Related papers: Moment Matching Training for Neural Machine Transl…
Neural marked temporal point processes have been a valuable addition to the existing toolbox of statistical parametric models for continuous-time event data. These models are useful for sequences where each event is associated with a single…
Transfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies. This paper shows effective techniques to transfer a…
Sentence embedding is an important research topic in natural language processing. It is essential to generate a good embedding vector that fully reflects the semantic meaning of a sentence in order to achieve an enhanced performance for…
We present a novel Neural Embedding Spatio-Temporal (NEST) point process model for spatio-temporal discrete event data and develop an efficient imitation learning (a type of reinforcement learning) based approach for model fitting. Despite…
Monolingual data have been demonstrated to be helpful in improving translation quality of both statistical machine translation (SMT) systems and neural machine translation (NMT) systems, especially in resource-poor or domain adaptation…
The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. In this paper, we focus on…
The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…
Neural Machine Translation (NMT) is the task of translating a text from one language to another with the use of a trained neural network. Several existing works aim at incorporating external information into NMT models to improve or control…
Designing machine intelligence to converse with a human user necessarily requires an understanding of how humans participate in conversation, and thus conversation modeling is an important task in natural language processing. New…
Using pre-trained word embeddings as input layer is a common practice in many natural language processing (NLP) tasks, but it is largely neglected for neural machine translation (NMT). In this paper, we conducted a systematic analysis on…
Inspired by human neurological structures for action anticipation, we present an action anticipation model that enables the prediction of plausible future actions by forecasting both the visual and temporal future. In contrast to current…
Multi-encoder models are a broad family of context-aware neural machine translation systems that aim to improve translation quality by encoding document-level contextual information alongside the current sentence. The context encoding is…
Word embeddings are one of the most useful tools in any modern natural language processing expert's toolkit. They contain various types of information about each word which makes them the best way to represent the terms in any NLP task. But…
Simultaneous neural machine translation(SNMT) models start emitting the target sequence before they have processed the source sequence. The recent adaptive policies for SNMT use monotonic attention to perform read/write decisions based on…
Though word embeddings and topics are complementary representations, several past works have only used pre-trained word embeddings in (neural) topic modeling to address data sparsity problem in short text or small collection of documents.…
Pre-training models with large crawled corpora can lead to issues such as toxicity and bias, as well as copyright and privacy concerns. A promising way of alleviating such concerns is to conduct pre-training with synthetic tasks and data,…
We propose a method to transfer knowledge across neural machine translation (NMT) models by means of a shared dynamic vocabulary. Our approach allows to extend an initial model for a given language pair to cover new languages by adapting…
The task of multi-step ahead prediction in language models is challenging considering the discrepancy between training and testing. At test time, a language model is required to make predictions given past predictions as input, instead of…
Successful methods for unsupervised neural machine translation (UNMT) employ crosslingual pretraining via self-supervision, often in the form of a masked language modeling or a sequence generation task, which requires the model to align the…
Any prediction from a model is made by a combination of learning history and test stimuli. This provides significant insights for improving model interpretability: {\it because of which part(s) of which training example(s), the model…