19 citations · 38 across the 12 of their papers we have counts for
13 papers
Resilient Combination of Complementary CNN and RNN Features for Text Classification through Attention and Ensembling
Athanasios Giannakopoulos, Maxime Coriou, Andreea Hossmann +2
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 neur…
Expanding the Text Classification Toolbox with Cross-Lingual Embeddings
Meryem M'hamdi, Robert West, Andreea Hossmann +2
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. T…
Interpretable Structure-aware Document Encoders with Hierarchical Attention
Khalil Mrini, Claudiu Musat, Michael Baeriswyl +1
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 sentence…
Embedding Individual Table Columns for Resilient SQL Chatbots
Bojan Petrovski, Ignacio Aguado, Andreea Hossmann +2
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…
Churn Intent Detection in Multilingual Chatbot Conversations and Social Media
Christian Abbet, Meryem M'hamdi, Athanasios Giannakopoulos +4
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 inten…
Diverse Beam Search for Increased Novelty in Abstractive Summarization
André Cibils, Claudiu Musat, Andreea Hossman +1
Text summarization condenses a text to a shorter version while retaining the important informations. Abstractive summarization is a recent development that generates new phrases, r…
Submodularity-Inspired Data Selection for Goal-Oriented Chatbot Training Based on Sentence Embeddings
Mladen Dimovski, Claudiu Musat, Vladimir Ilievski +2
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…
Goal-Oriented Chatbot Dialog Management Bootstrapping with Transfer Learning
Vladimir Ilievski, Claudiu Musat, Andreea Hossmann +1
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 s…
GitGraph - Architecture Search Space Creation through Frequent Computational Subgraph Mining
Kamil Bennani-Smires, Claudiu Musat, Andreea Hossmann +1
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 simp…
Simple Unsupervised Keyphrase Extraction using Sentence Embeddings
Kamil Bennani-Smires, Claudiu Musat, Andreea Hossmann +2
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 amo…
Machine Translation of Low-Resource Spoken Dialects: Strategies for Normalizing Swiss German
Pierre-Edouard Honnet, Andrei Popescu-Belis, Claudiu Musat +1
The goal of this work is to design a machine translation (MT) system for a low-resource family of dialects, collectively known as Swiss German, which are widely spoken in Switzerla…
Dataset Construction via Attention for Aspect Term Extraction with Distant Supervision
Athanasios Giannakopoulos, Diego Antognini, Claudiu Musat +2
Aspect Term Extraction (ATE) detects opinionated aspect terms in sentences or text spans, with the end goal of performing aspect-based sentiment analysis. The small amount of avail…
Unsupervised Aspect Term Extraction with B-LSTM & CRF using Automatically Labelled Datasets
Athanasios Giannakopoulos, Claudiu Musat, Andreea Hossmann +1
Aspect Term Extraction (ATE) identifies opinionated aspect terms in texts and is one of the tasks in the SemEval Aspect Based Sentiment Analysis (ABSA) contest. The small amount of…