Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Baeriswyl, Michael"'
Autor:
Giannakopoulos, Athanasios, Coriou, Maxime, Hossmann, Andreea, Baeriswyl, Michael, Musat, Claudiu
State-of-the-art methods for text classification include several distinct steps of pre-processing, feature extraction and post-processing. In this work, we focus on end-to-end neural architectures and show that the best performance in text classifica
Externí odkaz:
http://arxiv.org/abs/1903.12157
Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the artificial in
Externí odkaz:
http://arxiv.org/abs/1903.09878
We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentences into blocks of increasing complexity. Our Structure Tree-LSTM implem
Externí odkaz:
http://arxiv.org/abs/1902.09713
Most of the world's data is stored in relational databases. Accessing these requires specialized knowledge of the Structured Query Language (SQL), putting them out of the reach of many people. A recent research thread in Natural Language Processing (
Externí odkaz:
http://arxiv.org/abs/1811.00633
Autor:
Abbet, Christian, M'hamdi, Meryem, Giannakopoulos, Athanasios, West, Robert, Hossmann, Andreea, Baeriswyl, Michael, Musat, Claudiu
We propose a new method to detect when users express the intent to leave a service, also known as churn. While previous work focuses solely on social media, we show that this intent can be detected in chatbot conversations. As companies increasingly
Externí odkaz:
http://arxiv.org/abs/1808.08432
Text summarization condenses a text to a shorter version while retaining the important informations. Abstractive summarization is a recent development that generates new phrases, rather than simply copying or rephrasing sentences within the original
Externí odkaz:
http://arxiv.org/abs/1802.01457
Spoken language understanding (SLU) systems, such as goal-oriented chatbots or personal assistants, rely on an initial natural language understanding (NLU) module to determine the intent and to extract the relevant information from the user queries t
Externí odkaz:
http://arxiv.org/abs/1802.00757
Goal-Oriented (GO) Dialogue Systems, colloquially known as goal oriented chatbots, help users achieve a predefined goal (e.g. book a movie ticket) within a closed domain. A first step is to understand the user's goal by using natural language underst
Externí odkaz:
http://arxiv.org/abs/1802.00500
The dramatic success of deep neural networks across multiple application areas often relies on experts painstakingly designing a network architecture specific to each task. To simplify this process and make it more accessible, an emerging research ef
Externí odkaz:
http://arxiv.org/abs/1801.05159
Keyphrase extraction is the task of automatically selecting a small set of phrases that best describe a given free text document. Supervised keyphrase extraction requires large amounts of labeled training data and generalizes very poorly outside the
Externí odkaz:
http://arxiv.org/abs/1801.04470