Related papers: Two-pass Discourse Segmentation with Pairing and G…
Self-attention mechanisms have enabled transformers to achieve superhuman-level performance on many speech-to-text (STT) tasks, yet the challenge of automatic prosodic segmentation has remained unsolved. In this paper we finetune Whisper, a…
Recent advances in methods focused on the grounding problem have resulted in techniques that can be used to construct a symbolic language associated with a specific domain. Inspired by how humans communicate complex ideas through language,…
In speech separation, time-domain approaches have successfully replaced the time-frequency domain with latent sequence feature from a learnable encoder. Conventionally, the feature is separated into speaker-specific ones at the final stage…
Recent neural supervised topic segmentation models achieve distinguished superior effectiveness over unsupervised methods, with the availability of large-scale training corpora sampled from Wikipedia. These models may, however, suffer from…
We introduce a generic seq2seq parsing framework that casts constituency parsing problems (syntactic and discourse parsing) into a series of conditional splitting decisions. Our parsing model estimates the conditional probability…
This paper introduces a new statistical approach to partitioning text automatically into coherent segments. Our approach enlists both short-range and long-range language models to help it sniff out likely sites of topic changes in text. To…
Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments…
Breaking down a document or a conversation into multiple contiguous segments based on its semantic structure is an important and challenging problem in NLP, which can assist many downstream tasks. However, current works on topic…
Automatically detecting discourse segments is an important preliminary step towards full discourse parsing. Previous research on discourse segmentation have relied on the assumption that elementary discourse units (EDUs) in a document…
The purpose of speech tokenization is to transform a speech signal into a sequence of discrete representations, serving as the foundation for speech language models (SLMs). While speech tokenization has many options, their effect on the…
We present an unsupervised word segmentation model, in which the learning objective is to maximize the generation probability of a sentence given its all possible segmentation. Such generation probability can be factorized into the…
Referring expressions are natural language descriptions that identify a particular object within a scene and are widely used in our daily conversations. In this work, we focus on segmenting the object in an image specified by a referring…
We propose a segmental neural language model that combines the generalization power of neural networks with the ability to discover word-like units that are latent in unsegmented character sequences. In contrast to previous segmentation…
Many NLP pipelines split text into sentences as one of the crucial preprocessing steps. Prior sentence segmentation tools either rely on punctuation or require a considerable amount of sentence-segmented training data: both central…
Discourse parsing has long been treated as a stand-alone problem independent from constituency or dependency parsing. Most attempts at this problem are pipelined rather than end-to-end, sophisticated, and not self-contained: they assume…
Parsing spoken dialogue presents challenges that parsing text does not, including a lack of clear sentence boundaries. We know from previous work that prosody helps in parsing single sentences (Tran et al. 2018), but we want to show the…
Segmenting text into Elemental Discourse Units (EDUs) is a fundamental task in discourse parsing. We present a new simple method for identifying EDU boundaries, and hence segmenting them, based on lexical and character n-gram features,…
Due to the absence of explicit word boundaries in the speech stream, the task of segmenting spoken sentences into word units without text supervision is particularly challenging. In this work, we leverage the most recent self-supervised…
Recently, neural network models for natural language processing tasks have been increasingly focused on for their ability of alleviating the burden of manual feature engineering. However, the previous neural models cannot extract the…
Certain spans of utterances in a discourse, referred to here as segments, are widely assumed to form coherent units. Further, the segmental structure of discourse has been claimed to constrain and be constrained by many phenomena. However,…