Related papers: Towards Effective Ancient Chinese Translation: Dat…
Machine reading comprehension tasks require a machine reader to answer questions relevant to the given document. In this paper, we present the first free-form multiple-Choice Chinese machine reading Comprehension dataset (C^3), containing…
Classical Chinese poetry is a jewel in the treasure house of Chinese culture. Previous poem generation models only allow users to employ keywords to interfere the meaning of generated poems, leaving the dominion of generation to the model.…
Preservation of domain knowledge from the source to target is crucial in any translation workflow. It is common in the translation industry to receive highly specialized projects, where there is hardly any parallel in-domain data. In such…
Chinese idioms are special fixed phrases usually derived from ancient stories, whose meanings are oftentimes highly idiomatic and non-compositional. The Chinese idiom prediction task is to select the correct idiom from a set of candidate…
Recent advances in training multilingual language models on large datasets seem to have shown promising results in knowledge transfer across languages and achieve high performance on downstream tasks. However, we question to what extent the…
Both human and machine translation play a central role in cross-lingual transfer learning: many multilingual datasets have been created through professional translation services, and using machine translation to translate either the test…
While achieving state-of-the-art results in multiple tasks and languages, translation-based cross-lingual transfer is often overlooked in favour of massively multilingual pre-trained encoders. Arguably, this is due to its main limitations:…
During the development of large language models (LLMs), the scale and quality of the pre-training data play a crucial role in shaping LLMs' capabilities. To accelerate the research of LLMs, several large-scale datasets, such as C4 [1], Pile…
Because it is not feasible to collect training data for every language, there is a growing interest in cross-lingual transfer learning. In this paper, we systematically explore zero-shot cross-lingual transfer learning on reading…
Previous work on document-level NMT usually focuses on limited contexts because of degraded performance on larger contexts. In this paper, we investigate on using large contexts with three main contributions: (1) Different from previous…
Multilingual neural machine translation can translate unseen language pairs during training, i.e. zero-shot translation. However, the zero-shot translation is always unstable. Although prior works attributed the instability to the…
Recent advancements enlarge the capabilities of large language models (LLMs) in zero-shot image-to-text generation and understanding by integrating multi-modal inputs. However, such success is typically limited to English scenarios due to…
asya is a mobile application that consists of deep learning models which analyze spectra of a human voice and do noise detection, speaker diarization, gender detection, tempo estimation, and classification of emotions using only voice. All…
Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which is a core problem for domain adaptation in real-world…
While most machine translation systems to date are trained on large parallel corpora, humans learn language in a different way: by being grounded in an environment and interacting with other humans. In this work, we propose a communication…
Chinese information extraction (IE) involves multiple tasks across diverse temporal domains, including Classical and Modern documents. Fine-tuning a single model on heterogeneous tasks and across different eras may lead to interference and…
As a special machine translation task, dialect translation has two main characteristics: 1) lack of parallel training corpus; and 2) possessing similar grammar between two sides of the translation. In this paper, we investigate how to…
Recent work like GPT-3 has demonstrated excellent performance of Zero-Shot and Few-Shot learning on many natural language processing (NLP) tasks by scaling up model size, dataset size and the amount of computation. However, training a model…
Traditional Chinese Medicine theory is built on imagistic thinking, in which medical principles and diagnostic and therapeutic logic are structured through metaphor and metonymy. However, existing English translations largely rely on…
Holistically measuring societal biases of large language models is crucial for detecting and reducing ethical risks in highly capable AI models. In this work, we present a Chinese Bias Benchmark dataset that consists of over 100K questions…