Related papers: A Concise Model for Multi-Criteria Chinese Word Se…
With the explosive growth of Chinese text data and advancements in natural language processing technologies, Chinese text classification has become one of the key techniques in fields such as information retrieval and sentiment analysis,…
In this report, we present our submission to the WMT 2022 Metrics Shared Task. We build our system based on the core idea of UNITE (Unified Translation Evaluation), which unifies source-only, reference-only, and source-reference-combined…
In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria. Our experiments show that…
Short text matching often faces the challenges that there are great word mismatch and expression diversity between the two texts, which would be further aggravated in languages like Chinese where there is no natural space to segment words…
Existing Chinese text error detection mainly focuses on spelling and simple grammatical errors. These errors have been studied extensively and are relatively simple for humans. On the contrary, Chinese semantic errors are understudied and…
Segmentation remains an important preprocessing step both in languages where "words" or other important syntactic/semantic units (like morphemes) are not clearly delineated by white space, as well as when dealing with continuous speech…
Distributed word representations are very useful for capturing semantic information and have been successfully applied in a variety of NLP tasks, especially on English. In this work, we innovatively develop two component-enhanced Chinese…
Previous work has predominantly focused on monolingual English semantic parsing. We, instead, explore the feasibility of Chinese semantic parsing in the absence of labeled data for Chinese meaning representations. We describe the pipeline…
The evolution of language follows the rule of gradual change. Grammar, vocabulary, and lexical semantic shifts take place over time, resulting in a diachronic linguistic gap. As such, a considerable amount of texts are written in languages…
Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language…
We propose UniT, a Unified Transformer model to simultaneously learn the most prominent tasks across different domains, ranging from object detection to natural language understanding and multimodal reasoning. Based on the transformer…
Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…
Open-ended text generation has become a prominent task in natural language processing due to the rise of powerful (large) language models. However, evaluating the quality of these models and the employed decoding strategies remains…
In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1.9TB images and 292GB texts that cover a wide range of domains. We propose a cross-modal pretraining method called M6, referring…
Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem…
Pre-trained word embeddings encode general word semantics and lexical regularities of natural language, and have proven useful across many NLP tasks, including word sense disambiguation, machine translation, and sentiment analysis, to name…
Lexical analysis is believed to be a crucial step towards natural language understanding and has been widely studied. Recent years, end-to-end lexical analysis models with recurrent neural networks have gained increasing attention. In this…
This system report presents our approaches and results for the Chinese Essay Fluency Evaluation (CEFE) task at CCL-2024. For Track 1, we optimized predictions for challenging fine-grained error types using binary classification models and…
Computer poetry generation is our first step towards computer writing. Writing must have a theme. The current approaches of using sequence-to-sequence models with attention often produce non-thematic poems. We present a novel conditional…
In the field of medical imaging, AI-assisted techniques such as object detection, segmentation, and classification are widely employed to alleviate the workload of physicians and doctors. However, single-task models are predominantly used,…