244 citations · 480 across the 41 of their papers we have counts for
42 papers
TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild
Huayang Li, Siheng Li, Deng Cai +5
Large language models with instruction-following abilities have revolutionized the field of artificial intelligence. These models show exceptional generalizability to tackle variou…
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
Yue Zhang, Yafu Li, Leyang Cui +13
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit h…
Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction
Piji Li, Shuming Shi
We investigate the problem of Chinese Grammatical Error Correction (CGEC) and present a new framework named Tail-to-Tail (\textbf{TtT}) non-autoregressive sequence prediction to ad…
TexSmart: A Text Understanding System for Fine-Grained NER and Enhanced Semantic Analysis
Haisong Zhang, Lemao Liu, Haiyun Jiang +14
This technique report introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities. Com…
Dialogue Response Selection with Hierarchical Curriculum Learning
Yixuan Su, Deng Cai, Qingyu Zhou +6
We study the learning of a matching model for dialogue response selection. Motivated by the recent finding that models trained with random negative samples are not ideal in real-wo…
Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition
Yangming Li, Lemao Liu, Shuming Shi
In many scenarios, named entity recognition (NER) models severely suffer from unlabeled entity problem, where the entities of a sentence may not be fully annotated. Through empiric…
Segmenting Natural Language Sentences via Lexical Unit Analysis
Yangming Li, Lemao Liu, Shuming Shi
In this work, we present Lexical Unit Analysis (LUA), a framework for general sequence segmentation tasks. Given a natural language sentence, LUA scores all the valid segmentation…
When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models
Changlong Yu, Jialong Han, Peifeng Wang +4
We address hypernymy detection, i.e., whether an is-a relationship exists between words (x, y), with the help of large textual corpora. Most conventional approaches to this task ha…
On the Sub-Layer Functionalities of Transformer Decoder
Yilin Yang, Longyue Wang, Shuming Shi +3
There have been significant efforts to interpret the encoder of Transformer-based encoder-decoder architectures for neural machine translation (NMT); meanwhile, the decoder remains…
Evaluating Explanation Methods for Neural Machine Translation
Jierui Li, Lemao Liu, Huayang Li +3
Recently many efforts have been devoted to interpreting the black-box NMT models, but little progress has been made on metrics to evaluate explanation methods. Word Alignment Error…
On the Inference Calibration of Neural Machine Translation
Shuo Wang, Zhaopeng Tu, Shuming Shi +1
Confidence calibration, which aims to make model predictions equal to the true correctness measures, is important for neural machine translation (NMT) because it is able to offer u…
Understanding Learning Dynamics for Neural Machine Translation
Conghui Zhu, Guanlin Li, Lemao Liu +2
Despite the great success of NMT, there still remains a severe challenge: it is hard to interpret the internal dynamics during its training process. In this paper we propose to und…
Detecting and Understanding Generalization Barriers for Neural Machine Translation
Guanlin Li, Lemao Liu, Conghui Zhu +2
Generalization to unseen instances is our eternal pursuit for all data-driven models. However, for realistic task like machine translation, the traditional approach measuring gener…
SongNet: Rigid Formats Controlled Text Generation
Piji Li, Haisong Zhang, Xiaojiang Liu +1
Neural text generation has made tremendous progress in various tasks. One common characteristic of most of the tasks is that the texts are not restricted to some rigid formats when…
The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection
Zibo Lin, Deng Cai, Yan Wang +3
Response selection plays a vital role in building retrieval-based conversation systems. Despite that response selection is naturally a learning-to-rank problem, most prior works ta…
CASE: Context-Aware Semantic Expansion
Jialong Han, Aixin Sun, Haisong Zhang +2
In this paper, we define and study a new task called Context-Aware Semantic Expansion (CASE). Given a seed term in a sentential context, we aim to suggest other terms that well fit…
Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks
Yong Wang, Longyue Wang, Shuming Shi +2
The key challenge of multi-domain translation lies in simultaneously encoding both the general knowledge shared across domains and the particular knowledge distinctive to each doma…
Neuron Interaction Based Representation Composition for Neural Machine Translation
Jian Li, Xing Wang, Baosong Yang +3
Recent NLP studies reveal that substantial linguistic information can be attributed to single neurons, i.e., individual dimensions of the representation vectors. We hypothesize tha…
A Discrete CVAE for Response Generation on Short-Text Conversation
Jun Gao, Wei Bi, Xiaojiang Liu +3
Neural conversation models such as encoder-decoder models are easy to generate bland and generic responses. Some researchers propose to use the conditional variational autoencoder(…
Semi-supervised Text Style Transfer: Cross Projection in Latent Space
Mingyue Shang, Piji Li, Zhenxin Fu +4
Text style transfer task requires the model to transfer a sentence of one style to another style while retaining its original content meaning, which is a challenging problem that h…
Towards Understanding Neural Machine Translation with Word Importance
Shilin He, Zhaopeng Tu, Xing Wang +3
Although neural machine translation (NMT) has advanced the state-of-the-art on various language pairs, the interpretability of NMT remains unsatisfactory. In this work, we propose…
Multi-Granularity Self-Attention for Neural Machine Translation
Jie Hao, Xing Wang, Shuming Shi +2
Current state-of-the-art neural machine translation (NMT) uses a deep multi-head self-attention network with no explicit phrase information. However, prior work on statistical mach…
Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons
Jie Hao, Xing Wang, Shuming Shi +2
Recent studies have shown that a hybrid of self-attention networks (SANs) and recurrent neural networks (RNNs) outperforms both individual architectures, while not much is known ab…
Self-Attention with Structural Position Representations
Xing Wang, Zhaopeng Tu, Longyue Wang +1
Although self-attention networks (SANs) have advanced the state-of-the-art on various NLP tasks, one criticism of SANs is their ability of encoding positions of input words (Shaw e…