Related papers: Unsupervised Sentence Textual Similarity with Comp…
Speech-to-text translation (ST), which directly translates the source language speech to the target language text, has attracted intensive attention recently. However, the combination of speech recognition and machine translation in a…
Semantic text similarity plays an important role in software engineering tasks in which engineers are requested to clarify the semantics of descriptive labels (e.g., business terms, table column names) that are often consists of too short…
Incremental text-to-speech (TTS) synthesis generates utterances in small linguistic units for the sake of real-time and low-latency applications. We previously proposed an incremental TTS method that leverages a large pre-trained language…
Sentences that present a complex syntax act as a major stumbling block for downstream Natural Language Processing applications whose predictive quality deteriorates with sentence length and complexity. The task of Text Simplification (TS)…
The processing of legal texts has been developing as an emerging field in natural language processing (NLP). Legal texts contain unique jargon and complex linguistic attributes in vocabulary, semantics, syntax, and morphology. Therefore,…
This paper presents Semantic SentenceRank (SSR), an unsupervised scheme for automatically ranking sentences in a single document according to their relative importance. In particular, SSR extracts essential words and phrases from a text…
Sentence embeddings encode sentences in fixed dense vectors and have played an important role in various NLP tasks and systems. Methods for building sentence embeddings include unsupervised learning such as Quick-Thoughts and supervised…
Text segmentation (TS) aims at dividing long text into coherent segments which reflect the subtopic structure of the text. It is beneficial to many natural language processing tasks, such as Information Retrieval (IR) and document…
Semantic Similarity between two sentences can be defined as a way to determine how related or unrelated two sentences are. The task of Semantic Similarity in terms of distributed representations can be thought to be generating sentence…
Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo…
End-to-end text-to-speech (TTS) synthesis is a method that directly converts input text to output acoustic features using a single network. A recent advance of end-to-end TTS is due to a key technique called attention mechanisms, and all…
Similarity measures based purely on word embeddings are comfortably competing with much more sophisticated deep learning and expert-engineered systems on unsupervised semantic textual similarity (STS) tasks. In contrast to commonly used…
Semantic textual similarity (STS) plays a crucial role in many natural language processing tasks. While extensively studied in high-resource languages, STS remains challenging for under-resourced languages such as Slovak. This paper…
In this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation. We first design discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in…
Automatic text summarization (ATS) has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale corpora. To make the summarization results more faithful, this paper presents an…
BERT is inefficient for sentence-pair tasks such as clustering or semantic search as it needs to evaluate combinatorially many sentence pairs which is very time-consuming. Sentence BERT (SBERT) attempted to solve this challenge by learning…
Copying mechanism has been commonly used in neural paraphrasing networks and other text generation tasks, in which some important words in the input sequence are preserved in the output sequence. Similarly, in machine translation, we notice…
Automatic evaluation of ST systems is typically performed by comparing translation hypotheses with one or more reference translations. While effective to some extent, this approach inherits the limitation of reference-based evaluation that…
Simultaneous speech translation (SST) produces target text incrementally from partial speech input. Recent speech large language models (Speech LLMs) have substantially improved SST quality, yet they still struggle to correctly translate…
Semantic Textual Similarity (STS) is a crucial component of many Natural Language Processing (NLP) applications. However, existing approaches typically reduce semantic nuances to a single score, limiting interpretability. To address this,…