With the rapid development and popularization of Internet and mobile communication
technologies, text data mining has attracted much attention. In particular, with the wide use …

To translate well, machine translation (MT) systems and general-purposed language models
(LMs) need a deep understanding of both source and target languages and cultures …

We introduce a recurrent neural network language model (RNN-LM) with long short-term
memory (LSTM) units that utilizes both character-level and word-level inputs. Our model has …

This paper considers the problem of learning Chinese word embeddings. In contrast to
English, a Chinese word is usually composed of characters, and most of the characters …

Despite their success in a variety of NLP tasks, pre-trained language models, due to their
heavy reliance on compositionality, fail in effectively capturing the meanings of multiword …

Text is one of the most common unstructured data, and usually, the most primary task in text
mining is to transfer the text into a structured representation. However, the existing text …

Abstract Community Question Answering (CQA) has become an indispensable way for
modern people to share and acquire knowledge. It allows users to ask questions, which will …

Idiomatic expressions (IEs), characterized by their non-compositionality, are an important
part of natural language. They have been a classical challenge to NLP, including pre-trained …

Much like sentences are composed of words, words themselves are composed of smaller
units. For example, the English word questionably can be analyzed as question+ able+ ly …

Phrase embedding can improve the performance of multiple NLP tasks. Most of the previous
phrase-embedding methods that only use the external or internal semantic information of …