Related papers: MockConf: A Student Interpretation Dataset: Analys…
Simultaneous translation on both text and speech focuses on a real-time and low-latency scenario where the model starts translating before reading the complete source input. Evaluating simultaneous translation models is more complex than…
Recent progress in speech processing has highlighted that high-quality performance across languages requires substantial training data for each individual language. While existing multilingual datasets cover many languages, they often…
Lectures translation is a case of spoken language translation and there is a lack of publicly available parallel corpora for this purpose. To address this, we examine a language independent framework for parallel corpus mining which is a…
Sarcasm is a complex form of figurative language in which the intended meaning contradicts the literal one. Its prevalence in social media and popular culture poses persistent challenges for natural language understanding, sentiment…
In this paper, a novel approach is proposed to automatically construct parallel discourse corpus for dialogue machine translation. Firstly, the parallel subtitle data and its corresponding monolingual movie script data are crawled and…
Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimized long-sequence inference through operators, model…
Understanding long text is of great demands in practice but beyond the reach of most language-image pre-training (LIP) models. In this work, we empirically confirm that the key reason causing such an issue is that the training images are…
The success of a text simplification system heavily depends on the quality and quantity of complex-simple sentence pairs in the training corpus, which are extracted by aligning sentences between parallel articles. To evaluate and improve…
When people observe events, they are able to abstract key information and build concise summaries of what is happening. These summaries include contextual and semantic information describing the important high-level details (what, where,…
Recent advances in audio-language models have demonstrated remarkable success on short, segment-level speech tasks. However, real-world applications such as meeting transcription, spoken document understanding, and conversational analysis…
For human beings, the processing of text streams of unknown size leads generally to problems because e.g. noise must be selected out, information be tested for its relevance or redundancy, and linguistic phenomenon like ambiguity or the…
Large language models (LLMs) with extended context windows enable tasks requiring extensive information integration but are limited by the scarcity of high-quality, diverse datasets for long-context instruction tuning. Existing data…
Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair…
This work presents iMiGUE-Speech, an extension of the iMiGUE dataset that provides a spontaneous affective corpus for studying emotional and affective states. The new release focuses on speech and enriches the original dataset with…
Translation has played a crucial role in improving the performance on multilingual tasks: (1) to generate the target language data from the source language data for training and (2) to generate the source language data from the target…
Text alignment finds application in tasks such as citation recommendation and plagiarism detection. Existing alignment methods operate at a single, predefined level and cannot learn to align texts at, for example, sentence and document…
Stylistic variation in text needs to be studied with different aspects including the writer's personal traits, interpersonal relations, rhetoric, and more. Despite recent attempts on computational modeling of the variation, the lack of…
End-to-end Large Speech Language Models (LSLMs) have demonstrated impressive conversational generation abilities, yet consistently fall short of traditional pipeline systems on semantic understanding benchmarks. In this work, we reveal…
Semantic parsing offers many opportunities to improve natural language understanding. We present a semantically annotated parallel corpus for English, German, Italian, and Dutch where sentences are aligned with scoped meaning…
We investigate the problem of simultaneous machine translation of long-form speech content. We target a continuous speech-to-text scenario, generating translated captions for a live audio feed, such as a lecture or play-by-play commentary.…