#nlu

[eternalsunshinesss]

lo telling garrison he wished he had glaucoma so he couldn't see his batman tattoo on his neck is so on brand for him

[theprobeindia]

NLU Delhi: Another Student Death, 3 Deaths in a Month

NLU Delhi: 3 student deaths in September alone have tragically unfolded at the National Law University Delhi, prompting concerns about stude

[virginmiri99]

Literally crying with laughter over the memory that Love Live tried to name one of their units BEAT CATS

[a-dianthus-swaying-with-the-wind]

Relationship Status: Emotionally Attached to NLSIU

:)

[rantylawblr]

Hey hey! Just saw that you are an Indian lawblr. I'm currently preparing for CLAT and AILET 2021. Do you have some tips for the exams and the things that I shouldn't avoid doing in the last months of my preparation? How is law school treating you so far? You are so inspiring and meticulous. All the best for your internships and make sure that you take out some time for yourself.

-🍩anon

Heyy, first off, thank you soo much for the compliments, you're too kind♥️

So for CLAT and AILET there are some common things that will help in both, but both exams need completely different prepping styles.

COMMON TIPS

Read the newspaper daily

Focus on solving as many mock tests as you can, but make sure you review each one immediately after doing them, and consistently review the past papers as you keep giving mocks. Also aim to get 5 marks more than you got last time

Read up on legal gk, it will not only help you in the gk section but will also help in the legal section

Give the mock at the same time as the exam. If CLAT is at 2pm, give the mock at 2pm every week, same with AILET

TIPS FOR CLAT

Best way to prep is to keep giving papers. You may get crappy scores and that can be disheartening, but don't stop giving papers

Read, read, read. CLAT tests your reading speed as much as your comprehension skills. Try reading the newspaper every day and actively increasing your reading speed

Do weekly and monthly gk modules. You'll find them on telegram groups made for CLAT prep

Don't panic in the exam. You'll do well, don't worry. I'm assuming the paper is offline this time, so practice with an omr sheet while wearing a mask so that you get accustomed to it.

TIPS FOR AILET

Do past years papers immediately, don't leave it off for last minute. Career launcher and clat prep have very easy AILET mocks which can give you a false sense of confidence. Do past years papers so that you know what to expect

AILET is 150 qs in just 90 minutes. AILET tests your speed. So practice as much as you can and make sure you don't waste time on questions you can't answer

Maths is one section where you can maximize your score. Even if you feel you are bad at it, maths is a learnable skill. You learn one type of questions, you maximise your chances of getting into NLUD by one mark, and believe it or not, that is a lot

AILET wants you to panic, don't. Dedicate a certain amount of time to every section. Do mocks and see how much time you need for every section and draw out a map. In the exam, one eye should be on the paper and the other one on your watch

A month before your paper, try to maximise as many concepts you can learn. The more area you cover, the more chances you have at getting the answers right. I didn't clear AILET and I was only getting a lower NLU with my CLAT score so I'm telling you to not make the same mistakes I did.

My college is five times more strenuous than any NLU. We have 9 subjects in a semester and no end-sem break as our semester started late. I'd say give SLAT too since SLS Pune is a good university if you don't get into top 7 NLUs.

All the very best for CLAT, I hope you crack it and get to your dream university. Even if you don't, it isn't the end of the world. I have relatives who passed out from universities that don't have a good reputation on the market but are now working in some of India's top tier law firms. Be gentle with yourself, times are hard and you shouldn't jeopardize your mental health for this. CLAT is an exam that can be given every year, so you have another shot at this even if you don't get this one right. But I'll hope that you get into a good NLU in the first try because I recognise that CLAT prep is very stressful, and I'm happy I am out of that phase of my life.

Good luck 🥰

[iiericscott]

Finally some treats for you guys. 😊

[nlprocby]

Ekaterina Kruchinina: NLP is on the road

Hi Katja, let me ask about your professional experience: how did you find your interest in computational linguistics and developed through it?

Hi, I started my university studies in Rostov-on-Don, Russia. My subject was German language and literature, with emphasis on literature and translation studies. I studied for 2 years and then continued my studies at the University of Cologne in Germany. I started there from the first year, as in Germany similar program starts two years later than in Russia. Additionally, I took another topic of interest, French, as I was keen to learn it. But after a couple of years, I realized I had high interest in linguistics, especially after taking courses in modern linguistics and formal syntax in university. But honestly, I was not aware of computational linguistics at that point. One day I found that there is a study subject ‘Linguistic data processing’ at the University of Cologne and I joined the class after a talk with a professor. After a couple of years I started to work at the department, and of course, it was a good time to learn programming, which I really enjoyed. At that point, I realized much more about computer science. We studied Java as a first language, though many in the field start now with Python. I remember we programmed a search engine over a summer.

It reminds me a talk to Natalia Karlova-Burbonus. Natalia has a very similar story: going from interest to the German language to Computational Linguistics in Germany. 

My next question whether you remember your first project or last at that time.

Yes, my first job was related to exploring self-organizing maps (so-called Kohonen nets). I don’t remember all project details, but we worked on syntactic dependency structures and tried to represent it in Kohonen maps for the German language. After we tried different IE approaches, text classification and run other experiments. That was a great time for learning. I had done an internship during my studies as well. It was in Paris, at a software company called Arisem, so I could also practice my French. It was the B2B company which focused on semantic search, dedicated one, including crawling. Then I came back to finish my master thesis.

What was master thesis topic about?

It was about the numerical representation of text corpora including how can we represent corpora for classification. I tried LSA that time also, but the topic was like a meta-analysis of different approaches.

Then Ph.D. happened to you.

Yes, at some point after I decided to stay in academia, to do a Ph.D. I went to Jena university, a big move from Cologne. But it was not only a Ph.D. position but a research assistant position in a European project BootStrep. The focus was on biomedical text processing: text mining in biology, semantic search over the publication of medicine/bio published research. There is a huge database PubMed which has millions of citations and which continue to grow quickly. And, obviously, a problem for a biologist is to find relevant information in such an enormous amount of data. So, preprocessing of data, named entity recognition (NER), normalization of extracted entities and relation extraction, are of particular interest here. My personal focus was on relation extraction, e.g. how a researcher describes gene expression processes.

Did you have medicine ontology for named entities?

We had a couple of Ph.D. students, which helped to develop the ontology in our group, of course using terminology from established sources. It reminds also what else was great about the project group: everybody had a specific skill-set and the tasks were assigned well and according to a person focus: somebody worked on NER and fast annotation using active learning, someone - preprocessing, another person cared about the ontology, search engines. I focused on detection of events and relations. It was a great experience to have such a skilled team.

Do you remember a day when you realized that you need to leave the project?

I continued working on the project during my Ph.D. I started later and the main result I would say was my participation in BioNLP 2009 shared task, where I got a second place once evaluated. After that, I elaborated on my topic. On 2012 I’ve completed my Ph.D. and started to look for a new challenge. I could have stayed in the Biomedical domain, but I was open to other topics also as I studied a lot while reading about different topics, including dependency parsing, collecting data in general. Then I found an open position at Nuance, there were not many at that moment in Germany. So, I became one of the first joining the NLU (Natural Language Understanding) team and moved to Aachen, which I also like as it’s close to Cologne.

How many people in Nuance NLU team now?

There are about 60 people in Automotive cloud NLU, which includes Aachen, Montreal, and Burlington offices and people working remotely. Company-wide there are more NLU people (100+).

NLU is a challenge by the name. So, tell us, what do you do and how do you overcome the challenges?

First, our main application area is an automotive domain. Our team works at the moment on a classification of user intents and named entity recognition. So, you have one-two step dialog, one-shot query, which requires a classification of the intent. I’d say that it’s now for the navigation system, office system in the car.

Well, actually from my experience I remember around a year ago participating in a hackathon organized by Nuance NLU system. And if I recall correctly, for NLU system you need to provide not only intents but also labels, concepts to train it, am I right?

Yes, you also need to provide concepts which need to be detected.

Would be nice if you can share an example of a use-case.

Ok, the simple example is a question about the weather: “What will be the weather tomorrow in Trento?” So, we need to recognize the intent: weather, the date: tomorrow, the location: Trento. Another example, you can: would it be sunny tomorrow in Trento? So, we do have multiple steps, relying on statistical models and many features, like named entities, and lexical information (keywords sun, weather, etc). Both are possible: you can do intent classification first and then named entities or the other way around.

As I remember from the mentioned hackathon, you have two interfaces: speech and text.

You are right, but it’s another project, it’s Nuance MIX you mean, our project. In our solution, we provide an ability to type, use speech interface and handwriting.

You haven’t told us a lot of internal details yet ;) Ok, what languages do you support?

We support over 20 languages for Automotive cloud NLU, additionally to major European languages we have Czech, Swedish, Turkish, for Asia - Japanese, Cantonese, Mandarin, and others.

It leads me to the question: do you reuse models available or develop all yourself?

We develop all internally. For example, we have developers graduated from the Charles University in Prague, who work on Czech support.

That’s an interesting story about computational linguistics in Czech, though I wouldn’t call it as widely spoken as others in Europe, Charles University has two or three groups which develop universal dependencies for the language, though some more representative languages have none.

Alright, what do you work on currently?

It’s mostly improving accuracy for automotive-related projects (for features like navigation, weather search, and more), which includes adding of data. Also embedding extensions, and for that case, the main challenge is the proper evaluation, which helps to avoid a degradation in quality. We worked on a hybrid solution: embedded NLU and cloud NLU. As we have some overlap, we need to split the responsibilities in a clear way. We need to work on confidence for prediction. We are facing AI as well, I mean complex request, e.g. a user could ask: find me a good restaurant and a parking slot around. So, a combination of intents brings an interesting challenge.

So, let’s come back quickly to language sources: do you plan to release the language resources to the language developers community.

I have no insight regarding this from the business.

It is a company which was bought by Microsoft, Maluuba, which developed an evaluation dataset, NewsQA. So, releasing an evaluation dataset can be a good step from Nuance. Thank you for the talk and I wish you good luck with a challenge of multiple intents.

Thanks, I was happy to share the knowledge and what we do.

Image 1 is published with an agreement of K. Kruchinina

Author: @yauhen_info for @nlprocby

[iiericscott]

https://lnk.to/41Daysinlithonia

Some new tunes for you.

Eric Scott - 41 Days in Lithonia

Listen to 41 Days in Lithonia by Eric Scott.