and feeds into a system that jointly learns.

Think of decaNLP as a Swiss Army Knife for natural language processing. If NLP is customized repeatedly it won't scale. Salesforce was looking for a general purpose NLP approach where every task is transformed into a question answering format and trained jointly.

Socher said the approach melds deep learning and NLP and moves the discussion to one that revolves around an meta architecture. He added that an architecture approach can also be used to prevent model sprawl as NLP functions are layered together.

"This is a project that can have immediate useful applications because it's a model that is a single deploy and easier to maintain," said Socher. "We're bringing a bunch of tools together."

Salesforce is likely to use the decaNLP approach in its product roadmap for Einstein and its various clouds.

The decaNLP is combined with a multitask question answering network that jointly learns all tasks without any specific model. The network also allows for adaptation by completing new tasks through related descriptions.

Here's a diagram of the multitask question answering network.

And finally, Salesforce Research came up with code for processing datasets, training and evaluating models and ultimately coming up with a score called the decaScore.

NLP trained on the decaNLP system will in theory be better equipped to provide a framework for chat bots as well as any information in a customer service exchange.

Attention Uses Natural Language Processing To Help Sales Reps Sell Faster

Updating CRMs after each call is an important task for sales representatives, but it means a lot of administrative work that takes time away from actually selling. Attention wants to fix that with its sales assistant, which uses AI tech and natural language processing to automatically fill in CRMs after calls and draft follow-up emails.

The New York-based startup announced today it has raised $3.1 million led by Eniac Ventures, with participation from institutional investors Frst, Liquid2 Ventures, Maschmeyer Group Ventures and Ride Ventures. The round also included the founders of Ramp, Pawp, Truework and CB Insights.

Attention was founded in September 2021 by CEO Anis Bennaceur and CTO Matthias Wickenburg. The two met while running Swipecast and Mixer, competing job platforms for creative professionals. After five years of being rivals, the two got coffee and realized they face many of the same challenges with sales, like needing to constantly update Salesforce and onboarding new sales reps as quickly as possible.

"After many back-and-forths, we decided to work together," said Bennaceur. "I had hundreds of conversations with sales leaders and junior sales reps, asking about their pain points, digging into potential desired solutions, and continuously iterating, while Matthias would build those solutions in parallel. After numerous iterations, we knew that we were onto something."

One of the things Attention helps with is CRM hygiene, which means making sure CRM software is updated with clean and accurate data. Bennaceur explains this is important because chief revenue officers and vice presidents of sales rely on their organization's CRM to track interactions with customers, manage leads and analyze sales data. This lets them make decisions on how to increase revenue.

But there are several barriers to maintaining CRM hygiene. For one thing, it's a lot of administrative work for sales reps and takes time away from actually selling. It's also easy to miss data when sales reps leave their jobs or pass accounts onto other reps. This results in lost leads and customer attrition. Finally, without any way to track what is said during sales calls, revenue leaders have a harder time deciding how to advance potential deals.

Attention fixes this by automatically exporting data from calls into CRMs. For example, if a sales team uses the MEDDIC sales methodology, a framework of questions that includes six steps, Attention knows if each step has been covered in a conversation, and exports that information into the relevant Salesforce or HubSpot fields. This reduces the amount of busywork sales reps need to do, while giving revenue leaders more insight into sales leads and revenue opportunities.

By using natural language processing, Attention is also able to identify content for sales coaching in calls. During a call, it displays battlecards in real-time to help sales reps figure out what to say. "Let's say a prospect asks you a question on how to compare your competitor on a specific capability. A battlecard would contain the elements to answer that question appropriately, and appears on your screen during your conversation," says Bennaceur.

To increase deal velocity, or the speed at which a sales organization is able to negotiate and sign contracts, sales teams need to send a lot of emails, quickly. But the followup email templates they often rely on are impersonal, while catered emails sometimes leave out important data, says Bennaceur. Attention is able to draft emails after calls based on what was said during the conversation. For example, a sales rep can ask Attention to "write an email recapping our conversation. Mention our prospect's challenges and how our product can help them. And talk about next steps."

Attention's competitors include Gong and Chorus, both of which analyze customer conversations. Bennaceur says that Attention's advantage is its ability to flexibly understand conversations, display real-time prompts during calls and provide A/B testing for its coaching. "We haven't seen any of these players flexibly export conversations into CRMs, and this is a strong edge that we currently have," he said.

In a statement about the funding, Eniac Ventures' Hadley Harris said, "We're thrilled to partner with Anis and Matthias as they leverage the latest developments in AI generation and natural language understanding to superpower sales organizations. We love working with repeat founders and couldn't be happier with the strong pull they're already getting from the market."

Avoid 3 common sales mistakes startups make during a downturn

Catherine Shu covered startups in Asia and breaking news for TechCrunch. Her reporting has also appeared in the New York Times, the Taipei Times, Barron's, the Wall Street Journal and the Village Voice. She studied at Sarah Lawrence College and the Columbia Graduate School of Journalism.

Disclosures: None

---