How well can large language models (LLMs) generate summaries? We develop...
With the development of pre-trained models and the incorporation of phon...
Hyperbole, or exaggeration, is a common linguistic phenomenon. The detec...
Factuality is important to dialogue summarization. Factual error correct...
Sentence Simplification is a valuable technique that can benefit languag...
Research on automated text summarization relies heavily on human and
aut...
Randomly masking text spans in ordinary texts in the pre-training stage
...
Evaluating text summarization is a challenging problem, and existing
eva...
Video captioning aims to describe events in a video with natural languag...
One of the major problems with text simplification is the lack of
high-q...
Sarcasm generation has been investigated in previous studies by consider...
Chinese Spelling Check (CSC) aims to detect and correct error tokens in
...
Many studies have revealed that word embeddings, language models, and mo...
Automatic post-editing (APE) aims to reduce manual post-editing efforts ...
Crosstalk is a traditional Chinese theatrical performance art. It is com...
k-nearest-neighbor machine translation (NN-MT), proposed by Khandelwal e...
Pre-trained models are widely used in the tasks of natural language
proc...
Various models have been proposed to incorporate knowledge of syntactic
...
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analy...
Zero-shot paraphrase generation has drawn much attention as the large-sc...
The problem of poster generation for scientific papers is under-investig...
Grammatical Error Correction (GEC) is a task of detecting and correcting...
Text simplification is a valuable technique. However, current research i...
A riddle is a question or statement with double or veiled meanings, foll...
We propose CodeQA, a free-form question answering dataset for the purpos...
Despite being a common figure of speech, hyperbole is under-researched w...
Paraphrase generation is an important task in natural language processin...
In recent years, neural paraphrase generation based on Seq2Seq has achie...
Abstract Meaning Representation (AMR) is a rooted, labeled, acyclic grap...
Neural text generation models are likely to suffer from the low-diversit...
The search engine plays a fundamental role in online e-commerce systems,...
We propose ParaSCI, the first large-scale paraphrase dataset in the
scie...
Context-dependent text-to-SQL task has drawn much attention in recent ye...
Multimodal sentiment analysis is an important research area that predict...
It is reasonable to hypothesize that the divergence patterns formulated ...
In this paper, we explore a new approach for automated chess commentary
...
Ironies can not only express stronger emotions but also show a sense of
...
Nowadays, we are surrounded by more and more online news articles. Tens ...
We present a phenomenon-oriented comparative analysis of the two dominan...
Recently, encoder-decoder neural models have achieved great success on t...
Language style transfer has attracted more and more attention in the pas...
Unsupervised text attribute transfer automatically transforms a text to ...
Finding new academic Methods for research problems is the key task in a
...
This paper studies semantic parsing for interlanguage (L2), taking seman...
Till now, neural abstractive summarization methods have achieved great
s...
Crosstalk, also known by its Chinese name xiangsheng, is a traditional
C...
Accuracy is one of the basic principles of journalism. However, it is
in...
Coordinate relation refers to the relation between instances of a concep...
Future works in scientific articles are valuable for researchers and the...
Existing multi-document summarization systems usually rely on a specific...