Related papers: Improving Opinion-Target Extraction with Character…
Target Speaker Extraction (TSE) uses a reference cue to extract the target speech from a mixture. In TSE systems relying on audio cues, the speaker embedding from the enrolled speech is crucial to performance. However, these embeddings may…
Assessing the degree of semantic relatedness between words is an important task with a variety of semantic applications, such as ontology learning for the Semantic Web, semantic search or query expansion. To accomplish this in an automated…
Sentiment analysis is one of the well-known tasks and fast growing research areas in natural language processing (NLP) and text classifications. This technique has become an essential part of a wide range of applications including politics,…
Robust speech emotion recognition relies on the quality of the speech features. We present speech features enhancement strategy that improves speech emotion recognition. We used the INTERSPEECH 2010 challenge feature-set. We identified…
We investigate the integration of word embeddings as classification features in the setting of large scale text classification. Such representations have been used in a plethora of tasks, however their application in classification…
Most pretrained language models rely on subword tokenization, which processes text as a sequence of subword tokens. However, different granularities of text, such as characters, subwords, and words, can contain different kinds of…
Telecom services are at the core of today's societies' everyday needs. The availability of numerous online forums and discussion platforms enables telecom providers to improve their services by exploring the views of their customers to…
We consider the task of fine-grained sentiment analysis from the perspective of multiple instance learning (MIL). Our neural model is trained on document sentiment labels, and learns to predict the sentiment of text segments, i.e. sentences…
Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…
Neural network methods have achieved great success in reviews sentiment classification. Recently, some works achieved improvement by incorporating user and product information to generate a review representation. However, in reviews, we…
When dealing with text data containing subjective labels like speaker emotions, inaccuracies or discrepancies among labelers are not uncommon. Such discrepancies can significantly affect the performance of machine learning algorithms. This…
Distributed word representations are very useful for capturing semantic information and have been successfully applied in a variety of NLP tasks, especially on English. In this work, we innovatively develop two component-enhanced Chinese…
In this paper, we use several techniques with conventional vocal feature extraction (MFCC, STFT), along with deep-learning approaches such as CNN, and also context-level analysis, by providing the textual data, and combining different…
State-of-the-art target-oriented opinion word extraction (TOWE) models typically use BERT-based text encoders that operate on the word level, along with graph convolutional networks (GCNs) that incorporate syntactic information extracted…
Structured sentiment analysis, which aims to extract the complex semantic structures such as holders, expressions, targets, and polarities, has obtained widespread attention from both industry and academia. Unfortunately, the existing…
Past work that improves document-level sentiment analysis by encoding user and product information has been limited to considering only the text of the current review. We investigate incorporating additional review text available at the…
Traditional approaches to automatic emotion recognition are relying on the application of handcrafted features. More recently however the advent of deep learning enabled algorithms to learn meaningful representations of input data…
We explore the properties of byte-level recurrent language models. When given sufficient amounts of capacity, training data, and compute time, the representations learned by these models include disentangled features corresponding to…
Word embeddings are representations of individual words of a text document in a vector space and they are often use- ful for performing natural language pro- cessing tasks. Current state of the art al- gorithms for learning word embeddings…
Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification, semantic textual similarity, and natural language inference. Most state-of-the-art neural models for these tasks rely on pretrained word embedding and…