Large Language Models (LLMs) have revolutionized natural language proces...
Zero pronouns (ZPs) are frequently omitted in pro-drop languages (e.g.
C...
Knowledge-aided dialogue response generation aims at augmenting chatbots...
Current self-training methods such as standard self-training, co-trainin...
Simile recognition involves two subtasks: simile sentence classification...
Abstract Meaning Representation (AMR) parsing aims to predict an AMR gra...
The task of context-dependent text-to-SQL aims to convert multi-turn use...
Pre-trained language models have made great progress on dialogue tasks.
...
Utterance rewriting aims to recover coreferences and omitted information...
Approaches for the stance classification task, an important task for
und...
In this paper, we investigate channel acquisition for high frequency (HF...
Existing pre-trained models for knowledge-graph-to-text (KG-to-text)
gen...
Language models like BERT and SpanBERT pretrained on open-domain data ha...
Although neural models have achieved competitive results in dialogue sys...
Semantic role labeling (SRL) aims to extract the arguments for each pred...
We investigate video-aided grammar induction, which learns a constituenc...
In aspect-based sentiment analysis (ABSA), many neural models are equipp...
The task of graph-to-text generation aims at producing sentences that
pr...
This technique report introduces TexSmart, a text understanding system t...
The task of dialogue rewriting aims to reconstruct the latest dialogue
u...
AMR-to-text generation aims to recover a text containing the same meanin...
For multi-turn dialogue rewriting, the capacity of effectively modeling ...
Existing entity alignment methods mainly vary on the choices of encoding...
Simile recognition is to detect simile sentences and to extract simile
c...
Sentence ordering is to restore the original paragraph from a set of
sen...
Medical relation extraction discovers relations between entity mentions ...
Self-explaining text categorization requires a classifier to make a
pred...
How to properly model graphs is a long-existing and important problem in...
Benefiting from the excellent ability of neural networks on learning sem...
In aspect-level sentiment classification (ASC), it is prevalent to equip...
Evaluating AMR parsing accuracy involves comparing pairs of AMR graphs. ...
It is intuitive that semantic representations can be useful for machine
...
The task of linearization is to find a grammatical order given a set of
...
Multi-hop reading comprehension focuses on one type of factoid question,...
Cross-sentence n-ary relation extraction detects relations among n
entit...
Bi-directional LSTMs are a powerful tool for text representation. On the...
The problem of AMR-to-text generation is to recover a text representing ...
We propose a query-based generative model for solving both tasks of ques...
In recent years, many deep-learning based models are proposed for text
c...
This paper addresses the task of AMR-to-text generation by leveraging
sy...
Question generation from a knowledge base (KB) is the task of generating...
Conventional word sense induction (WSI) methods usually represent each
i...