Related papers: An Efficient, Probabilistically Sound Algorithm fo…
We introduce an unsupervised discriminative model for the task of retrieving experts in online document collections. We exclusively employ textual evidence and avoid explicit feature engineering by learning distributed word representations…
Decomposing models into multiple components is critically important in many applications such as language modeling (LM) as it enables adapting individual components separately and biasing of some components to the user's personal…
A series of recent papers has used a parsing algorithm due to Shen et al. (2018) to recover phrase-structure trees based on proxies for "syntactic depth." These proxy depths are obtained from the representations learned by recurrent…
Modeling topics effectively in short texts, such as tweets and news snippets, is crucial to capturing rapidly evolving social trends. Existing topic models often struggle to accurately capture the underlying semantic patterns of short…
The recent proliferation of richly structured probabilistic models raises the question of how to automatically determine an appropriate model for a dataset. We investigate this question for a space of matrix decomposition models which can…
Speech signals are complex composites of various information, including phonetic content, speaker traits, channel effect, etc. Decomposing this complicated mixture into independent factors, i.e., speech factorization, is fundamentally…
We present a state-of-the-art neural approach to the unsupervised reconstruction of ancient word forms. Previous work in this domain used expectation-maximization to predict simple phonological changes between ancient word forms and their…
Keyword extraction is a fundamental task in natural language processing that facilitates mapping of documents to a concise set of representative single and multi-word phrases. Keywords from text documents are primarily extracted using…
Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem…
Distributional models are derived from co-occurrences in a corpus, where only a small proportion of all possible plausible co-occurrences will be observed. This results in a very sparse vector space, requiring a mechanism for inferring…
The generative nature of Large Language Models (LLMs) is reflected in the conditional probabilities they compute to sample each response token given the previous tokens. These probabilities encode the distributional structure that the model…
This work studies discrete diffusion probabilistic models with applications to natural language generation. We derive an alternative yet equivalent formulation of the sampling from discrete diffusion processes and leverage this insight to…
Neural network-based language models deal with data sparsity problems by mapping the large discrete space of words into a smaller continuous space of real-valued vectors. By learning distributed vector representations for words, each…
Word or word-fragment based Language Models (LM) are typically preferred over character-based ones in many downstream applications. This may not be surprising as words seem more linguistically relevant units than characters. Words provide…
In natural language processing, a lot of the tasks are successfully solved with recurrent neural networks, but such models have a huge number of parameters. The majority of these parameters are often concentrated in the embedding layer,…
Large Language Models (LLMs) demonstrate strong few-shot generalization through in-context learning, yet their reasoning in dynamic and stochastic environments remains opaque. Prior studies mainly focus on static tasks and overlook the…
In NLP, text language models based on words or subwords are known to outperform their character-based counterparts. Yet, in the speech community, the standard input of spoken LMs are 20ms or 40ms-long discrete units (shorter than a…
Previous traditional approaches to unsupervised Chinese word segmentation (CWS) can be roughly classified into discriminative and generative models. The former uses the carefully designed goodness measures for candidate segmentation, while…
The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i.e. semantic representations) of word sequences as well. We…
In this work, we evaluate the potential of Large Language Models (LLMs) in building Bayesian Networks (BNs) by approximating domain expert priors. LLMs have demonstrated potential as factual knowledge bases; however, their capability to…