#questionanswering — Public Fediverse posts

👥 Justus-Jonas Erker (UKP Lab/Technische Universität Darmstadt), Nils Reimers (Cohere), Iryna Gurevych (UKP Lab/Technische Universität Darmstadt)

See you at Hashtag#EACL2026 in Rabat 🕌!

#UKPLab #NLP #NLProc #InformationRetrieval #DenseRetrieval #MultiHop #FactChecking #QuestionAnswering #RAG

📝 "PDF-Based Question Answering with Amazon Bedrock and Haystack"

👤 Bilge Yucel (@bilgeyucel)

🔗 https://medium.com/deepset-ai/pdf-based-question-answering-with-amazon-bedrock-and-haystack-dc234003ffd8?source=rss-dacda5cb969d------2

#pyladies #python #amazonwebservices #haystack #amazonbedrock #questionanswering #opensearch

#TechNews: #Qwen Releases New #VisionLanguage #LLM Qwen2-VL 🖥️👁️

After a year of development, #Qwen has released Qwen2-VL, its latest #AI system for interpreting visual and textual information. 🚀

Key Features of Qwen2-VL:

1. 🖼️ Image Understanding:

Qwen2-VL shows performance on #VisualUnderstanding benchmarks including #MathVista, #DocVQA, #RealWorldQA, and #MTVQA.

2. 🎬 Video Analysis:

Qwen2-VL can analyze videos over 20 minutes in length. This is achieved through online streaming capabilities, allowing for video-based #QuestionAnswering, #Dialog, and #ContentCreation. #VideoAnalysis

3. 🤖 Device Integration:

The #AI can be integrated with #mobile phones, #robots, and other devices. It uses reasoning and decision-making abilities to interpret visual environments and text instructions for device control. #AIAssistants 📱

4. 🌍 Multilingual Capabilities:

Qwen2-VL understands text in images across multiple languages. It supports most European languages, Japanese, Korean, Arabic, Vietnamese, among others, in addition to English and Chinese. #MultilingualAI

This release represents an advancement in #ArtificialIntelligence, combining visual perception and language understanding. 🧠 Potential applications include #education, #healthcare, #robotics, and #contentmoderation.

https://github.com/QwenLM/Qwen2-VL

MBZUAI is looking to recruit postdoctoral researchers (https://mbzuai.ac.ae/) to work on #Arabic #NLP. The ideal candidate should be particularly interested in #Dialectal Arabic, Arabic #LLMs, #QuestionAnswering, but candidates with experience on Arabic NLP in general will also be considered.

To apply, please write directly to Preslav Nakov:
[email protected]

🎉 We developed a prompting method for improved (and more human-like) LLM reasoning and applied it to hybrid question answering, surpassing the GPT-4 baseline. 🚀

Thanks to my co-authors Dhananjay, Preetam and @SaharVahdati ! We'll present the work at #ACL2024 in Bangkok this year where I hope I'll be able to meet a few of you.

Blog post: https://linkedin.com/pulse/beyond-boundaries-human-like-approach-question-over-sources-lehmann-dhtne

Paper: https://www.amazon.science/publications/beyond-boundaries-a-human-like-approach-for-question-answering-over-structured-and-unstructured-information-sources

#AI #LLMs #QuestionAnswering #ConversationalAI

Very biased, but also very excited about Khyathi Chandu's presentation of our new proposed shared task at #INLG2023: "LowReCorp: The Low-Resource NLG Corpus Building Challenge"

Join the #SharedTask during the coming year if you want to use our UI or task design to collect #NLG data for #LowResourceLanguages!

#DialogueSummarization #QuestionAnswering #ResponseGeneration

At #acl2023nlp in Toronto, we present our work on directly retrieving facts from a knowledge graph without explicit entity & relation linking. Work with Jinheon Baek, Alham Fikri and Sung Ju Hwang.

Paper link: https://arxiv.org/pdf/2305.12416.pdf

#QuestionAnswering #LLMs #KnowledgeGraphs

📢📢 NEW BLOG POST FROM SPONSOR

We interviewed The QA Company, and asked them a few questions regarding their main products, their role in the Semantic Web Community, and about their vision.

Read the interview here: https://semantics-org.github.io/page/news?page=2023-07-01a

#semanticsconf #questionanswering

Updates on the #Qur'an #QuestionAnswering Shared tasks (Qur'an QA 2023) organized at WANLP 2023 Conference on December 7th, 2023 are available here:

https://sites.google.com/view/quran-qa-2023/home

You can find information on the two tasks and register until August 10th, 2023 on the website.

Everybody talks about #LLMs and #ChatGPT. A task they fail big is described in this article in Nature
@[email protected]: https://www.nature.com/articles/s41598-023-33607-z

"The SciQA Scientific #QuestionAnswering Benchmark for Scholarly Knowledge" with
@[email protected],
@[email protected],
@[email protected] et al.

If you think you can develop a QA system performing better than plain LLMs consider participating in Scholarly QALD
@[email protected]

https://kgqa.github.io/scholarly-QALD-challenge/2023/

@astatide yeah there are good ways to use these models, but trying to generate when you want to search is definitely doing it wrong.

Generative models are drunk geniuses - they've seen all the knowledge in the world! But they're also drunk af. Like a modern oracle of Delphi, kinda!

But yes, search is: query understanding, then broad retrieval, then ranking, and finally returning _references_ which you can consult.

Even verging into #QuestionAnswering requires care, to avoid spewing nonsense.

Hello world! Here's my #introduction

I’m an #NLP #PhD student at #CMU and a Student Researcher at #Google, interested in #AI for {Language, Knowledge, Culture, Society}

Currently I work on #NLProc with applications to #ComputationalSocialScience, #ScienceOfScience, #QuestionAnswering, & #ScholarlyNLP.

I'm often inspired by #libraries, #wikis, #memex, etc -- long term I'd like to study & build interactive #KnowledgeAugmentation that supports discovery, agency, access, community, and trust.

In the past I've approached this in different ways, either collaborating on a #psycholinguistic experiment on #ReferringExpression production (https://aclanthology.org/W17-3522/) or #crowdsourcing variations on an existing #corpus (https://davehowcroft.com/publication/2017-08_interspeech_extended-sparky-restaurant-corpus/).

At the moment, I'm working to collect #dialogue/s grounded in a given information source (a description of a museum exhibit) to develop a dataset for training #ScottishGaelic / #Gàidhlig #chatbots for #QuestionAnswering (https://blogs.ed.ac.uk/garg/2022/08/23/scottish-gaelic-chatbots-for-museum-exhibits/).