Related papers: LET: Linguistic Knowledge Enhanced Graph Transform…

BERT, which stands for Bidirectional Encoder Representations from Transformers, is a recently introduced language representation model based upon the transfer learning paradigm. We extend its fine-tuning procedure to address one of its…

Named entity recognition, and other information extraction tasks, frequently use linguistic features such as part of speech tags or chunkings. For languages where word boundaries are not readily identified in text, word segmentation is a…

The classification of short texts is a common subtask in Information Retrieval (IR). Recent advances in graph machine learning have led to interest in graph-based approaches for low resource scenarios, showing promise in such settings.…

Despite recent successes with neural models for sign language translation (SLT), translation quality still lags behind spoken languages because of the data scarcity and modality gap between sign video and text. To address both problems, we…

Neural network techniques are widely applied to obtain high-quality distributed representations of words, i.e., word embeddings, to address text mining, information retrieval, and natural language processing tasks. Recently, efficient…

Linguistic ambiguity is critical to the robustness of Large Language Models (LLMs), yet existing research focuses mostly on English, with limited attention devoted to Chinese. Existing Chinese ambiguity datasets (e.g., CHAmbi) suffer from…

Chinese Grammatical Error Correction (CGEC) aims to automatically detect and correct grammatical errors contained in Chinese text. In the long term, researchers regard CGEC as a task with a certain degree of uncertainty, that is, an…

A widely acknowledged shortcoming of WordNet is that it lacks a distinction between word meanings which are systematically related (polysemy), and those which are coincidental (homonymy). Several previous works have attempted to fill this…

Most previous approaches to Chinese word segmentation formalize this problem as a character-based sequence labeling task where only contextual information within fixed sized local windows and simple interactions between adjacent tags can be…

Semantic consistency recognition aims to detect and judge whether the semantics of two text sentences are consistent with each other. However, the existing methods usually encounter the challenges of synonyms, polysemy and difficulty to…

Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or…

Grapheme-to-phoneme (G2P) conversion serves as an essential component in Chinese Mandarin text-to-speech (TTS) system, where polyphone disambiguation is the core issue. In this paper, we propose an end-to-end framework to predict the…

Text-to-Table aims to generate structured tables to convey the key information from unstructured documents. Existing text-to-table datasets are typically oriented English, limiting the research in non-English languages. Meanwhile, the…

The prevalent approaches of Chinese word segmentation task almost rely on the Bi-LSTM neural network. However, the methods based the Bi-LSTM have some inherent drawbacks: hard to parallel computing, little efficient in applying the Dropout…

Contextualized representations give significantly improved results for a wide range of NLP tasks. Much work has been dedicated to analyzing the features captured by representative models such as BERT. Existing work finds that syntactic,…

We present a Chinese BERT model dubbed MarkBERT that uses word information in this work. Existing word-based BERT models regard words as basic units, however, due to the vocabulary limit of BERT, they only cover high-frequency words and…

Using Large Language Models (LLMs) to process graph-structured data is an active research area, yet current state-of-the-art approaches typically rely on multi-step pipelines with Graph Neural Network (GNN) encoders that compress rich…

Existing research generally treats Chinese character as a minimum unit for representation. However, such Chinese character representation will suffer two bottlenecks: 1) Learning bottleneck, the learning cannot benefit from its rich…

Bilingual lexicons form a critical component of various natural language processing applications, including unsupervised and semisupervised machine translation and crosslingual information retrieval. We improve bilingual lexicon induction…

Current grammatical error correction (GEC) models typically consider the task as sequence generation, which requires large amounts of annotated data and limit the applications in data-limited settings. We try to incorporate contextual…