Related papers: Improving part-of-speech tagging via multi-task le…
We train one multilingual model for dependency parsing and use it to parse sentences in several languages. The parsing model uses (i) multilingual word clusters and embeddings; (ii) token-level language information; and (iii)…
Attribute labeling at large scale is typically incomplete and partial, posing significant challenges to model optimization. Existing attribute learning methods often treat the missing labels as negative or simply ignore them all during…
Recurrent neural networks have become ubiquitous in computing representations of sequential data, especially textual data in natural language processing. In particular, Bidirectional LSTMs are at the heart of several neural models achieving…
Automatic speech recognition and spoken dialogue systems have made great advances through the use of deep machine learning methods. This is partly due to greater computing power but also through the large amount of data available in common…
Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We exploit an ASR and NLU joint training method based on meta…
Automatic language processing tools typically assign to terms so-called weights corresponding to the contribution of terms to information content. Traditionally, term weights are computed from lexical statistics, e.g., term frequencies. We…
Linguistic Code Switching (CS) is a phenomenon that occurs when multilingual speakers alternate between two or more languages/dialects within a single conversation. Processing CS data is especially challenging in intra-sentential data given…
We present a deep hierarchical recurrent neural network for sequence tagging. Given a sequence of words, our model employs deep gated recurrent units on both character and word levels to encode morphology and context information, and…
Speech emotion recognition (SER) models typically rely on costly human-labeled data for training, making scaling methods to large speech datasets and nuanced emotion taxonomies difficult. We present LanSER, a method that enables the use of…
This paper advances NLP research for the low-resource Uzbek language by evaluating two previously untested monolingual Uzbek BERT models on the part-of-speech (POS) tagging task and introducing the first publicly available UPOS-tagged…
The Bidirectional long short-term memory networks (BiLSTM) have been widely used as an encoder in models solving the named entity recognition (NER) task. Recently, the Transformer is broadly adopted in various Natural Language Processing…
Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often…
Speech applications dealing with conversations require not only recognizing the spoken words but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate systems,…
We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The central assumption of our work is that by combining cues from multiple languages, the structure of each becomes more apparent. We…
In the recent years, speech representation learning is constructed primarily as a self-supervised learning (SSL) task, using the raw audio signal alone, while ignoring the side-information that is often available for a given speech…
This paper focuses on how to take advantage of external knowledge bases (KBs) to improve recurrent neural networks for machine reading. Traditional methods that exploit knowledge from KBs encode knowledge as discrete indicator features. Not…
Most of the existing pre-trained language representation models neglect to consider the linguistic knowledge of texts, which can promote language understanding in NLP tasks. To benefit the downstream tasks in sentiment analysis, we propose…
Selecting optimal parameters for a neural network architecture can often make the difference between mediocre and state-of-the-art performance. However, little is published which parameters and design choices should be evaluated or selected…
Automatic speech recognition (ASR) models rely on high-quality transcribed data for effective training. Generating pseudo-labels for large unlabeled audio datasets often relies on complex pipelines that combine multiple ASR outputs through…
Self-supervised learning offers an efficient way of extracting rich representations from various types of unlabeled data while avoiding the cost of annotating large-scale datasets. This is achievable by designing a pretext task to form…