Related papers: Unsupervised Inference of Data-Driven Discourse St…
Knowledge-enhanced text generation aims to enhance the quality of generated text by utilizing internal or external knowledge sources. While language models have demonstrated impressive capabilities in generating coherent and fluent text,…
Unsupervised dialogue structure learning is an important and meaningful task in natural language processing. The extracted dialogue structure and process can help analyze human dialogue, and play a vital role in the design and evaluation of…
Human language is known to exhibit a nested, hierarchical structure, allowing us to form complex sentences out of smaller pieces. However, many state-of-the-art neural networks models such as Transformers have no explicit hierarchical…
Implicit discourse relations are not only more challenging to classify, but also to annotate, than their explicit counterparts. We tackle situations where training data for implicit relations are lacking, and exploit domain adaptation from…
Autoregressive language models demonstrate excellent performance in various scenarios. However, the inference efficiency is limited by its one-step-one-word generation mode, which has become a pressing problem recently as the models become…
We introduce Hyper-Trees as a novel framework for modeling time series data using gradient boosted trees. Unlike conventional tree-based approaches that forecast time series directly, Hyper-Trees learn the parameters of a target time series…
Data augmentation methods for neural machine translation are particularly useful when limited amount of training data is available, which is often the case when dealing with low-resource languages. We introduce a novel augmentation method,…
The development of lexicalized grammars, particularly Tree-Adjoining Grammar (TAG), has significantly advanced our understanding of syntax and semantics in natural language processing (NLP). While existing syntactic resources like the Penn…
Transforming unstructured text into structured data is a complex task, requiring semantic understanding, reasoning, and structural comprehension. While Large Language Models (LLMs) offer potential, they often struggle with handling…
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…
Endowing chatbots with a consistent persona is essential to an engaging conversation, yet it remains an unresolved challenge. In this work, we propose a new retrieval-enhanced approach for personalized response generation. Specifically, we…
Publicly available, large pretrained LanguageModels (LMs) generate text with remarkable quality, but only sequentially from left to right. As a result, they are not immediately applicable to generation tasks that break the unidirectional…
The search for a standardized optimum way to communicate using natural language dialog has involved a lot of research. However, due to the diversity of communication domains, we think that this is extremely difficult to achieve and…
It is commonly believed that knowledge of syntactic structure should improve language modeling. However, effectively and computationally efficiently incorporating syntactic structure into neural language models has been a challenging topic.…
Recent breakthroughs in Natural Language Processing (NLP) have been driven by language models trained on a massive amount of plain text. While powerful, deriving supervision from textual resources is still an open question. For example,…
Most prior work on task-oriented dialogue systems are restricted to a limited coverage of domain APIs, while users oftentimes have domain related requests that are not covered by the APIs. In this paper, we propose to expand coverage of…
Tabular foundation models are becoming increasingly popular for low-resource tabular problems. These models make up for small training datasets by pretraining on large volumes of synthetic data. The prior knowledge obtained via pretraining…
Latent tree learning models learn to parse a sentence without syntactic supervision, and use that parse to build the sentence representation. Existing work on such models has shown that, while they perform well on tasks like sentence…
Implicit discourse relation classification is a challenging task due to the absence of discourse connectives. To overcome this issue, we design an end-to-end neural model to explicitly generate discourse connectives for the task, inspired…
End-to-end neural approaches are becoming increasingly common in conversational scenarios due to their promising performances when provided with sufficient amount of data. In this paper, we present a novel methodology to address the…