Zobrazeno 1 - 10
of 56
pro vyhledávání: '"Rokhlenko, Oleg"'
Digital assistants have become ubiquitous in e-commerce applications, following the recent advancements in Information Retrieval (IR), Natural Language Processing (NLP) and Generative Artificial Intelligence (AI). However, customers are often unsure
Externí odkaz:
http://arxiv.org/abs/2405.01738
Autor:
Fetahu, Besnik, Cohen, Nachshon, Haramaty, Elad, Lewin-Eytan, Liane, Rokhlenko, Oleg, Malmasi, Shervin
Voice assistants have become ubiquitous in smart devices allowing users to instantly access information via voice questions. While extensive research has been conducted in question answering for voice search, little attention has been paid on how to
Externí odkaz:
http://arxiv.org/abs/2404.06017
Conversational Task Assistants (CTAs) guide users in performing a multitude of activities, such as making recipes. However, ensuring that interactions remain engaging, interesting, and enjoyable for CTA users is not trivial, especially for time-consu
Externí odkaz:
http://arxiv.org/abs/2404.06659
Autor:
Patwa, Parth, Filice, Simone, Chen, Zhiyu, Castellucci, Giuseppe, Rokhlenko, Oleg, Malmasi, Shervin
Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks. In-Context Learning (ICL) typically achieves better accuracy than the 0-shot setting, but it pays in terms of efficiency,
Externí odkaz:
http://arxiv.org/abs/2404.02422
E-commerce customers frequently seek detailed product information for purchase decisions, commonly contacting sellers directly with extended queries. This manual response requirement imposes additional costs and disrupts buyer's shopping experience w
Externí odkaz:
http://arxiv.org/abs/2401.09785
Many Natural Language Generation (NLG) tasks aim to generate a single output text given an input prompt. Other settings require the generation of multiple texts, e.g., for Synthetic Traffic Generation (STG). This generation task is crucial for traini
Externí odkaz:
http://arxiv.org/abs/2311.12534
E-commerce product catalogs contain billions of items. Most products have lengthy titles, as sellers pack them with product attributes to improve retrieval, and highlight key product aspects. This results in a gap between such unnatural products titl
Externí odkaz:
http://arxiv.org/abs/2310.16361
Autor:
Fetahu, Besnik, Faustini, Pedro, Castellucci, Giuseppe, Fang, Anjie, Rokhlenko, Oleg, Malmasi, Shervin
The adoption of voice assistants like Alexa or Siri has grown rapidly, allowing users to instantly access information via voice search. Query suggestion is a standard feature of screen-based search experiences, allowing users to explore additional to
Externí odkaz:
http://arxiv.org/abs/2310.17034
We present MULTICONER V2, a dataset for fine-grained Named Entity Recognition covering 33 entity classes across 12 languages, in both monolingual and multilingual settings. This dataset aims to tackle the following practical challenges in NER: (i) ef
Externí odkaz:
http://arxiv.org/abs/2310.13213
Customers interacting with product search engines are increasingly formulating information-seeking queries. Frequently Asked Question (FAQ) retrieval aims to retrieve common question-answer pairs for a user query with question intent. Integrating FAQ
Externí odkaz:
http://arxiv.org/abs/2306.03411